Improved Small Target Detection Algorithm Based on YOLOX
MENG Kuangyin
FU Kai
WANG Mingzheng
GU Hao
Abstract：Object detection is an important direction of computer vision,and small object detection has long been a difficult point in computer vision.With the progress of satellite and remote sensing technology,there are a large number of high-definition re-mote sensing images every day.Because the target's feature map will shift after the target passes through the deep convolution net-work,which has a great impact on small target detection.In order to solve this problem,this paper introduce the receptive field mod-ule RFB in the relevant algorithm to enhance the discrimination of small target features.This paper further introduces the ASPP spa-tial pyramid module into the backbone network to expand the receptive field of the backbone network,so as to strengthen the detec-tion of small and medium-sized targets.In order to evaluate its effectiveness,experiments are carried out in YOLOX target detection algorithm.The results show that this improvement can significantly improve the detection accuracy of small targets without affecting the reasoning speed.
Keywords：object detectionsmall targetreceptive field
Publication Date：2025-09-20
Online Publishing Date：2025-12-23(First online date of this platform, not the publication date of the document)
Pages：5( 2404-2408 )