A retina-inspired robust on-focal-plane multi-band edge-detection scheme for CMOS image sensors

An edge-detection scheme suitable for machine vision and digital motion detection applications is presented. The scheme is inspired by the human visual system (human retina) and modified for a compact and scalable CMOS hardware implementation. In addition, pixel circuit and implementation of the scheme on a CMOS focal-plane are proposed and simulation results are presented. The circuit performs thresholding and single-bit quantization of high-frequency image content over multiple frequency bands using a low-complexity down-sampling scheme. As a result, a 1-bit per pixel output is obtained which results in efficient edge-detection of the image content. Depending on the number of the utilized frequency bands, the presented scheme achieves image compression levels that range from 1 BPP (bit-per-pixel) to 1.33 BPP. The proposed acquisition technique and the corresponding CMOS circuit can easily be adjusted to various imaging applications and scaled towards new CMOS technology nodes and high resolution image sensors.