Difference between revisions of "S15: Hand Gesture Recognition using IR Sensors"

From Embedded Systems Learning Academy
Jump to: navigation, search
(Parts List & Cost)
(Conclusion)
 
(79 intermediate revisions by the same user not shown)
Line 2: Line 2:
  
 
== Abstract ==
 
== Abstract ==
The aim of the project is to develop hand gesture recognition system using grid of IR proximity
+
<p style="text-indent: 1em; text-align: justify;">
sensors. Hand gestures like pan, thumbs-up, moving hand back and forth, up and down or left and right
+
The aim of the project is to develop hand gesture recognition system using grid of IR proximity sensors. Various hand gestures like swipe, pan etc. can be recognized. These gestures can be used to control different devices or can be used in various applications. The system will recognize different hand gestures based on the values received from IR proximity sensors. We have used Qt to develop the application to demonstrate the working of the project.
can be recognized. These gestures can be used to control different devices or can be used in various
+
</p>
applications.The system will recognize different hand gestures based on the IR proximity sensor values.
 
  
 
== Objectives & Introduction ==
 
== Objectives & Introduction ==
 +
<p style="text-indent: 1em; text-align: justify;">
 +
We use various hand gestures in our day-to-day life to communicate while trying to explain someone something, direct them somewhere etc. It would be so cool if we could communicate with various applications running on the computers or different devices around us understand the hand gestures and give the expected output.
  
The idea is to make a 3x3 grid of using IR proximity sensors, and connect them via analog multiplexers to the ADC pins on SJONE board. As we move our hand in front of the sensor grid, the corresponding values of the sensors will change in a specific pattern. We will map this specific change in values to a gesture. Similarly we will be able to map gestures such as swipe left, swipe right, swipe up and swipe down.
+
In order to achieve this, we are using a 3-by-3 grid of analog IR proximity sensors and connecting these sensors via multiplexers to the ADC pins on SJOne Board. As a hand is moved in front of the sensors, the sensor values would in a particular pattern enabling us to detect the gesture and instruct the application to perform the corresponding action.
 
+
</p>
 
 
IR Sensors- For the project we are using sensors manufactured by Sharp to determine distance from the objects. The sensors have a range from 10 to 80 cm. The analog voltage output varies with the distance of the object, it is 3 Volts when an object is 10 cm away while it is 0.4v when object is 80 cm away. The ideal operating voltage for the sensor is 4.5 to 5.5 volts.
 
 
 
 
 
Analog Multiplexers- We are also using 3 Analog 4:1 multiplexers. This is because SJONE board only has 3 ADC pins where as our sensor grid consists of 9 sensors. The GPIO pins of SJONE board will act as select lines to the multiplexers. The select lines will be common to all multiplexers.  
 
 
 
 
=== Team Members & Responsibilities ===
 
=== Team Members & Responsibilities ===
 
*  Harita Parekh
 
*  Harita Parekh
Line 29: Line 24:
  
 
== Schedule ==
 
== Schedule ==
Show a simple table or figures that show your scheduled as planned before you started working on the project.  Then in another table column, write down the actual schedule so that readers can see the planned vs. actual goals.  The point of the schedule is for readers to assess how to pace themselves if they are doing a similar project.
 
  
 
{| class="wikitable"
 
{| class="wikitable"
Line 54: Line 48:
 
| Read the data sheet for sensors and understand its working. Test multiplexers
 
| Read the data sheet for sensors and understand its working. Test multiplexers
 
| Completed
 
| Completed
| align="center" |4/4/2015
+
| align="center" |4/04/2015
 
|-
 
|-
 
|-
 
|-
 
| 3
 
| 3
| align="center" |4/5/2015
+
| align="center" |4/05/2015
 
| align="center" |4/11/2015
 
| align="center" |4/11/2015
 
| Interfacing of sensors, multiplexers and controller
 
| Interfacing of sensors, multiplexers and controller
Line 72: Line 66:
  
 
* Implement algorithm to recognize left-to-right movement
 
* Implement algorithm to recognize left-to-right movement
| Ongoing
+
| Completed
|  
+
| align="center" |4/25/2015
 
|-
 
|-
 
|-
 
|-
Line 85: Line 79:
  
 
* Implement algorithm to recognize right-to-left movement
 
* Implement algorithm to recognize right-to-left movement
| Scheduled
+
| Completed
| align="center" |
+
| align="center" |5/02/2015
 
|-
 
|-
 
|-
 
|-
 
| 6
 
| 6
 
| align="center" |4/26/2015
 
| align="center" |4/26/2015
| align="center" |5/2/2015
+
| align="center" |5/02/2015
 
|  
 
|  
* Implement algorithm to recognize pan movement
 
 
 
* Implement algorithm to recognize down-to-up movement
 
* Implement algorithm to recognize down-to-up movement
  
* Develop the application module
+
* Develop the Qt application
| Scheduled
+
| Completed
| align="center" |
+
| align="center" |5/09/2015
 
|-
 
|-
 
|-
 
|-
 
| 7
 
| 7
| align="center" |5/3/2015
+
| align="center" |5/03/2015
| align="center" |5/9/2015
+
| align="center" |5/09/2015
 
| Testing and bug fixes
 
| Testing and bug fixes
| Scheduled
+
| Completed
| align="center" |
+
| align="center" |5/15/2015
 
|-
 
|-
 
|-
 
|-
Line 114: Line 106:
 
| align="center" |5/16/2015
 
| align="center" |5/16/2015
 
| Testing and final touches
 
| Testing and final touches
| Scheduled
+
| Completed
| align="center" |
+
| align="center" |5/22/2015
 
|-
 
|-
 
|-
 
|-
 
| 9
 
| 9
 +
| align="center" |5/21/2015
 +
| align="center" |5/24/2015
 +
| Report Completion
 +
| Completed
 +
| align="center" |5/24/2015
 +
|-
 +
|-
 +
| 10
 
| align="center" |5/25/2015
 
| align="center" |5/25/2015
 
| align="center" |5/25/2015
 
| align="center" |5/25/2015
 
| Final demo
 
| Final demo
 
| Scheduled
 
| Scheduled
| align="center" |
+
| align="center" |5/25/2015
 
|-
 
|-
|
 
 
|}
 
|}
  
Line 137: Line 136:
 
