Face Tracking on ROS Electric using Pi_face_tracker and gencam_cu

Here is a tutorial for running face detection on ROS using pi_face tracker and gencam_cu

Pi_face tracker will work on Kinect and uvc_cam based webcams .Some webcams and laptop integrated cams have some issues while using uvc_cam .There is another package on ROS site called gencam_cu for webcams .Its working on OpenCV library .

Here is the link for gencam_cu

http://ros.org/wiki/gencam_cu

Pi_face tracker package is available in following link

http://www.ros.org/wiki/pi_face_tracker

First you need to download and install gencam_cu first .

Before installing pi_face_tracker we need to change some parameters in pi_face_tracker launch file .

The launch file is called face_tracker_uvc_cam.launch 

Replace the line  

    <remap from="input_rgb_image" to="/camera/image_raw" /> into 

    <remap from="input_rgb_image" to="/image_raw" /> 

It looks like this 

<launch>

  <arg name="auto_face_tracking" default="True" />

  <node pkg="pi_face_tracker" name="pi_face_tracker" type="face_tracker.py" out$

    <remap from="input_rgb_image" to="/image_raw" />

    <remap from="output_image" to="/pi_face_tracker/image" />

It is a patch ,because gencam_cu publishs images on /image_raw topic ,but uvc_cam publishes on /camera/image_raw

Install pi_face_tracker 

eg_cmd : rosmake --rosdep-install 

Run roscore

Run gencam_cu by following command

rosrun gencam_cu gencam_cu

Launch pi_face_tracker

roslaunch pi_face_tracker face_tracker_uvc_cam.launch

Output Image