With some effort I have found that controlling two servo motors to allow a webcam to pan/tilt while tracking a face in real time using the raspberry pi not as impossible as it may at first seem. With some careful tweaking and code optimization I was able to allow the pi to keep up with two servos while running OpenCV face detection at 320x240 looking for a right profile,left profile, and frontal face and adjusting the servos faster than once per second.

Step 1: Acquire the hardware.

Things needed:

A raspberry pi -- Model A will work fine, I have the original Model B which has the same specs as the new Model A (minus network).
A pan/tilt bracket
Two Servos
A GPIO Ribbin Cable
A Pi-Supported Webcam --  I used a Logitech C210

Assuming you already have a raspberry pi and a webcam the additional hardware will run you about $25
<p>its so cool.. i made it ! </p>
Whether the cam comes to its initial position after the face goes out of its sight??
<p>Traceback (most recent call last):</p><p> File &quot;PiFace.py&quot;, line 14, in &lt;module&gt;</p><p> ServoBlaster = open('/home/pi/Desktop/ServoBlaster', 'w')# ServoBlaster is what we use to control the servo motors</p><p>IOError: [Errno 21] Is a directory: '/home/pi/Desktop/ServoBlaster'</p><p>can u hepl me fix it</p>
<p>It seems like /home/pi/Desktop/ServoBlaster should be a file, and not a directory.</p><p>Python's builtin function &quot;open&quot; opens files for reading from and writing to, so when you specify a directory, the program throws an error.</p><p>PiFace.py uses a file at /dev/servoblaster ... I'm not familiar with controlling servo's, but it seems like /dev/servoblaster is supposed to be a buffer (file) that's responsible for the communication between a the programmed instructions and the actual machine. </p><p>I hope that helps a little and sets you on the right track - but like I said, I know python but nothing about servos, so take what I say with a grain of salt. :)</p>
<p>I was getting all 0's returned to the console for a while. Turns out my glasses were interfering with the face detection! Also helps if you find the optimal distance from the webcam. </p>
<p>i am using code of facetrack2.py ,i got trouble in servo,it is not running along with detection, i connected it to GPIO 23 but still it is not running, servo i am using is 'mg 90s pro'. plz tell me that if there is some thing in the code i have to do? or i am connectiing to wrong pin ? bcz there are two things regarding pins ist is GPIO pin and other is pin #, i connected it to pin# 16, i-e GPIO 23</p>
<p>Hi Chris,</p><p>How easy/hard would it be to adapt this setup to use a joystick to control the movement of this servos? I was looking at something along these lines: <a href="http://letsmakerobots.com/node/33643" rel="nofollow">http://letsmakerobots.com/node/33643 </a> where the camera does not return to the centre position.</p><p>Thanks,</p><p>Chris</p>
<p>Nice project! I used your core PiFace.py codebase as a starting point but modified it to use RPIO.PWM instead of ServoBlaster and also to use the RaspiCam instead of a USB camera. I did make one fix where the pan servo was moving the wrong direction when the image was flipped for the reverse profile search:</p><p>if lastface==3:</p><p> Cface[0]=(w/2)+(320-x-h)</p><p>In general for opencv, using an LBP cascade was a little faster for frontal face searches, but HAAR was more reliable for profile searches.</p><p>In addition to some other minor tweaks, I also added a video feed window with a face rectangle so I could see what it was looking at.</p><p>Did you ever find a more elegant way to handle the frame lag issue than just doing a bunch of successive reads?</p>
<p>Can you give me some guidance on how you added the video feed window? I am trying to do that, as the camera continuously over shoots the face and constantly corrects. I would like to see if I can determine why it is doing that. I have been trying to use imshow and having no luck. If you could share your code for adding the video display, that would be wonderful. Thanks.</p>
<p>Here are the code snippets I used for displaying the video feed:</p><p>#setup video at startup:</p><p>capture = cv2.VideoCapture(0) <br>capture.set(cv2.cv.CV_CAP_PROP_FRAME_WIDTH, width)<br>capture.set(cv2.cv.CV_CAP_PROP_FRAME_HEIGHT, height)</p><p>cv2.cv.NamedWindow(&quot;video&quot;, cv2.cv.CV_WINDOW_AUTOSIZE)</p><p>#update screen with rectangle around found face after every face search in the while loop</p><p> cv2.cv.Rectangle(cv2.cv.fromarray(aframe), (x,y), (x+w, y+h), cv2.cv.RGB(255, 0, 0), 3, 8, 0)<br> cv2.imshow(&quot;video&quot;, aframe)<br> cv2.waitKey(1)</p>
<p>@JennaSys any chance you could also share the code you used to get the capture from the raspberry pi camera module? I have been strugling for ours trying to figure it out ;)</p>