! scope="col"| Total Price
 
! scope="col"| Total Price
 
|-
 
|-
|-
+
! align="justify" scope="row"| 1
| 1
 
 
| Sharp Distance Measuring Sensor Unit (GP2Y0A21YK0F)
 
| Sharp Distance Measuring Sensor Unit (GP2Y0A21YK0F)
 
| align="center" |9
 
| align="center" |9
Line 144: Line 142:
 
| $134.55
 
| $134.55
 
|-
 
|-
|-
+
! align="justify" scope="row"| 2
| 2
 
 
| STMicroelectronics Dual 4-Channel Analog Multiplexer/Demultiplexer (M74HC4052)
 
| STMicroelectronics Dual 4-Channel Analog Multiplexer/Demultiplexer (M74HC4052)
 
| align="center" |3
 
| align="center" |3
| $
+
| $0.56
| $
+
| $1.68
 
|-
 
|-
|-
+
! align="justify" scope="row"| 3
| 3
 
 
| SJ-One Board
 
| SJ-One Board
 
| align="center" |1
 
| align="center" |1
Line 158: Line 154:
 
| $80
 
| $80
 
|-
 
|-
 +
! align="justify" scope="row"| 4
 +
| USB-to-UART converter
 +
| align="center" |1
 +
| $7
 +
| $7
 +
|-
 +
! align="left" colspan="4" | Total (excluding shipping and taxes)
 +
| $223.23
 
|}
 
|}
  
 
== Design & Implementation ==
 
== Design & Implementation ==
The design section can go over your hardware and software design. Organize this section using sub-sections that go over your design and implementation.
+
=== Hardware Design ===
 +
The image shows the setup of the project.<br>
 +
[[File:S15 244 Grp10 Ges system setup.jpg|800px|center]]<br>
 +
<center>Figure 1: Setup of the project</center>
 +
<br>
 +
<table>
 +
<tr valign="top">
 +
<b><i>System Block Diagram:</i></b>
 +
</tr>
 +
<br>
 +
<tr>
 +
<td valign="top" align="center">
 +
[[File:S15 244 Grp10 Ges block diagram.png|700px|center]]<br>
 +
<center>Figure 2: System Block Diagram</center> <br>
 +
</td>
 +
</tr>
  
=== Hardware Design ===
+
<tr align="justify">
Discuss your hardware design here. Show detailed schematics, and the interface here.
+
<p style="text-indent: 1em; text-align: justify;">
 +
The system consists of 9 IR proximity sensors, which are arranged in 3x3 grid. The output of the sensors is given to the Analog-to-Digital convertor on the SJOne Board to get the digital equivalent of the voltage given by the sensors. Since there are only 3 ADC channels exposed on the pins on the board, we cannot connect all the sensors directly to the board. For these we have used three multiplexers, which has 3 sensors each connected to its input. The output of the multiplexers is connected to ADC. SJOne board is connected to the laptop via UART-to-USB connection.</p>
 +
</tr>
 +
 
 +
<tr>
 +
<td valign="top" align="justify" width=950px>
 +
<b><i>Proximity Sensor:</i></b>
 +
<br>
 +
<p style="text-indent: 1em; text-align: justify;">
 +
This sensor by Sharp measures the distance from an obstacle by bouncing IR rays off the obstacle. This sensor can measure distances from 10 to 80 cms. The sensor returns an analog voltage corresponding to the distance from the obstacle. Depending on which sensor returns valid values, validations could be made and hand movement can be determined. The voltage returned by the sensor increases as the obstacle approaches the sensor. There is no external circuitry required for this sensor. The operating voltage recommended for this sensor is 4.5V to 5.5V.</p>
 +
</td>
 +
<td>
 +
[[File:S15 244 G10 Ges sensor.jpg|200px]]<br>
 +
<center>Figure 3: IR Proximity Sensor</center><br>
 +
</td>
 +
</tr>
 +
 
 +
<tr>
 +
<td valign="top" align="justify" width=950px>
 +
<b><i>Multiplexer:</i></b>
 +
<br>
 +
<p style="text-indent: 1em; text-align: justify;">
 +
The chip used in the project is M74HC4052 from STMicroelectronics. This is a dual 4-channel multiplexer/demultiplexer. Due to shortage of ADC pins to interface with the sensors, use of multiplexer is required. The multiplexer takes input from three sensors and enables only one of them at the output. The program logic decides which sensor’s output should be enabled at the multiplexer’s output. A and B control signals select one of the channel out of the four. The operating voltage for the multiplexer is 2 to 6V.</p>
 +
</td>
 +
<td>
 +
[[File:S15 244 G10 Ges mux.jpg|200px]]<br>
 +
<center>Figure 4: 4-Channel Dual Multiplexer</center><br>
 +
</td>
 +
</tr>
 +
 
 +
<tr>
 +
<td valign="top" align="justify" width=950px>
 +
<b>USB-to-UART converter:</b>
 +
<br>
 +
<p style="text-indent: 1em; text-align: justify;">
 +
To communicate to SJONE board over UART there is a need an USB to serial converter and a MAX232 circuit to convert the voltage levels to TTL, which the SJONE board understands. Instead it’s better to use a USB-to-UART converter to avoid the multiple conversions. This is done using CP2102 IC, which is similar to a FTDI chip.</p>
 +
</td>
 +
<td>
 +
[[File:S15_244_Grp10_Ges_UART_to_USB.JPG|200px]]<br>
 +
<center>Figure 5: USB-to-UART chip</center><br>
 +
</td>
 +
</tr>
 +
</table>
  
 
=== Hardware Interface ===
 
=== Hardware Interface ===
In this section, you can describe how your hardware communicates, such as which BUSes used. You can discuss your driver implementation here, such that the '''Software Design''' section is isolated to talk about high level workings rather than inner working of your project.
+
<table>
 +
<tr>
 +
<td valign="top" width=1150px>
 +
<center><i>Pin connections for IR Sensor to Multiplexer:</i></center><br>
 +
[[File:S15 244 Grp10 Ges sensor-to-mux.png|600px|center]]<br>
 +
<center>Figure 6: Pin connections for IR Sensor to Multiplexer</center><br>
 +
</td>
 +
</tr>
 +
</table>
 +
<table>
 +
<tr>
 +
<td valign="top" align="center" width=600px>
 +
<br>
 +
<i>Pin connections on SJOne board:</i><br>
 +
[[File:S15 244 Grp10 Ges sjone pinouts.png|400px]]<br><br>
 +
Figure 7: Pin connections on SJOne board<br>
 +
</td>
 +
<td valign="top" align="center">
 +
<br>
 +
<i>Connections between SJOne board and USB-to-UART Converter:</i><br>
 +
[[File:S15 244 Grp10 Ges SJOne to UART.JPG|360px|x400px]]<br>
 +
Figure 8: Connections between SJOne board and USB-to-UART Converter<br>
 +
</td>
 +
</tr>
 +
</table>
  
