Tracking multiple animals in wildlife footage

D. Tweed, A. Calway
Object recognition supported by user interaction for service robots  
We describe a method for tracking animals in wildlife footage. It uses a CONDENSATION particle filtering framework driven by learnt characteristics of specific animals. The key contribution is a periodic model of animal motion based on the relative positions over time of trackable features at significant body points. We also introduce techniques for maintaining a multimodal state density within the particle filter over time to enable consistent tracking of multiple animals. Initial experiments
more » ... nitial experiments show that the approach has considerable potential.
doi:10.1109/icpr.2002.1048227 dblp:conf/icpr/TweedC02 fatcat:auggk5lqr5hhtmphfan5nscrru