This paper presents a 64×64 CMOS image sensor with on-chip moving object detection and localization capability. Pixel-level storage elements (capacitors) enable the sensor to simultaneously output two consecutive frames, with temporal differences digitalized into binary events by a global differentiator. An on-chip, hardware-implemented, clustering-based algorithm processes events on the fly and localizes up to three moving objects in the scene. The sensor can automatically switch to region of interest mode and capture a picture of the object. The proposed image sensor was implemented using UMC 0.18 μm CMOS technology with a die area of 1.5 mm × 1.5 mm, and power consumption was only 0.4 mW at 100 FPS.Index Terms-Motion detection, moving object localization, on-the-fly clustering, smart image sensor.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.