 
=== Software Design ===
 
=== Software Design ===
Show your software design. For example, if you are designing an MP3 Player, show the tasks that you are using, and what they are doing at a high level. Do not show the details of the code. For example, do not show exact code, but you may show psuedocode and fragments of code. Keep in mind that you are showing DESIGN of your software, not the inner workings of it.
+
<table>
 +
<tr>
 +
<td valign="top" align="justify" width=850px>
 +
<b><font size="2.5">Initialization</font></b><br>
 +
<p style="text-indent: 1em; text-align: justify;">
 +
SJOne board has 3 ADC pins exposed on Port 0 (0.26) and Port 1 (1.30 and 1.31). To use these pins as ADC, the function should be selected in PINSEL.</p>
 +
<p style="text-indent: 1em; text-align: justify;">
 +
The GPIO pins on Port 2 are connected to the select pins on multiplexer. These pins should be initialized as output pins.
 +
Once, initialization is completed, the function for normalizing the sensor values is called.
 +
</p>
 +
</td>
 +
<td valign="top">
 +
<br>
 +
[[File:S15 244 Grp10 Ges sensor init.png|center|160px|x400px]]<br>
 +
<center>Figure 9: Flowchart for initialization of ADC and multiplexer </center><br>
 +
</td>
 +
</tr>
 +
<tr>
 +
<td valign="top" align="justify" width=850px>
 +
<br><br>
 +
<p style="text-indent: 1em; text-align: justify;">
 +
SJOne board uses UART 3 to communicate with the QT application. UART 3 is initialized to baud rate of 9600 with receiver buffer as 0 and transmission buffer as 32 bytes. Once initialization is completed, the function for processing sensor values is called.</p>
 +
</td>
 +
<td valign="top">
 +
<br><br>
 +
[[File:S15 244 Grp10 Ges process init.png|center|160px|x300px]]<br>
 +
<center>Figure 10: Flowchart for initialization of UART and process </center><br>
 +
</td>
 +
</tr>
 +
</table>
 +
 
 +
<table>
 +
<tr>
 +
<td valign="top" align="justify" width=850px>
 +
<b><font size="2.5">Filter Algorithm</font></b><br>
 +
<p style="text-indent: 1em; text-align: justify;">
 +
The current value of sensor is fetched by setting the corresponding values on the multiplexer select pins and reading the output of the ADC. A queue of size 5 is maintained and the fetched value is inserted at the tail of the queue. This queue is sorted using bubble sort. The median value of the queue is checked to be greater than 2000 (sensor returns a voltage corresponding to a value greater than 2000 when the hand is near enough to it) and gesture array for that sensor is set accordingly.</p>
 +
</td>
 +
<td valign="top">
 +
<br>
 +
[[File:S15 244 Grp10 Ges filter task.png|center|320px]]<br>
 +
<center>Figure 11: Flowchart for filter algorithm</center><br>
 +
</td>
 +
</tr>
 +
</table>
 +
 
 +
<table>
 +
<tr>
 +
<td valign="top" align="justify" width=900px>
 +
<b><font size="2.5">Gesture Recognition Algorithm</font></b><br>
 +
<p style="text-indent: 1em; text-align: justify;">
 +
Different sets of sensors are monitored in order to recognize a valid pattern in the sensor output and thereby recognize the gesture pattern.<br>
 +
(We have assumed that the sensors are numbered 0 through 8 and the corresponding value for the sensor is set by the filter algorithm in gesture[] array). <br></p>
 +
</td>
 +
</tr>
 +
</table>
 +
 
 +
<table>
 +
<tr>
 +
<td rowspan="2" valign="top">
 +
<i>Pattern 1:</i><br>
 +
[[File:S15 244 Grp10 Ges process1.png|left|400px]]<br>
 +
<center>Figure 12: Flowchart for selection of pattern 1 </center><br>
 +
</td>
 +
<td valign="top" align="justify"><br>
 +
<p style="text-indent: 1em; text-align: justify;">
 +
Here the three sensors present at the top left corner are monitored.
 +
* If sensor1 value is zero
 +
** Check the values of sensors in the second column. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
 +
*** Check the values of sensors in the third column. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
 +
*** Send “Right” to UART 3.
 +
</p>
 +
</td>
 +
<td valign="top">
 +
<br><br>
 +
[[File:S15 244 Grp10 Ges tlright.gif|center|100px]]<br>
 +
</td>
 +
</tr>
 +
<tr>
 +
<td valign="top" align="justify"><br>
 +
* If sensor3 value is zero
 +
** Check the values of sensors in the second row. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
 +
*** Check the values of sensors in the third row. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
 +
*** Send “Down ” to UART 3.
 +
</td>
 +
<td valign="top">
 +
<br><br>
 +
[[File:S15 244 Grp10 Ges tldown.gif|center|100px]]<br>
 +
</td>
 +
</tr>
 +
</table>
 +
 
 +
<table>
 +
<tr>
 +
<td rowspan="2" valign="top">
 +
<i>Pattern 2:</i><br>
 +
[[File:S15 244 Grp10 Ges process2.png|left|400px]]<br>
 +
<center>Figure 13: Flowchart for selection of pattern 2 </center><br>
 +
</td>
 +
<td valign="top" align="justify"><br>
 +
<p style="text-indent: 1em; text-align: justify;">
 +
Here the three sensors present at the top right corner are monitored.
 +
* If sensor1 value is zero
 +
** Check the values of sensors in the second column. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
 +
*** Check the values of sensors in the first column. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
 +
*** Send “Left ” to UART 3.
 +
</p>
 +
</td>
 +
<td valign="top">
 +
<br><br>
 +
[[File:S15 244 Grp10 Ges trleft.gif|center|100px]]<br>
 +
</td>
 +
</tr>
 +
<tr>
 +
<td valign="top" align="justify"><br>
 +
* If sensor5 value is zero
 +
** Check the values of sensors in the second row. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
 +
*** Check the values of sensors in the third row. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
 +
*** Send “Down ” to UART 3.
 +
</td>
 +
<td valign="top">
 +
<br><br>
 +
[[File:S15 244 Grp10 Ges trdown.gif|center|100px]]<br>
 +
</td>
 +
</tr>
 +
</table>
 +
 
 +
<table>
 +
<tr>
 +
<td rowspan="2" valign="top">
 +
<i>Pattern 3:</i><br>
 +
[[File:S15 244 Grp10 Ges process3.png|left|400px]]<br>
 +
<center>Figure 14: Flowchart for selection of pattern 3 </center><br>
 +
</td>
 +
<td valign="top" align="justify"><br>
 +
<p style="text-indent: 1em; text-align: justify;">
 +
Here the three sensors present at the bottom left corner are monitored.
 +
* If sensor7 value is zero
 +
** Check the values of sensors in the second column. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
 +
*** Check the values of sensors in the third column. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
 +
*** Send “Right ” to UART 3.
 +
</p>
 +
</td>
 +
<td valign="top">
 +
<br><br>
 +
[[File:S15 244 Grp10 Ges blright.gif|center|100px]]<br>
 +
</td>
 +
</tr>
 +
<tr>
 +
<td valign="top" align="justify"><br>
 +
* If sensor3 value is zero
 +
** Check the values of sensors in the second row. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
 +
*** Check the values of sensors in the first row. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
 +
*** Send “Up ” to UART 3.
 +
</td>
 +
<td valign="top">
 +
<br><br>
 +
[[File:S15 244 Grp10 Ges blup.gif|center|100px]]<br>
 +
</td>
 +
</tr>
 +
</table>
 +
 
