publication . Article . 2020

A Low-Power VGA Vision Sensor with Embedded Event Detection for Outdoor Edge Applications

Yu Zou; Massimo Gottardi; Michela Lecca; Matteo Perenzoni;
Open Access
  • Published: 13 Jul 2020
  • Publisher: Zenodo
Abstract
We report on a low-power VGA vision sensor embedding event-detection capabilities targeted to battery-powered vision processing at the edge. The sensor relies on an always-ON Double-Threshold dynamic background subtraction (DT-DBS) algorithm. The resulting motion bitmap is de-noised, projected along $xy$ -axes of the array of pixels and filtered to robustly detect moving targets even in noisy outdoor scenarios. The chip operates in motion detection (MD), applied on a QQVGA sub-sampled image, looking for anomalous motion in the scene at 344 $\mu \text{W}$ , and in imaging mode (IM), delivering full-resolution gray-scale images with associated local binary pattern (LBP) coding and motion bitmaps at 8 frames/s and 1.35 mW. The 4- $\mu \text{m}$ pixel vision sensor is manufactured in a 110-nm 1P4M CMOS and occupies 25.4 mm2.
Persistent Identifiers
Subjects
ACM Computing Classification System: ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
free text keywords: Background subtraction, event detection, local binary pattern, low-power vision sensors, motion detection, Electrical and Electronic Engineering, Artificial intelligence, business.industry, business, Computer vision, Video Graphics Array, Pixel, Computer science, Motion detection, Local binary patterns, Background subtraction
Related Organizations
Any information missing or wrong?Report an Issue