[1] Wang C Q, Shi L, Zhang X C et al. Effect of welding defects on fatigue behavior of dissimilar aluminum alloy TIG butt joint[J]. Journal of Beijing University of Aeronautics and Astronautics, 47, 1505-1514(2021).
[2] Luo H J. Establishment of typical defect reference image library for digital radiography aluminum alloy lap welding[J]. Nondestructive Testing, 41, 23-26(2019).
[3] Fan D, Hu A D, Huang J K et al. X-ray image defect recognition method for pipe weld based on improved convolutional neural network[J]. Transactions of the China Welding Institution, 41, 7-11, 97(2020).
[4] Cao Z J, Zhang L. Fast object detection algorithm based on faster-RCNN[J]. Aerospace Control, 38, 49-55(2020).
[5] Xu K, Wang X Y, Wang D. A scalable OpenCL-based FPGA accelerator for YOLOv2[C], 18742103(2019).
[9] Tang X Y, Huang J B, Feng J W et al. Image segmentation and defect detection of insulators based on U-net and YOLOv4[J]. Journal of South China Normal University (Natural Science Edition), 52, 15-21(2020).
[10] Huang H X, Jin X. Small target defect detection based on YOLOv4[J]. Electronics World, 146-147(2021).
[11] Wang J C, Wang X F. Automatic detection of weld defects in X-ray based on ButterWorth filtering[J]. Microcomputer & Its Applications, 36, 21-24(2017).
[12] Wang X, Gao W X, Wu X M et al. Image detecting of weld defect based on fuzzy pattern recognition[J]. Journal of Xi’an Shiyou University (Natural Science Edition), 31, 115-121(2016).
[13] Chen L, Zhang S J, Wang Y X. Based on improved YOLOv3 and its detection in remote sensing images[J]. Journal of Chinese Computer Systems, 41, 2321-2324(2020).
[14] Fang Y X, Gan P, Chen L. Improved YOLOv3 algorithm for detection of metal surface defect[J]. Mechanical Science and Technology for Aerospace Engineering, 39, 1390-1394(2020).
[15] Sun J, Guo D B, Yang T T et al. Real-time object detection based on improved YOLOv3 network[J]. Laser & Optoelectronics Progress, 57, 221505(2020).
[16] Lu Y H, Cai J Y, Zheng H et al. Researches on few-shot learning based on deep learning: an overview[J]. Telecommunication Engineering, 61, 125-130(2021).
[17] Yang Y, Li L W, Gao S Y et al. Objects detection from high-resolution remote sensing imagery using training-optimized YOLOv3 network[J]. Laser & Optoelectronics Progress, 58, 1601002(2021).