 +
<table>
 +
<tr>
 +
<td rowspan="2" valign="top">
 +
<i>Pattern 4:</i><br>
 +
[[File:S15 244 Grp10 Ges process4.png|left|400px]]<br>
 +
<center>Figure 15: Flowchart for selection of pattern 4 </center><br>
 +
</td>
 +
<td valign="top" align="justify"><br>
 +
<p style="text-indent: 1em; text-align: justify;">
 +
Here the three sensors present at the bottom right corner are monitored.
 +
* If sensor7 value is zero
 +
** Check the values of sensors in the second column. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
 +
*** Check the values of sensors in the first column. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
 +
*** Send “Left ” to UART 3.
 +
</p>
 +
</td>
 +
<td valign="top">
 +
<br><br>
 +
[[File:S15 244 Grp10 Ges brleft.gif|center|100px]]<br>
 +
</td>
 +
</tr>
 +
<tr>
 +
<td valign="top" align="justify"><br>
 +
* If sensor5 value is zero
 +
** Check the values of sensors in the second row. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
 +
*** Check the values of sensors in the first row. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
 +
*** Send “Up ” to UART 3.
 +
</td>
 +
<td valign="top">
 +
<br><br>
 +
[[File:S15 244 Grp10 Ges brup.gif|center|100px]]<br>
 +
</td>
 +
</tr>
 +
</table>
 +
 
 +
<table>
 +
<tr>
 +
<td valign="top" align="justify" width=850px>
 +
<b><font size="2.5">Application Development</font></b><br>
 +
<i><font size="2">Qt Software</font></i><br>
 +
<p style="text-indent: 1em; text-align: justify;">
 +
Qt is a cross-platform application framework that is widely used in developing application software that can be run on various software and hardware platforms with little or no change in the underlying codebase while having the speed and the power of native application.</p>
 +
<p style="text-indent: 1em; text-align: justify;">
 +
It is mainly used to make GUI based applications but there can be applications such as consoles or command-line applications developed in Qt. Qt is preferred by many application programmers as it helps in developing GUI applications in C++ as it uses the standard C++ libraries for backend.</p>
 +
<p style="text-indent: 1em; text-align: justify;">
 +
Platforms supported by Qt are:
 +
* Android
 +
* Embedded Linux
 +
* Integrity
 +
* iOS
 +
* OSX
 +
* QNX
 +
* VxWorks
 +
* Waylands
 +
* Windows
 +
* Windows CE
 +
* Windows RT
 +
* X11
 +
</p>
 +
<p style="text-indent: 1em; text-align: justify;">
 +
Qt applications are highly portable from one platform to other as Qt first runs a Qmake function before compiling the source code. It is very similar to ‘cmake’ which is used for cross platform compilation of any source code. The qmake auto generates a makefile depending on the operating system and the compiler used for the project. So if a project is to be ported from windows to linux based system then the qmake auto generated a new makefile with arguments and parameters that the g++ compiler expects.</p>
 +
</td>
 +
<td width=300px align="center">
 +
[[File:S15 244 Grp10 Ges qtdevices.png|300px]]<br>
 +
<center>Figure 16: Devices supporting Qt</center><br>
 +
[[File:S15 244 Grp10 Ges qt-sdk.png|300px]]<br>
 +
<center>Figure 17: Qt-SDK</center><br>
 +
</td>
 +
</tr>
 +
</table>
 +
 
 +
<table>
 +
<tr>
 +
<td valign="top" align="justify" width=1150px>
 +
<i><font size="2">Gesture Recognition application on Qt</font></i><br>
 +
<p style="text-indent: 1em; text-align: justify;">
 +
Once the gesture is recognized on the SJONE board, a message is sent over UART3 stating which gesture was sensed. The Qt application gets this message from the COM port and scrolls the images left and right based on the left/right gesture and it moves a vertical slider up and down which in turn changes the value on a LCD screen display.</p>
 +
<p style="text-indent: 1em; text-align: justify;">
 +
The application opens up in a window that has 2 tabs, config and App. The config tab includes the fields required to open the COMM port and test the COMM port using a loopback connection.</p>
 +
[[File:S15 244 Grp10 Ges qt tab1.JPG|center|650px|x434px]]<br>
 +
<center>Figure 18: Configuration Tab</center><br>
 +
<p style="text-indent: 1em; text-align: justify;">This tab has the following QObjects.</p><br>
 +
[[File:S15 244 Grp10 Ges table1.png|center|650px|x480px]]<br>
 +
<center>Table 1: QObjects used for Configuration Tab</center><br>
 +
<p style="text-indent: 1em; text-align: justify;">The App tab includes the objects required to change images and change the value in the vertical slider and lcd number display.</p><br>
 +
[[File:S15 244 Grp10 Ges qt tab2.JPG|center|650px|x434px|]]<br>
 +
<center>Figure 19: Application Tab</center><br>
 +
<p style="text-indent: 1em; text-align: justify;">This tab has the following Qobjects.</p><br>
 +
[[File:S15 244 Grp10 Ges table2.png|center|650px|x420px]]<br>
 +
<center>Table 2: QObjects used for Application Tab</center><br>
 +
 
 +
 
 +
</td>
 +
</tr>
 +
</table>
  
 
=== Implementation ===
 
=== Implementation ===
This section includes implementation, but again, not the details, just the high level. For example, you can list the steps it takes to communicate over a sensor, or the steps needed to write a page of memory onto SPI Flash. You can include sub-sections for each of your component implementation.
+
==== Application Logic ====
 +
<table>
 +
<tr>
 +
<td valign="top" align="justify" width=1150px>
 +
<p style="text-indent: 1em; text-align: justify;">
 +
The below diagram shows the setup of the files used in the project.</p><br>
 +
[[File:S15 244 Grp10 Ges code structure.png|center|600px|x400px]]<br>
 +
<center>Figure 20: Code Structure tree diagram</center><br><br>
 +
<p style="text-indent: 1em; text-align: justify;">The main function creates the tasks required for the application namely, SensorTask, WaitTask and ProcessSensor.</p><br>
 +
[[File:S15 244 Grp10 Ges main.PNG|center]]<br>
 +
<center>Figure 21: Main file snippet</center><br><br>
 +
The tasks are declared in Hand_Gesture.hpp file.<br>
 +
[[File:S15 244 Grp10 Ges gesturehpp.PNG|center]]<br>
 +
<center>Figure 22: Header file snippet</center><br>
 +
<p style="text-indent: 1em; text-align: justify;">
 +
This file also includes the enumerations required in the program logic.
 +
* sensorNo_t: This enumeration assigns numbers to the sensor from 0 through 8.
 +
* portPins_t: This enumeration assigns the shifting logic to P2_0 through P2_5 for better readability.</p>
 +
<p style="text-indent: 1em; text-align: justify;">
 +
Hand_Gesture.cpp file contains the definitions of all the functions as listed below.</p><br>
 +
[[File:S15 244 Grp10 Ges gesturecpp.PNG|center]]<br>
 +
<center>Figure 23: Source File snippet showing the function defined</center><br>
 +
<p style="text-indent: 1em; text-align: justify;">
 +
The WaitTask is used internally in ProcessSensor to wait for values of sensor to change while navigating through the above described algorithm. This task enables the system to wait for maximum of 5 seconds to receive any change of values in the sensor. If after 5 seconds, the sensor values are not as desired by the algorithm (to proceed to next stage), the sensor values are concluded to be false positives and further execution is skipped.</p>
 +
 
