TO–YOLOX: a pure CNN tiny object detection model for remotesensing images  

作　　者：Zhe Chen Yuan Liang Zhengbo Yu Ke Xu Qingyun Ji Xueqi Zhang Quanping Zhang Zijia Cui Ziqiong He Ruichun Chang Zhongchang Sun Keyan Xiao Huadong Guo 

机构地区：[1]School of Mathematics and Physics,Chengdu University of Technology,Chengdu,People’s Republic of China [2]Key Laboratory of Digital Earth Science,Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing,People’s Republic of China [3]International Research Centre of Big Data for Sustainable Development Goals,Beijing,People’s Republic of China [4]Geomathematics Key Laboratory of Sichuan Province,Chengdu University of Technology,Chengdu,People’s Republic of China [5]Digital Hu Line Research Institute,Chengdu University of Technology,Chengdu,People’s Republic of China [6]School of Management Science,Chengdu University of Technology,Chengdu,People’s Republic of China [7]School of Earth Science and Resources,China University of Geosciences(Beijing),Beijing,People’s Republic of China [8]MNR Key Laboratory of Metallogeny and Mineral Assessment,Institute of Mineral Resources,Chinese Academy of Geological Sciences,Beijing,People’s Republic of China

出　　处：《International Journal of Digital Earth》2023年第1期3882-3904,共23页国际数字地球学报（英文）

基　　金：funded by the Innovative Research Program of the International Research Center of Big Data for Sustainable Development Goals(Grant No.CBAS2022IRP04);the Sichuan Natural Resources Department Project(Grant NO.510201202076888);the Project of the Geological Exploration Management Department of the Ministry of Natural Resources(Grant NO.073320180876/2);the Key Research and Development Program of Guangxi(Guike-AB22035060);the National Natural Science Foundation of China(Grant No.42171291);the Chengdu University of Technology Postgraduate Innovative Cultivation Program:Tunnel Geothermal Disaster Susceptibility Evaluation in Sichuan-Tibet Railway Based on Deep Learning(CDUT2022BJCX015).

摘　　要：Remote sensing and deep learning are being widely combined in tasks such as urban planning and disaster prevention.However,due to interference occasioned by density,overlap,and coverage,the tiny object detection in remote sensing images has always been a difficult problem.Therefore,we propose a novel TO–YOLOX(Tiny Object–You Only Look Once)model.TO–YOLOX possesses a MiSo(Multiple-in-Singleout)feature fusion structure,which exhibits a spatial-shift structure,and the model balances positive and negative samples and enhances the information interaction pertaining to the local patch of remote sensing images.TO–YOLOX utilizes an adaptive IOU-T(Intersection Over Uni-Tiny)loss to enhance the localization accuracy of tiny objects,and it applies attention mechanism Group-CBAM(group-convolutional block attention module)to enhance the perception of tiny objects in remote sensing images.To verify the effectiveness and efficiency of TO–YOLOX,we utilized three aerial-photography tiny object detection datasets,namely VisDrone2021,Tiny Person,and DOTA–HBB,and the following mean average precision(mAP)values were recorded,respectively:45.31%(+10.03%),28.9%(+9.36%),and 63.02%(+9.62%).With respect to recognizing tiny objects,TO–YOLOX exhibits a stronger ability compared with Faster R-CNN,RetinaNet,YOLOv5,YOLOv6,YOLOv7,and YOLOX,and the proposed model exhibits fast computation.

关 键 词：Tiny object detection TO-YOLOX remote sensing image deep learning attentionmechanism 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]