Retina-Inspired Object Motion Segmentation for Event-Cameras

TL;DR

This paper presents a bio-inspired, efficient algorithm for object motion segmentation in event-camera data, leveraging retinal functionalities to achieve high-speed, low-bandwidth processing without deep learning.

Contribution

It introduces a novel, neuroscience-inspired method for ego-motion compensation and object segmentation that significantly reduces computational complexity compared to prior approaches.

Findings

Effective pixel-wise object motion segmentation in real and synthetic datasets.

Reduces model parameters by 10^3 to 10^6 times compared to previous methods.

Demonstrates robustness and high speed suitable for in-sensor decision-making.

Abstract

Event-cameras have emerged as a revolutionary technology with a high temporal resolution that far surpasses standard active pixel cameras. This technology draws biological inspiration from photoreceptors and the initial retinal synapse. This research showcases the potential of additional retinal functionalities to extract visual features. We provide a domain-agnostic and efficient algorithm for ego-motion compensation based on Object Motion Sensitivity (OMS), one of the multiple features computed within the mammalian retina. We develop a method based on experimental neuroscience that translates OMS' biological circuitry to a low-overhead algorithm to suppress camera motion bypassing the need for deep networks and learning. Our system processes event data from dynamic scenes to perform pixel-wise object motion segmentation using a real and synthetic dataset. This paper introduces a bio-inspired computer vision method that dramatically reduces the number of parameters by $\text{10}^\text{3}$ to $\text{10}^\text{6}$ orders of magnitude compared to previous approaches. Our work paves the way for robust, high-speed, and low-bandwidth decision-making for in-sensor computations.