 +
<p style="text-indent: 1em; text-align: justify;">The constructor of SensorTask includes the initialization of pins for ADC and Port 2 pins used as select lines for the multiplexer.</p><br>
 +
[[File:S15 244 Grp10 Ges pins init.png|center]]<br>
 +
<center>Figure 24: Pin initialization</center><br>
 +
<p style="text-indent: 1em; text-align: justify;">UART 3 is initialized using the Singleton pattern.</p><br>
 +
[[File:S15 244 Grp10 Ges Singleton.png|center]]<br>
 +
<center>Figure 25: UART initialization using Singleton Pattern</center><br>
 +
<p style="text-indent: 1em; text-align: justify;">The init function of UART is used to initialize UART 3 to communicate at the baud rate of 9600. Since the application will only be sending values to the Qt application and not expecting any replies, the receive buffer is set to zero and the transmission buffer is set to 32 bytes.</p><br>
 +
[[File:S15 244 Grp10 Ges UART init.png|center]]<br>
 +
<center>Figure 26: UART driver initialization</center><br><br>
 +
</td>
 +
</tr>
 +
</table>
 +
 
 +
==== Qt Application Implementation ====
 +
 
 +
<table>
 +
<tr>
 +
<td valign="top" align="justify" width=1150px>
 +
<i>Includes and app initialization</i><br>
 +
This sections includes all header files required for the app and the constructor and destructor for the app.
 +
As we are displaying multiple images in the app the path of these images have to be hardcoded. We also define an enum to capture the received gesture. An instance of the serial port is also created in the constructor, and an initial welcome image (SJSU logo) is displayed on the app.<br>
 +
[[File:S15 244 Grp10 Ges qt includes.JPG|center]]<br>
 +
<center>Figure 27: Snippet of initialization</center><br>
 +
<i>Configuration COM port</i><br>
 +
The COM port is configured in this section of the code, the name of the COM port and the baud rate is picked up from the lineEdits present on the config tab and passed to populate the structure of the serial port. If there is an error opening the COM port then an error message is displayed. The COM port is closed once the disconnect button is pressed.<br>
 +
[[File:S15 244 Grp10 Ges qt comport.JPG|center]]<br>
 +
<center>Figure 28: Configuration of COM port</center><br>
 +
<i>Serial receive and loopback test</i><br>
 +
This section includes the code to copy all the data received in the receive buffer parse it and take the decision on which kind of gesture was received and take the appropriate decision. The loop back section picks up anything written on the Tx lineEdit and displays the received buffer on the rx lineEdit.<br>
 +
[[File:S15 244 Grp10 Ges qt recv loopback.JPG|center]]<br>
 +
<center>Figure 29: Code to test serial receive using loopback</center><br>
 +
<i>Open Image</i><br>
 +
The logic to switch between images and to loop through the images is implemented here.<br>
 +
[[File:S15 244 Grp10 Ges qt image.JPG|center]]<br>
 +
<center>Figure 30: Code to switch between images</center><br>
 +
<i>Scroll</i><br>
 +
The position of the vertical slider is changed depending on the up/down gesture, the LCDnumber display is used to display the position (value) of the vertical slider. The value ranges from 0-99 and loops through if the value is greater 99 or smaller than 0.<br>
 +
[[File:S15 244 Grp10 Ges qt scroll.JPG|center]]<br>
 +
<center>Figure 31: Code to scroll the vertical slider</center><br>
 +
</td>
 +
</tr>
 +
</table>
 +
 
 +
==== Setup and Working ====
 +
<table>
 +
<tr>
 +
<td valign="top" align="justify" width=1150px>
 +
<b>Sensor setup</b><br>
 +
[[File:S15 244 Grp10 Ges sensor setup.jpg|center|450px|x600px]]<br>
 +
<center>Figure 32: Sensor setup</center><br>
 +
<br>
 +
<b>Screenshots of Qt application</b><br>
 +
[[File:S15 244 Grp10 Ges Qt config working.JPG|center|700px|x540px]]<br>
 +
<center>Figure 33: Configuration screen</center><br>
 +
[[File:S15 244 Grp10 Ges qt working demo.JPG|center|700px|x540px]]<br>
 +
<center>Figure 34: Application screen</center><br>
 +
</td>
 +
</tr>
 +
</table>
  
 
== Testing & Technical Challenges ==
 
== Testing & Technical Challenges ==
Describe the challenges of your project.  What advise would you give yourself or someone else if your project can be started from scratch again?
+
<b>Challenge #1:</b><br>
Make a smooth transition to testing section and described what it took to test your project.
+
<p style="text-indent: 1em; text-align: justify;">
 +
The sensor produces many spikes giving false positive outputs.</p>
  
Include sub-sections that list out a problem and solution, such as:
+
<i>Resolution:</i><br>
 +
<p style="text-indent: 1em; text-align: justify;">
 +
In order to overcome spikes received and deal with false positive, normalization of the sensor output is done. A circular queue of size 5 is maintained for each sensor and each value received from the ADC is stored at the end on the queue. This queue is then sorted and only the median value is considered for computation. This reduces the false positives to a great extent.<br>
 +
</p><br>
 +
<b>Challenge #2:</b><br>
 +
<p style="text-indent: 1em; text-align: justify;">
 +
Number of sensors used was far greater than the available ADC pins.</p>
  
=== My Issue #1 ===
+
<i>Resolution:</i><br>
Discuss the issue and resolution.
+
<p style="text-indent: 1em; text-align: justify;">
 +
Even if we had 9 ADC pins converting values of 9 sensors, we would still be reading the each sensor one by one. Keeping this in mind, in order to overcome the deficit of ADC pins, we have used multiplexer which takes the input from 3 sensors at a time and gives the output of only the selected sensor. In this way, we could read the output of any sensor at any given point of time. The introduction of multiplexer introduces a lag but this lag is not long enough to hinder the operation of the application.<br>
 +
</p><br>
 +
<b>Challenge #3:</b><br>
 +
<p style="text-indent: 1em; text-align: justify;">
 +
Qt being a new application for all the team members, it was a challenge to learn its programming style and use the objects.<br>
 +
</p><br>
 +
<b>Challenge #4:</b><br>
 +
<p style="text-indent: 1em; text-align: justify;">
 +
Setting up the serial port communication in Qt.
 +
</p>
  
