A Directionally Selective Small Target Motion Detecting Visual Neural Network in Cluttered Backgrounds

TL;DR

This paper introduces a neural network model inspired by fly visual neurons, capable of detecting small moving targets in cluttered backgrounds by incorporating directional selectivity and size filtering mechanisms.

Contribution

It presents a novel DSTMD neural network model that systematically simulates directional selectivity of STMD neurons for small target detection.

Findings

Accurately detects small targets in cluttered scenes

Exhibits directional selectivity consistent with biological neurons

Works reliably in complex visual environments

Abstract

Discriminating targets moving against a cluttered background is a huge challenge, let alone detecting a target as small as one or a few pixels and tracking it in flight. In the fly's visual system, a class of specific neurons, called small target motion detectors (STMDs), have been identified as showing exquisite selectivity for small target motion. Some of the STMDs have also demonstrated directional selectivity which means these STMDs respond strongly only to their preferred motion direction. Directional selectivity is an important property of these STMD neurons which could contribute to tracking small targets such as mates in flight. However, little has been done on systematically modeling these directional selective STMD neurons. In this paper, we propose a directional selective STMD-based neural network (DSTMD) for small target detection in a cluttered background. In the proposed neural network, a new correlation mechanism is introduced for direction selectivity via correlating signals relayed from two pixels. Then, a lateral inhibition mechanism is implemented on the spatial field for size selectivity of STMD neurons. Extensive experiments showed that the proposed neural network not only is in accord with current biological findings, i.e. showing directional preferences, but also worked reliably in detecting small targets against cluttered backgrounds.