TY - GEN
T1 - Recurrence textures for human activity recognition from compressive cameras
AU - Kulkarni, Kuldeep
AU - Turaga, Pavan
PY - 2012/12/1
Y1 - 2012/12/1
N2 - Recent advances in camera architectures and associated mathematical representations now enable compressive acquisition of images and videos at low data-rates. In such a setting, we consider the problem of human activity recognition, which is an important inference problem in many security and surveillance applications. We propose a framework for understanding human activities as a non-linear dynamical system, and propose a robust, generalizable feature that can be extracted directly from the compressed measurements without reconstructing the original video frames. The proposed feature is termed recurrence texture and is motivated from recurrence analysis of non-linear dynamical systems. We show that it is possible to obtain discriminative features directly from the compressed stream and show its utility in recognition of activities at very low data rates.
AB - Recent advances in camera architectures and associated mathematical representations now enable compressive acquisition of images and videos at low data-rates. In such a setting, we consider the problem of human activity recognition, which is an important inference problem in many security and surveillance applications. We propose a framework for understanding human activities as a non-linear dynamical system, and propose a robust, generalizable feature that can be extracted directly from the compressed measurements without reconstructing the original video frames. The proposed feature is termed recurrence texture and is motivated from recurrence analysis of non-linear dynamical systems. We show that it is possible to obtain discriminative features directly from the compressed stream and show its utility in recognition of activities at very low data rates.
KW - Activity Analysis
KW - Inference from Compressive Cameras
UR - http://www.scopus.com/inward/record.url?scp=84875833124&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84875833124&partnerID=8YFLogxK
U2 - 10.1109/ICIP.2012.6467135
DO - 10.1109/ICIP.2012.6467135
M3 - Conference contribution
AN - SCOPUS:84875833124
SN - 9781467325332
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 1417
EP - 1420
BT - 2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings
T2 - 2012 19th IEEE International Conference on Image Processing, ICIP 2012
Y2 - 30 September 2012 through 3 October 2012
ER -