Improved Anchor-Free Object Detection Algorithm Based on Task-Aligned One-Stage Object Detection

Abstract

Numerous fields, including autonomous driving, facial recognition, video monitoring, and medical picture analysis, use object detection. The Task-aligned One-stage Object Detection (TOOD) technique, however, will result in information loss and slow detection speeds when classifying and aligning objects. In order to increase the receptive field of detection and lower the amount of calculations required by the model, a Receptive Field Enhancement Module (RFEM) is added between the backbone network and the neck network of the detector in this article. This effectively addresses the issues of decreasing accuracy and slow speed. Then, in the head network, the original detecting head is switched out for an Enhanced Task Alignment Head (ET-Head) based on Layer Hybrid Attention Module (LHAM), which significantly enhances the detector’s performance and feature extraction capability. Additionally, SIOU loss is used in place of regression loss to enhance the training effect. For our experiments, we use the PASCAL VOC dataset. According to experimental findings, the detection accuracy is up 1.1% compared to the TOOD algorithm, and the speed is up 1 frame per second (FPS).