 
== Conclusion ==
 
== Conclusion ==
Conclude your project here. You can recap your testing and problems. You should address the "so what" part here to indicate what you ultimately learnt from this project. How has this project increased your knowledge?
+
<p style="text-indent: 1em; text-align: justify;">
 +
Gesture recognition using IR sensors was a very interesting and challenging project. The main areas where we enjoyed working were the development of the gesture recognition algorithm and sensor filter algorithm.  
 +
This project increased our knowledge in:
 +
* Developing filters for analog sensors
 +
* Working with the sensor itself
 +
* Reading datasheets for the multiplexer and sensor
 +
* Hands-on experience in Qt application
 +
* Using Singleton pattern for UART
 +
</p>
 +
 
 +
<p style="text-indent: 1em; text-align: justify;">
 +
This project was developed in a small scale. Further work can be done to integrate this project in devices, which would help blind people to use software, which require manual intervention, seamlessly.
 +
</p>
  
 
=== Project Video ===
 
=== Project Video ===
Upload a video of your project and post the link here.
+
[https://youtu.be/Dev3LnjyL3Y Gesture Recognition using IP Proximity Sensors]
  
 
=== Project Source Code ===
 
=== Project Source Code ===
Line 195: Line 648:
 
== References ==
 
== References ==
 
=== Acknowledgement ===
 
=== Acknowledgement ===
Any acknowledgement that you may wish to provide can be included here.
+
<p style="text-indent: 1em; text-align: justify;">
 +
All the components where procurred from Amazon, Adafruit and digikey. We are thankful to Preet for his continuous guidance during the project.
 +
</p>
  
 
=== References Used ===
 
=== References Used ===
List any references used in project.
+
<p style="width: 700px; text-align: justify;">
 
+
[http://www.sharpsma.com/webfm_send/1208 IR Sensor Data Sheet]<br>
=== Appendix ===
+
[http://www.nxp.com/documents/data_sheet/LPC1769_68_67_66_65_64_63.pdf LPC_USER_MANUAL]<br>
You can list the references you used.
+
[http://www.st.com/web/en/resource/technical/document/datasheet/CD00002398.pdf Multiplexer Data Sheet]<br>
 +
[http://en.wikipedia.org/wiki/Qt_%28software%29 QT Software]<br>
 +
[http://www.socialledge.com/sjsu/index.php?title=S14:_Virtual_Dog Filter code refered from Spring'14 project Virtual Dog]
 +
</p>

Latest revision as of 03:43, 25 May 2015


Abstract

The aim of the project is to develop hand gesture recognition system using grid of IR proximity sensors. Various hand gestures like swipe, pan etc. can be recognized. These gestures can be used to control different devices or can be used in various applications. The system will recognize different hand gestures based on the values received from IR proximity sensors. We have used Qt to develop the application to demonstrate the working of the project.

Objectives & Introduction

We use various hand gestures in our day-to-day life to communicate while trying to explain someone something, direct them somewhere etc. It would be so cool if we could communicate with various applications running on the computers or different devices around us understand the hand gestures and give the expected output. In order to achieve this, we are using a 3-by-3 grid of analog IR proximity sensors and connecting these sensors via multiplexers to the ADC pins on SJOne Board. As a hand is moved in front of the sensors, the sensor values would in a particular pattern enabling us to detect the gesture and instruct the application to perform the corresponding action.

Team Members & Responsibilities

  • Harita Parekh
    • Implementing algorithm for gesture recognition
    • Implementation of sensor data filters
  • Shruti Rao
    • Implementing algorithm for gesture recognition
    • Interfacing of sensors, multiplexers and controller
  • Sushant Potdar
    • Implementation of final sensor grid
    • Development of the application module

Schedule

Week# Start Date End Date Task Status Actual Completion Date
1 3/22/2015 3/28/2015 Research on the sensors, order sensors and multiplexers Completed 3/28/2015
2 3/29/2015 4/4/2015 Read the data sheet for sensors and understand its working. Test multiplexers Completed 4/04/2015
3 4/05/2015 4/11/2015 Interfacing of sensors, multiplexers and controller Completed 4/15/2015
4 4/12/2015 4/18/2015
  • Implementation of sensor data filters
  • Implement algorithm to recognize left-to-right movement
Completed 4/25/2015
5 4/19/2015 4/25/2015
  • Implementation of final sensor grid
  • Implement algorithm to recognize up-to-down movement
  • Implement algorithm to recognize right-to-left movement
Completed 5/02/2015
6 4/26/2015 5/02/2015
  • Implement algorithm to recognize down-to-up movement
  • Develop the Qt application
Completed 5/09/2015
7 5/03/2015 5/09/2015 Testing and bug fixes Completed 5/15/2015
8 5/10/2015 5/16/2015 Testing and final touches Completed 5/22/2015
9 5/21/2015 5/24/2015 Report Completion Completed 5/24/2015
10 5/25/2015 5/25/2015 Final demo Scheduled 5/25/2015

Parts List & Cost

SR# Component Name Quantity Price per component Total Price
1 Sharp Distance Measuring Sensor Unit (GP2Y0A21YK0F) 9 $14.95 $134.55
2 STMicroelectronics Dual 4-Channel Analog Multiplexer/Demultiplexer (M74HC4052) 3 $0.56 $1.68
3 SJ-One Board 1 $80 $80
4 USB-to-UART converter 1 $7 $7
Total (excluding shipping and taxes) $223.23

Design & Implementation

Hardware Design

The image shows the setup of the project.

S15 244 Grp10 Ges system setup.jpg

Figure 1: Setup of the project


System Block Diagram:

The system consists of 9 IR proximity sensors, which are arranged in 3x3 grid. The output of the sensors is given to the Analog-to-Digital convertor on the SJOne Board to get the digital equivalent of the voltage given by the sensors. Since there are only 3 ADC channels exposed on the pins on the board, we cannot connect all the sensors directly to the board. For these we have used three multiplexers, which has 3 sensors each connected to its input. The output of the multiplexers is connected to ADC. SJOne board is connected to the laptop via UART-to-USB connection.

S15 244 Grp10 Ges block diagram.png

Figure 2: System Block Diagram

Proximity Sensor:

This sensor by Sharp measures the distance from an obstacle by bouncing IR rays off the obstacle. This sensor can measure distances from 10 to 80 cms. The sensor returns an analog voltage corresponding to the distance from the obstacle. Depending on which sensor returns valid values, validations could be made and hand movement can be determined. The voltage returned by the sensor increases as the obstacle approaches the sensor. There is no external circuitry required for this sensor. The operating voltage recommended for this sensor is 4.5V to 5.5V.

