Attention and Prediction Guided Motion Detection for Low-Contrast Small Moving Targets

TL;DR

This paper introduces a novel attention and prediction guided visual system inspired by insect vision to improve detection of small, low-contrast moving targets in complex natural environments, outperforming existing models.

Contribution

The paper proposes a new recurrent visual system combining attention, neural network, and prediction modules to enhance small target detection in challenging conditions.

Findings

Effective detection of low-contrast small targets in complex backgrounds.

Superior performance over existing STMD-based models.

Validated on synthetic and real-world datasets.

Abstract

Small target motion detection within complex natural environments is an extremely challenging task for autonomous robots. Surprisingly, the visual systems of insects have evolved to be highly efficient in detecting mates and tracking prey, even though targets occupy as small as a few degrees of their visual fields. The excellent sensitivity to small target motion relies on a class of specialized neurons called small target motion detectors (STMDs). However, existing STMD-based models are heavily dependent on visual contrast and perform poorly in complex natural environments where small targets generally exhibit extremely low contrast against neighbouring backgrounds. In this paper, we develop an attention and prediction guided visual system to overcome this limitation. The developed visual system comprises three main subsystems, namely, an attention module, an STMD-based neural network, and a prediction module. The attention module searches for potential small targets in the predicted areas of the input image and enhances their contrast against complex background. The STMD-based neural network receives the contrast-enhanced image and discriminates small moving targets from background false positives. The prediction module foresees future positions of the detected targets and generates a prediction map for the attention module. The three subsystems are connected in a recurrent architecture allowing information to be processed sequentially to activate specific areas for small target detection. Extensive experiments on synthetic and real-world datasets demonstrate the effectiveness and superiority of the proposed visual system for detecting small, low-contrast moving targets against complex natural environments.