Low-power Computer Vision: Status, Challenges and Opportunities


Where: Mission City B1-B5

Date:  Day 2

Start Time: 4:55 pm

End Time: 5:25 pm

Energy efficiency plays a crucial role in making computer vision successful in battery-powered systems, including drones, mobile phones and autonomous robots. Since 2015, IEEE has been organizing annual competition on low-power computer vision to identify the most energy-efficient technologies for detecting objects in images. The scores are the ratio of accuracy and energy consumption. Over the four years, the winning solutions have improved the scores by a factor of 24. The speaker will describe this competition and summarize the winning solutions, including quantization and accuracy-energy tradeoffs. Based on technology trends, the speaker will identify the challenges and opportunities in enabling energy-efficient computer vision.

Track

Session Speakers

  • Yung-Hsiang Lu is a professor in the School of Electrical and Computer Engineering and (by courtesy) the Department of Computer Science of Purdue University. He is an ACM Distinguished Scientist and ACM Distinguished Speaker. He is a co-founder and the adviser, of Perceive Inc. Perceive is a technology startup using video analytics for improving shopping experience in physical stores. Perceive has received a $1M Small Business Innovation Research (SBIR) Phase-1 and Phase-2 award from the National Science Foundation. Dr. Lu has been the lead organizer of the IEEE Annual International Low-Power Image Recognition Challenge since 2015. His research topics include image processing, computer vision, cloud computing, mobile computing, and energy management for computers. He is the author of Intermediate C Programming (CRC Press).


Share

Low-power Computer Vision: Status, Challenges and Opportunities