UK Mirror |   Australia Mirror

PHD Filter Multi-Target Tracking Demonstrations

Here we demonstrate some examples of tracking with Probability Hypothesis Density (PHD) filters on both simulated and real data to illustrate the ability of these algorithms to identify (detect) targets, initiate tracks and terminate them when targets leave the scene. The number of targets varies over time and the algorithms also estimate the number of targets. This is in the presence of clutter (false alarms), where there are many more false measurements than those generated by true targets. The tracking videos are grouped into different sections according to the implementation or application.

Gaussian mixture PHD Filter

GM-(C)PHD filter tracking |   Sonar |   Video |   Radar


GMPHD on Forward Scan|   GMCPHD on Forward Scan|   GMPHD on Multibeam Sonar

Tracking in Sonar

Gaussian mixture PHD filter Tracking in Sonar

This shows the first real data practical example of Gaussian mixture PHD filter multiple target tracking algorithm detecting, identifying and tracking targets in forward scan sonar images. This approach was recently deployed by SeeByte Ltd on an underwater vehicle for oil pipeline tracking in commercial trials with BP, where it achieved a world record for the length of pipeline tracked. The algorithm successfully tracked 22km of pipeline continuously over 5-6 hours, which is substantially more than the previous 4km record. This work played a crucial role in the navigational control of the vehicle. (Video courtesy of Heriot-Watt University, the University of Melbourne and data from Florida Atlantic University).

Gaussian mixture CPHD filtering in Sonar

This video illustrates the first example of the GM-CPHD filter algorithm on sonar data where the objects are pier legs in a harbour. The intensity function is also plotted and the cardinality distribution gives the discrete distribution in the number of targets. The techniques developed for the Gaussian mixture PHD filter for track management demonstrated above for maintaining target trajectories can also be employed here.

(Video courtesy of Heriot-Watt University, the University of Western Australia and the University of Melbourne and data from SeeByte Ltd).

Gaussian mixture PHD Filtering in Multibeam Sonar

This example shows the Gaussian mixture PHD filter detecting and estimating the position of an oil pipeline in multibeam sonar. This is a 1-dimensional problem and the circle indicates the estimated position. (Video courtesy of Heriot-Watt University and data from SeeByte Ltd).

Heriot-Watt University and the University of Melbourne 2008