Carried Object Detection using a Generic Shape Model and Positional Consistency

Aryana Tavanai, Muralikrishna Sridhar, Feng Gu, Anthony G. Cohn and David C. Hogg

This work applies local and global constraints in an optimisation procedure where the interpretation of the tracks (local constraints) and events (global constraints) mutually influence each other.


Software Download

Geometric carried object detection code will be available soon. (Please contact Aryana Tavanai for any queries)
Tracking and optimisation code will be available in the near future.

Publications

Aryana Tavanai, Muralikrishna Sridhar, Feng Gu, Anthony G. Cohn, and David C. Hogg. Carried Object Detection and Tracking using Geometric Shape Models and Spatio-Temporal Consistency. 9th International Conference on Computer Vision Systems, ICVS 2013. (To appear)
[pdf]

Datasets

The following two datasets have been used to evaluate the proposed approach.

MINDSEYE2012: A subset of Mind's Eye Year 2 videos were selected.

PETS2006: All seven videos of the third camera were chosen from the PETS2006 dataset.

Acknowledgement

The financial support of the EU Framework 7 project Co-RACE (FP7-ICT- 287752), and the DARPA Mind's Eye program (project VIGIL, W911NF-10-C-0083) is gratefully acknowledged.
Last Updated 2/7/2013