Rating is available when the video has been rented.
This feature is not available right now. Please try again later.
Published on Nov 29, 2011
Our tracking algorithm on the video sequences S2L2 and S1L2-1.
The color coding of the bounding boxes visualizes the differences between tracking with and without occlusion modeling (methods "om" and "no om" in the paper). Targets that are successfully tracked with both methods are shown in blue. False positives are rendered in red. Cyan boxes show targets that are tracked without, but lost with occlusion modeling. Similarly, targets that are only tracked with explicit occlusion modeling have yellow bounding boxes.