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 show that the approach has considerable potential.
|Translated title of the contribution||Tracking Multiple Animals in Wildlife Footage|
|Title of host publication||16th International Conference on Pattern Recognition (ICPR 2002), Quebec, August|
|Editors||R Kasturi, D Laurendeau, C Suen|
|Publisher||IEEE Computer Society|
|Pages||20024 - 20027|
|Number of pages||4|
|Publication status||Published - Aug 2002|