Target Tracking with the Linear Kalman Filter

In this short movie, a ball, created from the code in the game section, is tracked around a small room. The green square represents the detects, the yellow square represents the a-priori Kalman state, and the blue square represents the a-posteriori Kalman state.

Near the very end of the movie, the ball starts to roll and no detections occur. At this point, the Kalman filter coasts the track, predicting where the ball is going to be. Then, once the detections return, the Kalman state is quickly fixed.

The text at the top of the video displays the instantaneous and root mean square (RMS) error for both the a-priori state and a-posteriori state.

Target Tracking Among Similar Objects

In this version, to confuse the detection algorithm, multiple bouncing balls are added.

The detection algorithm is the matched filter. The matched filter and Kalman filter work in tandem to ignore false alarms. The basic idea is that if the detection is too far away from the prediction, then that detection will be ignored and the Kalman filter will be coasted.


One thought on “School

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s