Title: Person Following with a Mobile Robot Using Binocular Feature-Based Tracking
1Person Following with a Mobile RobotUsing
Binocular Feature-Based Tracking
- Zhichao Chen and Stanley T. Birchfield
- Dept. of Electrical and Computer Engineering
- Clemson University
- Clemson, South Carolina USA
2Motivation
- Goal Enable a mobile robot to follow a person in
a cluttered indoor environment by vision. - Previous approaches
- Appearance properties color, edges. Sidenbladh
et al. 1999, Tarokh and Ferrari 2003, Kwon et
al. 2005 - Person has different color from background or
faces camera. - Lighting changes.
- Optical flow. Piaggio et al 1998, Chivilò et
al. 2004 - Drift as the person moves with out-of-plane
rotation - Dense stereo and odometry. Beymer and Konolige
2001 - difficult to predict the movement of the robot
(uneven surfaces, slippage in the wheels).
3Our approach
- Algorithm Sparse stereo based on Lucas-Kanade
feature tracking. - Handles
- Dynamic backgrounds.
- Out-of-plane rotation.
- Similar disparity between the person and
background. - Similar color between the person and background.
4System overview
5Detect 3D features of the scene
- Kanade-Lucas-Tomasi (KLT) feature tracker
- Automatically selects 2D features using
eigenvalues of 2x2 gradient covariance matrix - Automatically matching features by minimizing sum
of squared differences (SSD) between left and
right images. - Augmented with gain and bias to handle lighting
changes - Open-source implementation
gradient of image
unknown displacement
gray-level images
http//www.ces.clemson.edu/stb/klt
6Detect 3D features of the scene ( Cont. )
- Features are selected in the left image IL and
matched in the right image IR.
Left image
Right image
7System overview
8Overview of Removing Background
1) using the known disparity of the person in the
previous image frame.
2) using the estimated motion of the background.
3) using the estimated motion of the person
9Remove BackgroundStep 1 Using the known
disparity
- Discard features for which
- where is the known disparity of the
person in the previous frame, - and is the disparity of a feature at time
t .
Original features
10Remove BackgroundStep 2 Using background
motion
- Estimate the motion of the background by
computing a 4 4 projective transformation
matrix H between two image frames at times t and
t 1
- Random sample consensus (RANSAC) algorithm is
- used to yield dominant motion.
11Remove BackgroundStep 3 Using person motion
- Similar to step 2, the motion model of the person
is calculated. - The size of the person group should be the
biggest. - The centroid of the person group should be
proximate to the previous location of the person.
Foreground features after step 2
Foreground features after step 3
12System overview
13Detect Face
- The Viola-Jones frontal face detector is applied.
- This detector is used both to initialize the
system and to enhance robustness when the person
is facing the camera.
Note The face detector is not necessary in our
system.
14System overview
15Experimental Results
16Video
17Comparison with a ColorHistogram-Based Algorithm
Color-based (Camshift, Bradski 1998)
Our approach
18Conclusion
- Approach
- detects and matches feature points between a
stereo pair of images and between successive
images. - RANSAC-based procedure to estimate the motion of
each region. - Advantages
- does not require the person to wear a different
color from the background. - track a person in an office environment, even
through doorways, with clutter, and in the
presence of other moving objects. - Future work
- fusing the information with additional
appearance-based information ( template or edges)
. - integration with other modules (obstacle
avoidance)