MSC-YOLO:Improved YOLOv7 Based on Multi-Scale Spatial Context for Small Object Detection in UAV-View

作     者：Xiangyan Tang Chengchun Ruan Xiulai Li Binbin Li Cebin Fu 

作者机构：School of Computer Science and TechnologyHainan UniversityHaikou570228China Hainan Blockchain Technology Engineering Research CenterHainan UniversityHaikou570228China School of Cyberspace Security(School of Cryptology)Hainan UniversityHaikou570228China 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2024年第79卷第4期

页      面：983-1003页

核心收录：

学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 

基　　金：the Key Research and Development Program of Hainan Province(Grant Nos.ZDYF2023GXJS163,ZDYF2024GXJS014) National Natural Science Foundation of China(NSFC)(Grant Nos.62162022,62162024) the Major Science and Technology Project of Hainan Province(Grant No.ZDKJ2020012) Hainan Provincial Natural Science Foundation of China(Grant No.620MS021) Youth Foundation Project of Hainan Natural Science Foundation(621QN211) 

主　　题：Small object detection YOLOv7 multi-scale attention spatial context 

摘      要：Accurately identifying small objects in high-resolution aerial images presents a complex and crucial task in thefield of small object detection on unmanned aerial vehicles(UAVs).This task is challenging due to variations inUAV flight altitude,differences in object scales,as well as factors like flight speed and motion *** enhancethe detection efficacy of small targets in drone aerial imagery,we propose an enhanced You Only Look Onceversion 7(YOLOv7)algorithm based on multi-scale spatial *** build the MSC-YOLO model,whichincorporates an additional prediction head,denoted as P2,to improve adaptability for small *** replaceconventional downsampling with a Spatial-to-Depth Convolutional Combination(CSPDC)module to mitigatethe loss of intricate feature details related to small ***,we propose a Spatial Context Pyramidwith Multi-Scale Attention(SCPMA)module,which captures spatial and channel-dependent features of smalltargets acrossmultiple *** module enhances the perception of spatial contextual features and the utilizationof multiscale feature *** the Visdrone2023 and UAVDT datasets,MSC-YOLO achieves remarkableresults,outperforming the baseline method YOLOv7 by 3.0%in terms ofmean average precision(mAP).The MSCYOLOalgorithm proposed in this paper has demonstrated satisfactory performance in detecting small targets inUAV aerial photography,providing strong support for practical applications.