TY - GEN
T1 - Adaptive Video Subsampling for Energy-Efficient Object Detection
AU - Mohan, DIvya
AU - Katoch, Sameeksha
AU - Jayasuriya, Suren
AU - Turaga, Pavan
AU - Spanias, Andreas
N1 - Funding Information:
*These authors contributed equally. This work is funded in part by the NSF CPS Program #1646542 and the SenSIP Center.
Publisher Copyright:
© 2019 IEEE.
PY - 2019/11
Y1 - 2019/11
N2 - Energy-efficient computer vision is vitally important for embedded and mobile platforms where a longer battery life can allow increased deployment in the field. In image sensors, one of the primary causes of energy expenditure is the sampling and digitization process. Smart subsampling of the image-array in a manner that is task-specific, can result in significant savings of energy. We present an adaptive algorithm for video subsampling, which is aimed at enabling accurate object detection, while saving sampling energy. The approach utilizes objectness measures, which we show can be accurately estimated even from sub-sampled frames, and then uses that information to determine the adaptive sampling for the subsequent frame. We show energy savings of 18-67% with only a slight degradation in object detection accuracy in experiments. These results motivated us to further explore energy-efficient subsampling using advanced techniques such as, reinforcement learning and Kalman filtering. The experiments using these techniques are underway and provide ample support for adaptive subsampling as a promising avenue for embedded computer vision in the future.
AB - Energy-efficient computer vision is vitally important for embedded and mobile platforms where a longer battery life can allow increased deployment in the field. In image sensors, one of the primary causes of energy expenditure is the sampling and digitization process. Smart subsampling of the image-array in a manner that is task-specific, can result in significant savings of energy. We present an adaptive algorithm for video subsampling, which is aimed at enabling accurate object detection, while saving sampling energy. The approach utilizes objectness measures, which we show can be accurately estimated even from sub-sampled frames, and then uses that information to determine the adaptive sampling for the subsequent frame. We show energy savings of 18-67% with only a slight degradation in object detection accuracy in experiments. These results motivated us to further explore energy-efficient subsampling using advanced techniques such as, reinforcement learning and Kalman filtering. The experiments using these techniques are underway and provide ample support for adaptive subsampling as a promising avenue for embedded computer vision in the future.
KW - Energy-efficient computer vision
KW - Image and Video Subsam-pling
KW - Objectness
UR - http://www.scopus.com/inward/record.url?scp=85083311415&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85083311415&partnerID=8YFLogxK
U2 - 10.1109/IEEECONF44664.2019.9048698
DO - 10.1109/IEEECONF44664.2019.9048698
M3 - Conference contribution
AN - SCOPUS:85083311415
T3 - Conference Record - Asilomar Conference on Signals, Systems and Computers
SP - 103
EP - 107
BT - Conference Record - 53rd Asilomar Conference on Circuits, Systems and Computers, ACSSC 2019
A2 - Matthews, Michael B.
PB - IEEE Computer Society
T2 - 53rd Asilomar Conference on Circuits, Systems and Computers, ACSSC 2019
Y2 - 3 November 2019 through 6 November 2019
ER -