基于上下文协同感知的航拍小目标检测算法

打开文本图片集

Aerial small target detection algorithm based on context collaborative perception

YANG Luxia 1，2 ，LIU Zekai 1，2 ， ZHANG Hongrui 1，2* ，MA Yongjie³

（1.School of Computer Science and Technology， Taiyuan Normal University， Jinzhong O3O6l9，China; 2. Shanxi Provincial Key Laboratory of Intelligent Optimization Computing and Blockchain Technology ， Jinzhong 030619，China; 3. School of Physics and Electronic Engineering，Northwest Normal University， Lanzhou 730070，China）

Abstract： Aiming at the problem of low detection accuracy of small targets caused by large scale change and complex background in aerial photography，a detection algorithm based on multi-scale collaborative perception of context is proposed. Firstly，a lightweight multi-scale enhancement module （LMEM） is constructed to activate local significance information with attntion mechanism to enhance feature capture capability of small targets. Secondly，the context-driven cross-level feature fusion architecture module （CCFFAM） is designed. The integration of receptive field attntion convolution and dynamic sampling technology realizes multi-layer feature space-channel dual alignment and adaptive weighted fusion to enhance feature fusion capability.Finally，the scale distribution of the detection head was reconstructed， and the original loss function was replaced with Focaler-CIoU to optimize the bounding box regression process，ensuring that the model is lightweight while having a high detection efficiency.Experiments on VisDrone2Ol9 and DOTAvl data sets show that the proposed method reduces the number of model parameters by 27.9% （2.17M） compared with the original model，and the mAP increases by 5.3% and （204号 1.4% respectively，which verifies that the algorithm has a good detection effect.

Key words： UAVaerial photography; cross-dimensional interaction;cross-layer feature fusion; lightweight

1引言

随着计算机视觉领域的深人发展，小目标检测作为目标检测的重要分支，在无人机航拍[1-3]、路桥检测[4]、智慧交通[5-6]等领域有着广泛的应用。（剩余16509字）