TY - GEN
T1 - Energy characterization and optimization of image sensing toward continuous mobile vision
AU - Likamwa, Robert
AU - Priyantha, Bodhi
AU - Philipose, Matthai
AU - Zhong, Lin
AU - Bahl, Paramvir
PY - 2013
Y1 - 2013
N2 - A major hurdle to frequently performing mobile computer vision tasks is the high power consumption of image sensing. In this work, we report the first publicly known experimental and analytical characterization of CMOS image sensors. We find that modern image sensors are not energy-proportional: energy per pixel is in fact inversely proportional to frame rate and resolution of image capture, and thus image sensor systems fail to provide an important principle of energy-aware system design: trading quality for energy efficiency. We reveal two energy-proportional mechanisms, supported by current image sensors but unused by mobile systems: (i) using an optimal clock frequency reduces the power up to 50% or 30% for low-quality single frame (photo) and sequential frame (video) capturing, respectively; (ii) by entering low-power standby mode between frames, an image sensor achieves almost constant energy per pixel for video capture at low frame rates, resulting in an additional 40% power reduction. We also propose architectural modifications to the image sensor that would further improve operational efficiency. Finally, we use computer vision benchmarks to show the performance and efficiency tradeoffs that can be achieved with existing image sensors. For image registration, a key primitive for image mosaicking and depth estimation, we can achieve a 96% success rate at 3 FPS and 0.1 MP resolution. At these quality metrics, an optimal clock frequency reduces image sensor power consumption by 36% and aggressive standby mode reduces power consumption by 95%.
AB - A major hurdle to frequently performing mobile computer vision tasks is the high power consumption of image sensing. In this work, we report the first publicly known experimental and analytical characterization of CMOS image sensors. We find that modern image sensors are not energy-proportional: energy per pixel is in fact inversely proportional to frame rate and resolution of image capture, and thus image sensor systems fail to provide an important principle of energy-aware system design: trading quality for energy efficiency. We reveal two energy-proportional mechanisms, supported by current image sensors but unused by mobile systems: (i) using an optimal clock frequency reduces the power up to 50% or 30% for low-quality single frame (photo) and sequential frame (video) capturing, respectively; (ii) by entering low-power standby mode between frames, an image sensor achieves almost constant energy per pixel for video capture at low frame rates, resulting in an additional 40% power reduction. We also propose architectural modifications to the image sensor that would further improve operational efficiency. Finally, we use computer vision benchmarks to show the performance and efficiency tradeoffs that can be achieved with existing image sensors. For image registration, a key primitive for image mosaicking and depth estimation, we can achieve a 96% success rate at 3 FPS and 0.1 MP resolution. At these quality metrics, an optimal clock frequency reduces image sensor power consumption by 36% and aggressive standby mode reduces power consumption by 95%.
KW - Computer vision
KW - Energy efficiency
KW - Energy proportionality
KW - Image sensor
KW - Mobile systems
UR - http://www.scopus.com/inward/record.url?scp=84881126474&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84881126474&partnerID=8YFLogxK
U2 - 10.1145/2462456.2464448
DO - 10.1145/2462456.2464448
M3 - Conference contribution
AN - SCOPUS:84881126474
SN - 9781450316729
T3 - MobiSys 2013 - Proceedings of the 11th Annual International Conference on Mobile Systems, Applications, and Services
SP - 69
EP - 81
BT - MobiSys 2013 - Proceedings of the 11th Annual International Conference on Mobile Systems, Applications, and Services
T2 - 11th Annual International Conference on Mobile Systems, Applications, and Services, MobiSys 2013
Y2 - 25 June 2013 through 28 June 2013
ER -