Enhanced-YOLOv8: A new small target detection model

Abstract

Small target detection is a very difficult task and remains one of the most challenging problems in computer vision due to variations in object shape, appearance and position, as well as the effects of lighting and occlusion during imaging. To improve the accuracy of the small target detection results, we propose a new small target detection model, Enhanced-YOLOv8. Firstly, a small target detection level (STDL) is added to the original effective feature layer of YOLOv8, which not only provides richer semantic information but also get more accurate target localization and bounding box accuracy. When detecting small targets, the detection accuracy can be improved by more detailed information. Then, the fusion convolutional block attention module (FCBAM) is proposed by introducing the position attention module (PAM) based on the traditional CBAM. FCBAM not only can adaptively select and fuse the most representative features, but also can better capture the image important features at different positions in the image and enhance spatial detail perception. Finally, semantic fusion network (SFN) is proposed on the basis of residual network, which introduces semantic information of high-layer feature into low-layer feature. It can adaptively guide the fusion of high-layer feature and low-layer feature to reduce the loss of feature information. After experimental verification, the Enhanced-YOLOv8 proposed improves the accuracy of the detection results.