You are on page 1of 22

Tennis Player and Ball

Tracking
Yeshwanth Malekar

CONTENT
Motivation

Results

Challenges

Future Work

Previous Work

References

Algorithm
Detection

Solution
Problems

Motivation
Tracking Tennis players and ball in a Tennis match

Useful for automatic tennis video annotation.


Player and ball trajectories contain high level
information which can be used for training purposes and
designing strategies.

Project Goal

Challenges
Video taken is not from a steady camera.
The speed and size of the ball pose real problems.

Most of the times, ball undergoes either occlusion or gets


blurred in the background.
Chances of false detection are high.

Previous Work
Most of the previous work is done on a video taken from
a steady camera.

They also used Kalman filter and Particle filters to predict


the location of foreground objects.
These filters need a steady camera to work on and a
model of the movement of players and balls.

Algorithm
1. Extract Background image.
2. Frame difference method.

3. Morphological Operations.
4. Blob analysis.
5. Detect players and ball.

Background extraction using median function.

Bad background examples:


Too few Frames:

Over all frames:

Foreground Separation

Player and Ball detection

Morphological Operations

Conditions
Added extra boundary conditions for the ball.
Finally centroid conditions to keep track of the players
and ball in the following frames.

What if camera moves?


The whole court is detected in the
difference image instead of just
Foreground.

Simple solution
Skipped through the frames with more than required blobs.
Continue detecting the players when the video is stabilized.
Saved the centroid of the players detected in all the frames.
Adjustments:
Added the difference of the centroid positions of last two images to the
previous image.
We have new approximated candidate positions for the blank frame.

Advantages of this solution


It is very simple technique to implement.
Players detection is excellent.
Even if the ball is occluded or blurred, it is detected.

Advantages (Cont.)

Problems encountered
The ball moves at high speeds and changes its direction
rapidly.

If detection in a frame is missed, keeping track of the


ball in the next frame with this approximation method is
not possible.
False detections influence further false detections.

Problems (Cont.)

Results

Results (Cont.)

Result (Doubles)

Future Work
Better ball detection techniques for a moving camera.
Would also like to work on different ball games such as
soccer.

References
Hira Fatima et al, Object Recognition, Tracking and Trajectory Generation
in Real-Time Video Sequence, International Journal of Information and
Electronics Engineering vol.3, no.6, pp. 639-642, 2013.

Amor Salorpour et al, Vehicle Tracking Using Kalman Filter and Features,
Signal & Image Processing, an International Journal (SIPIJ), Vol.2, No.2,
June 2011.
F. Yan and W. Christmas and J. Kittler, Tennis Ball Tracking Algorithm for
Automatic Annotation of Tennis Match, BMVC, pp 619-628, 2005.

Questions

You might also like