<p>I've had several people ask for my code updates for this so I went ahead and put it up on github:</p><p><a href="https://github.com/JennaSys/facetrack" rel="nofollow">https://github.com/JennaSys/facetrack</a></p><p>The python code is in facetrack2.py</p><p>I admittedly didn't do a good job of documenting my code changes since I was just messing around with this, so if anyone has questions, let me know and I'll go back and add explanations where necessary.</p><p>Also in case anyone is interested here is the pan/tilt hardware I used for the PiCam:</p><p><a href="http://www.adafruit.com/products/1434" rel="nofollow">http://www.adafruit.com/products/1434 </a> (Pimoroni camera mount)</p><p><a href="http://www.adafruit.com/products/1968" rel="nofollow">http://www.adafruit.com/products/1968 </a> (pan/tilt rig w/o servos) </p><p>or</p><p><a href="http://www.adafruit.com/products/1967" rel="nofollow">http://www.adafruit.com/products/1967 </a> (pan/tilt rig w/servos) </p><p>I also 3D printed an adapter for the camera mount so I wouldn't have to attach it to the pan/tilt rig with rubberbands:</p><p><a href="http://www.thingiverse.com/thing:480559" rel="nofollow">http://www.thingiverse.com/thing:480559</a></p><p>When I get a chance, I'll try and make a video of it in action. Thanks again to Grintor for putting up this instructable!</p>
<p>hi, first of all give you thanks, thats more than i need to achieve my purpose.</p><p>But im having a trouble, when i run your code, the video display appears and inmediately rpi get frozen, it seems like it is too much for my raspberry, im using rpi model b+. Do you know why this happens??</p>
<p>I have had that happen before as well and have 2 possible causes:</p><p>1. Make sure the power to the Raspberry Pi is sufficient and that the servos aren't causing a brownout.</p><p>2. Try running the program outside of any editors (like Idle) using:</p><p>sudo python facetrack2.py</p>
<p>Thank you for finding that bug. I actually haven't done anything else with this project since I posted this. But, yours looks nicer than mine. If you make a video of it in action, i'll post it in this instructable and link you credit.</p>
<p>i am building a similar project only the camera will be mounted inside a 12&quot; steel ball so I am thinking of sending the coordinate info to an arduino and stepper controllers with step dir to control bigger stepper motors for pan tilt. Awesome project , great job!</p>
<p>Hello <br>did you use a bridge to controll those motors ?</p>
<p>No, they are controlled directly from the GPIO pins on the Pi</p>
<p>hey how do interface the web camera with pi the code send to me please,then which algorithm is best for face detection and tracking also please give the code on for image tracking in python format send to my id selvam27193@gmail.com</p>
<p>The code is in the zip file in the instructable. </p>
<p>Hey Grintor nice tutorial. I'm from the UK and I'm in an engineering scheme placement over here and would like some help with my team's project. We have to construct a rig to stream and control a number of cameras in a test lab at GKN, to a nearby office. We were wondering, is it better to control the servos directly from the GPIO pins, or to use an extension board such as a PiFace Digital? Thanks in advance, Dan.</p>
<p>'better' is subjective. Since raspian is not a real-time operating system (unless you recompile the kernel), the timing will be be more precise when you use an external controller like that, but I haven't seen this translate into any real-world performance impact. Also, the Pi signaling is 3.3v, some servos may require 5v. My advice is to give it a try, if you have problems then use a board.</p>
<p>Hello, how would you go about recording this video?</p>
<p>hey how do interface the web camera with pi the code send to me please,then which algorithm is best for face detection and tracking also please give the code on for image tracking in python format send to my id selvam27193@gmail.com</p>
<p>I want assembly for fitting servo motor </p>
Hello,<br><br>I want to try this one but I can't find the download for the &quot;PiFace.py&quot;. Can somebody help me?
It's in the zip file on step 6
Hello,<br><br>I want to try this one but I can't find the download for the &quot;PiFace.py&quot;. Can somebody help me?
Skip earlier question.... Resolved. Power fluctuations. <br>New problem also resolved: Servo 0 was moving opposite to correct tracking direction. Resolution: changed str(_Servo0CP) to str(300 - _Servo0CP) in the two ServoBlaster.write statements. Woohoo! Works like a charm!
Face recognition seems to be working great, but servo control seems erratic. When face is seen, and coordinates appear in the stream, the servos move way too far. Could it be that my webcam is running at higher resolution than 320x240? If so, where do I change the cam mode? <br>Thanks, -Jeff
