[5] [5] LIN E,QIN R J,EDGERTON J,et al.Crater detection from commercial satellite imagery to estimate unexploded ordnance in Cambodian agricultural land［J］.PLoS ONE, 2020,15(3):e229826.

[6] [6] BARNAWI A,BUDHIRAJA I,KUMAR K,et al.A comprehensive review on landmine detection using deep learning techniques in 5G environment:open issues and challenges［J］.Neural Computing and Applications,2022,34:21657-21676.

[15] [15] AROLA S,AKHLOUFI M A.Vision-based deep learning for UAVs collaboration［C］//Proceeding SPIE,Unmanned Systems Technology XXI.Baltimore:SPIE,2019:1102108.

[16] [16] QI Z P,LI X,LI H,et al.First results from drone-based transient electromagnetic survey to map and detect unexploded ordnance［J］.IEEE Geoscience and Remote Sensing Letters,2020,17(12):2055-2059.

[17] [17] BROCK A,DONAHUE J,SIMONYAN K.Large scale GAN training for high fidelity natural image synthesis［R］.Los Alamos：arXiv Preprint,2018:arXiv:1809.11096.

[21] [21] LIU W,ANGUELOV D,ERHAN D,et al.SSD:single shot multibox detector［C］//European Conference on Computer Vision.Cham:Springer,2016:21-37.

[22] [22] LOWE D G.Distinctive image features from scale invariant keypoints［J］.International Journal of Computer Vision,2004,60(2):91-110.