S15 244 G10 Ges sensor.jpg

Figure 3: IR Proximity Sensor

Multiplexer:

The chip used in the project is M74HC4052 from STMicroelectronics. This is a dual 4-channel multiplexer/demultiplexer. Due to shortage of ADC pins to interface with the sensors, use of multiplexer is required. The multiplexer takes input from three sensors and enables only one of them at the output. The program logic decides which sensor’s output should be enabled at the multiplexer’s output. A and B control signals select one of the channel out of the four. The operating voltage for the multiplexer is 2 to 6V.

S15 244 G10 Ges mux.jpg

Figure 4: 4-Channel Dual Multiplexer

USB-to-UART converter:

To communicate to SJONE board over UART there is a need an USB to serial converter and a MAX232 circuit to convert the voltage levels to TTL, which the SJONE board understands. Instead it’s better to use a USB-to-UART converter to avoid the multiple conversions. This is done using CP2102 IC, which is similar to a FTDI chip.

S15 244 Grp10 Ges UART to USB.JPG

Figure 5: USB-to-UART chip

Hardware Interface

Pin connections for IR Sensor to Multiplexer:

S15 244 Grp10 Ges sensor-to-mux.png

Figure 6: Pin connections for IR Sensor to Multiplexer


Pin connections on SJOne board:
S15 244 Grp10 Ges sjone pinouts.png

Figure 7: Pin connections on SJOne board


Connections between SJOne board and USB-to-UART Converter:
S15 244 Grp10 Ges SJOne to UART.JPG
Figure 8: Connections between SJOne board and USB-to-UART Converter

Software Design

Initialization

SJOne board has 3 ADC pins exposed on Port 0 (0.26) and Port 1 (1.30 and 1.31). To use these pins as ADC, the function should be selected in PINSEL.

The GPIO pins on Port 2 are connected to the select pins on multiplexer. These pins should be initialized as output pins. Once, initialization is completed, the function for normalizing the sensor values is called.


S15 244 Grp10 Ges sensor init.png

Figure 9: Flowchart for initialization of ADC and multiplexer



SJOne board uses UART 3 to communicate with the QT application. UART 3 is initialized to baud rate of 9600 with receiver buffer as 0 and transmission buffer as 32 bytes. Once initialization is completed, the function for processing sensor values is called.



S15 244 Grp10 Ges process init.png

Figure 10: Flowchart for initialization of UART and process

Filter Algorithm

The current value of sensor is fetched by setting the corresponding values on the multiplexer select pins and reading the output of the ADC. A queue of size 5 is maintained and the fetched value is inserted at the tail of the queue. This queue is sorted using bubble sort. The median value of the queue is checked to be greater than 2000 (sensor returns a voltage corresponding to a value greater than 2000 when the hand is near enough to it) and gesture array for that sensor is set accordingly.


S15 244 Grp10 Ges filter task.png

Figure 11: Flowchart for filter algorithm

Gesture Recognition Algorithm

Different sets of sensors are monitored in order to recognize a valid pattern in the sensor output and thereby recognize the gesture pattern.
(We have assumed that the sensors are numbered 0 through 8 and the corresponding value for the sensor is set by the filter algorithm in gesture[] array).

Pattern 1:

S15 244 Grp10 Ges process1.png

Figure 12: Flowchart for selection of pattern 1


Here the three sensors present at the top left corner are monitored.

  • If sensor1 value is zero
    • Check the values of sensors in the second column. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
      • Check the values of sensors in the third column. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
      • Send “Right” to UART 3.



S15 244 Grp10 Ges tlright.gif


  • If sensor3 value is zero
    • Check the values of sensors in the second row. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
      • Check the values of sensors in the third row. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
      • Send “Down ” to UART 3.



S15 244 Grp10 Ges tldown.gif

Pattern 2:

S15 244 Grp10 Ges process2.png

Figure 13: Flowchart for selection of pattern 2


Here the three sensors present at the top right corner are monitored.

  • If sensor1 value is zero
    • Check the values of sensors in the second column. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
      • Check the values of sensors in the first column. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
      • Send “Left ” to UART 3.



S15 244 Grp10 Ges trleft.gif


  • If sensor5 value is zero
    • Check the values of sensors in the second row. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
      • Check the values of sensors in the third row. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
      • Send “Down ” to UART 3.



S15 244 Grp10 Ges trdown.gif

Pattern 3:

S15 244 Grp10 Ges process3.png

Figure 14: Flowchart for selection of pattern 3


Here the three sensors present at the bottom left corner are monitored.

  • If sensor7 value is zero
    • Check the values of sensors in the second column. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
      • Check the values of sensors in the third column. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
      • Send “Right ” to UART 3.



S15 244 Grp10 Ges blright.gif


  • If sensor3 value is zero
    • Check the values of sensors in the second row. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
      • Check the values of sensors in the first row. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
      • Send “Up ” to UART 3.



S15 244 Grp10 Ges blup.gif

Pattern 4:

S15 244 Grp10 Ges process4.png

Figure 15: Flowchart for selection of pattern 4


Here the three sensors present at the bottom right corner are monitored.

  • If sensor7 value is zero
    • Check the values of sensors in the second column. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
      • Check the values of sensors in the first column. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
      • Send “Left ” to UART 3.



S15 244 Grp10 Ges brleft.gif


  • If sensor5 value is zero
    • Check the values of sensors in the second row. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
      • Check the values of sensors in the first row. If the combination of first two or last two sensors is 1, go to next step. Else, update the gesture array for these sensors and check.
      • Send “Up ” to UART 3.



S15 244 Grp10 Ges brup.gif

Application Development
Qt Software

Qt is a cross-platform application framework that is widely used in developing application software that can be run on various software and hardware platforms with little or no change in the underlying codebase while having the speed and the power of native application.

It is mainly used to make GUI based applications but there can be applications such as consoles or command-line applications developed in Qt. Qt is preferred by many application programmers as it helps in developing GUI applications in C++ as it uses the standard C++ libraries for backend.

Platforms supported by Qt are:

  • Android
  • Embedded Linux
  • Integrity
  • iOS
  • OSX
  • QNX
  • VxWorks
  • Waylands
  • Windows
  • Windows CE
  • Windows RT
  • X11

Qt applications are highly portable from one platform to other as Qt first runs a Qmake function before compiling the source code. It is very similar to ‘cmake’ which is used for cross platform compilation of any source code. The qmake auto generates a makefile depending on the operating system and the compiler used for the project. So if a project is to be ported from windows to linux based system then the qmake auto generated a new makefile with arguments and parameters that the g++ compiler expects.