Very good tutorial for beginners that uses <a href="http://www.intorobotics.com/18-excellent-tutorials-compilation-start-working-raspberry-pi/" rel="nofollow">Raspberry Pi</a> minicomputer. I add this tutorial in a series of tutorials from where the users can learn how to start working with this device.&nbsp;
i too get error on line: <br>fface = frontalface.detectMultiScale(aframe,1.3,4,(cv2.cv.CV_HAAR_DO_CANNY_PRUNING + cv2.cv.CV_HAAR_FIND_BIGGEST_OBJECT + cv2.cv.CV_HAAR_DO_ROUGH_SEARCH),(60,60)) <br>and rmmod uvcvideo <br>modprobe uvcvideo nodrop=1 timeout=5000 quirks=0x80 <br>does not do the job. <br>Could you help? <br>thanks
looks similar to something i've always wanted to do: <br>a tripod head that 'learns' a move temporarily for pan with ease-in and ease-out. <br>so I set its start point, the end point, the time interval it needs to do the deed. <br> <br>hooray. one take. maybe one more for good measure. <br> <br>once done i might break into the iLink connector and get to to control zoom as well. <br> <br>thing is i have so many more things to do
Hi the program works <br/>I wanted to run the script at start-up so I wrote <br/>python /home/pi/FaceDetection/PiFace/PiFace.py<br/>But it did not work it just output <br/>0,0<br/>0,0<br/>0,0<br/>0,0<br/>0,0<br/>And so on nothing happen even though I stared right into the camera
Wrote it in /etc/rc.local
try making it start with LXDE: <br>http://wiki.lxde.org/en/Autostart
When I run python PiFace.py the outputs were <br>VIDIOC_QUERYMENU: Invalid argument <br>VIDIOC_QUERYMENU: Invalid argument <br>VIDIOC_QUERYMENU: Invalid argument <br>VIDIOC_QUERYMENU: Invalid argument <br>VIDIOC_QUERYMENU: Invalid argument <br>VIDIOC_QUERYMENU: Invalid argument <br>VIDIOC_QUERYMENU: Invalid argument <br>0,0 <br>0,0 <br>0,0 <br>0,0 <br>0,0 <br>And it the 0,0 keeps on going and nothing else happens. <br> <br>Any ideas what's happening?
it seems to be running, all the invalid argument stuff is normal. may be something wrong with the video. try to view your webcam feed through another program and see hew the video stream looks.
When I run make install_autostart is says Make: *** No rule to make target 'install_autostart'. Stop'. <br>any idea what's happening?
make sure you are doing 'make install_autostart' not doing 'sudo make install_autostart' <br>try 'make clean' before you run again.
great tutorial but i keep getting an error on this line: <br>fface = frontalface.detectMultiScale(aframe,1.3,4,(cv2.cv.CV_HAAR_DO_CANNY_PRUNING + cv2.cv.CV_HAAR_FIND_BIGGEST_OBJECT + cv2.cv.CV_HAAR_DO_ROUGH_SEARCH),(60,60)) <br>it says the array type is not supported. <br>Could you help? <br>thanks
Hi I had the same problem, you may have forgotten to run these commands <br> <br>rmmod uvcvideo <br>modprobe uvcvideo nodrop=1 timeout=5000 quirks=0x80
Did you use viola-jones algorithm to tracking the face ?
No, <a href="http://en.wikipedia.org/wiki/Haar-like_features" rel="nofollow">Haar </a>Cascade.
Does it still connection to computer ? I mean it still need connection to PC for image processing or maybe raspberry pi can replacing the PC ?
No, the pi does all the image processing and controls both servos
Hey Gintor. <br>This looks project looks awesome I've been trying it out as my first project with the PI but have hit a wall I don't seem to be able to get around, When I run &quot;sudo make install_autostart&quot; to install the servoblaster driver i get the responce &quot;CP: cannot stat '/udev_scripts/servoblaster&quot;. I've tried this a root too but i get the same response each time. I've gone through the servoblaster.c file and added the servoblaster and 20-servoblaster.rules file to my /etc/udev directories but still no luck. <br>I've downloaded the servo blaster directory to my pi and placed it in the folder &quot;/pi/servblaster&quot;. <br>I'm very new to linux and the rapberry pi so I'm guessing it;s something ridiculously simple I've missed. Any Ideas would help.
Go into the Makefile and copy the lines where it gets stuck and execute them manualy in the terminal, i.e cp /udev_scripts/servoblaster... <br> <br>then delete them from the make file. <br>about 4 lines gave me issues , not sure why <br> <br>im stuck on the line &quot; sudo modprobe servoblaster&quot; , it gives me the error: could not insert 'servoblaster' : Exec format error ??? <br> <br>does this have something to do with the kernel version?
I used kernel version 3.6.11+. If the module won't load, servoblaster offers a userspace daemon: <br>make servod <br>chmod +x servod <br>sudo ./servod <br> <br>You can just start servod before each run

About This Instructable


195 favorites


More by Grintor: Pan / Tilt face tracking with the raspberry pi
Add instructable to: