CA-YOLO: Cross Attention Empowered YOLO for Biomimetic Localization

TL;DR

This paper introduces CA-YOLO, a novel object detection model inspired by biological visual mechanisms, which improves small target recognition and localization accuracy in complex environments, validated by experiments on standard datasets.

Contribution

The paper presents CA-YOLO, integrating bionic modules and attention mechanisms into YOLO to enhance small target detection and localization accuracy.

Findings

Outperforms original YOLO on COCO and VisDrone datasets

Achieves 3.94% and 4.90% higher accuracy respectively

Demonstrates effectiveness in time-sensitive target localization

Abstract

In modern complex environments, achieving accurate and efficient target localization is essential in numerous fields. However, existing systems often face limitations in both accuracy and the ability to recognize small targets. In this study, we propose a bionic stabilized localization system based on CA-YOLO, designed to enhance both target localization accuracy and small target recognition capabilities. Acting as the "brain" of the system, the target detection algorithm emulates the visual focusing mechanism of animals by integrating bionic modules into the YOLO backbone network. These modules include the introduction of a small target detection head and the development of a Characteristic Fusion Attention Mechanism (CFAM). Furthermore, drawing inspiration from the human Vestibulo-Ocular Reflex (VOR), a bionic pan-tilt tracking control strategy is developed, which incorporates central positioning, stability optimization, adaptive control coefficient adjustment, and an intelligent recapture function. The experimental results show that CA-YOLO outperforms the original model on standard datasets (COCO and VisDrone), with average accuracy metrics improved by 3.94%and 4.90%, respectively.Further time-sensitive target localization experiments validate the effectiveness and practicality of this bionic stabilized localization system.