S15 244 Grp10 Ges qtdevices.png

Figure 16: Devices supporting Qt

S15 244 Grp10 Ges qt-sdk.png

Figure 17: Qt-SDK

Gesture Recognition application on Qt

Once the gesture is recognized on the SJONE board, a message is sent over UART3 stating which gesture was sensed. The Qt application gets this message from the COM port and scrolls the images left and right based on the left/right gesture and it moves a vertical slider up and down which in turn changes the value on a LCD screen display.

The application opens up in a window that has 2 tabs, config and App. The config tab includes the fields required to open the COMM port and test the COMM port using a loopback connection.

S15 244 Grp10 Ges qt tab1.JPG

Figure 18: Configuration Tab

This tab has the following QObjects.


S15 244 Grp10 Ges table1.png

Table 1: QObjects used for Configuration Tab

The App tab includes the objects required to change images and change the value in the vertical slider and lcd number display.


S15 244 Grp10 Ges qt tab2.JPG

Figure 19: Application Tab

This tab has the following Qobjects.


S15 244 Grp10 Ges table2.png

Table 2: QObjects used for Application Tab


Implementation

Application Logic

The below diagram shows the setup of the files used in the project.


S15 244 Grp10 Ges code structure.png

Figure 20: Code Structure tree diagram


The main function creates the tasks required for the application namely, SensorTask, WaitTask and ProcessSensor.


S15 244 Grp10 Ges main.PNG

Figure 21: Main file snippet


The tasks are declared in Hand_Gesture.hpp file.

S15 244 Grp10 Ges gesturehpp.PNG

Figure 22: Header file snippet

This file also includes the enumerations required in the program logic.

  • sensorNo_t: This enumeration assigns numbers to the sensor from 0 through 8.
  • portPins_t: This enumeration assigns the shifting logic to P2_0 through P2_5 for better readability.

Hand_Gesture.cpp file contains the definitions of all the functions as listed below.


S15 244 Grp10 Ges gesturecpp.PNG

Figure 23: Source File snippet showing the function defined

The WaitTask is used internally in ProcessSensor to wait for values of sensor to change while navigating through the above described algorithm. This task enables the system to wait for maximum of 5 seconds to receive any change of values in the sensor. If after 5 seconds, the sensor values are not as desired by the algorithm (to proceed to next stage), the sensor values are concluded to be false positives and further execution is skipped.

The constructor of SensorTask includes the initialization of pins for ADC and Port 2 pins used as select lines for the multiplexer.


S15 244 Grp10 Ges pins init.png

Figure 24: Pin initialization

UART 3 is initialized using the Singleton pattern.


S15 244 Grp10 Ges Singleton.png

Figure 25: UART initialization using Singleton Pattern

The init function of UART is used to initialize UART 3 to communicate at the baud rate of 9600. Since the application will only be sending values to the Qt application and not expecting any replies, the receive buffer is set to zero and the transmission buffer is set to 32 bytes.


S15 244 Grp10 Ges UART init.png

Figure 26: UART driver initialization


Qt Application Implementation

Includes and app initialization
This sections includes all header files required for the app and the constructor and destructor for the app. As we are displaying multiple images in the app the path of these images have to be hardcoded. We also define an enum to capture the received gesture. An instance of the serial port is also created in the constructor, and an initial welcome image (SJSU logo) is displayed on the app.

S15 244 Grp10 Ges qt includes.JPG

Figure 27: Snippet of initialization

Configuration COM port
The COM port is configured in this section of the code, the name of the COM port and the baud rate is picked up from the lineEdits present on the config tab and passed to populate the structure of the serial port. If there is an error opening the COM port then an error message is displayed. The COM port is closed once the disconnect button is pressed.

S15 244 Grp10 Ges qt comport.JPG

Figure 28: Configuration of COM port

Serial receive and loopback test
This section includes the code to copy all the data received in the receive buffer parse it and take the decision on which kind of gesture was received and take the appropriate decision. The loop back section picks up anything written on the Tx lineEdit and displays the received buffer on the rx lineEdit.

S15 244 Grp10 Ges qt recv loopback.JPG

Figure 29: Code to test serial receive using loopback

Open Image
The logic to switch between images and to loop through the images is implemented here.

S15 244 Grp10 Ges qt image.JPG

Figure 30: Code to switch between images

Scroll
The position of the vertical slider is changed depending on the up/down gesture, the LCDnumber display is used to display the position (value) of the vertical slider. The value ranges from 0-99 and loops through if the value is greater 99 or smaller than 0.

S15 244 Grp10 Ges qt scroll.JPG

Figure 31: Code to scroll the vertical slider

Setup and Working

Sensor setup

S15 244 Grp10 Ges sensor setup.jpg

Figure 32: Sensor setup


Screenshots of Qt application

S15 244 Grp10 Ges Qt config working.JPG

Figure 33: Configuration screen

S15 244 Grp10 Ges qt working demo.JPG

Figure 34: Application screen

Testing & Technical Challenges

Challenge #1:

The sensor produces many spikes giving false positive outputs.

Resolution:

In order to overcome spikes received and deal with false positive, normalization of the sensor output is done. A circular queue of size 5 is maintained for each sensor and each value received from the ADC is stored at the end on the queue. This queue is then sorted and only the median value is considered for computation. This reduces the false positives to a great extent.


Challenge #2:

Number of sensors used was far greater than the available ADC pins.

Resolution:

Even if we had 9 ADC pins converting values of 9 sensors, we would still be reading the each sensor one by one. Keeping this in mind, in order to overcome the deficit of ADC pins, we have used multiplexer which takes the input from 3 sensors at a time and gives the output of only the selected sensor. In this way, we could read the output of any sensor at any given point of time. The introduction of multiplexer introduces a lag but this lag is not long enough to hinder the operation of the application.


Challenge #3:

Qt being a new application for all the team members, it was a challenge to learn its programming style and use the objects.


Challenge #4:

Setting up the serial port communication in Qt.

Conclusion

Gesture recognition using IR sensors was a very interesting and challenging project. The main areas where we enjoyed working were the development of the gesture recognition algorithm and sensor filter algorithm. This project increased our knowledge in:

  • Developing filters for analog sensors
  • Working with the sensor itself
  • Reading datasheets for the multiplexer and sensor
  • Hands-on experience in Qt application
  • Using Singleton pattern for UART

This project was developed in a small scale. Further work can be done to integrate this project in devices, which would help blind people to use software, which require manual intervention, seamlessly.

Project Video

Gesture Recognition using IP Proximity Sensors

Project Source Code

References

Acknowledgement

All the components where procurred from Amazon, Adafruit and digikey. We are thankful to Preet for his continuous guidance during the project.

References Used

IR Sensor Data Sheet
LPC_USER_MANUAL
Multiplexer Data Sheet
QT Software
Filter code refered from Spring'14 project Virtual Dog