[5] WANG Sen, WU Xing, ZHANG Yinghui, et al. A neuralnetwork ensemble method for effective crack segmentation using fully convolutional networks and multi-scale structured forests[J]. Machine Vision and Applications, 31, 16-30(2020).

[6] [6] THIRUPPATHIRAJ S, KUMAR U, BUCHKE S. Automatic pothole classification segmentation using roid smartphone senss camera images with machine learning techniques[C]2020 IEEE Region 10 Conference (Tencon). Osaka, Japan.USA: IEEE, 2020: 13861391.

[8] ATTIQUE K M, TALLHA A, ZHANG Y D, et al. Attrib-utes based skin lesion detection and recognition: a maskRCNN and transfer learning-based deep learning framework[J]. Pattern Recognition Letters, 143, 58-66(2021).

[9] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE, 39, 1137-1149(2017).

[10] [10] OLIVEIRA H, CREIA P L. Road surface crack detection: improved segmentation with pixelbasedrefinement[C]. 2017 25th European Signal Processing Conference (EUSIPCO), Greek KOS.USA: IEEE: 2017, 20262030.

[12] CHEN F C, JAHANSHAHI R M. Deep learning-based crack detection using convolutional neural networkand naïve bayes data fusion[J]. IEEE, 65, 4392-4440(2018).

[13] [13] RAZA A, HONG H, FANG T. PFAF: pyra feature wk f multimodal fusion[J]. IEEE Senss Letters, 2020, 4(12) : 14.

[15] [15] DUAN K, BAI S, XIE L, et al. Center: keypointtriplets f object detection[C]IEEECVF International Conference on Computer Vision (ICCV), Seoul, Kea (South).USA:IEEE,2019: 65686577.

[16] HEI L, JIA D. Cornernet: detecting objects as paired key-points[J]. International Journal of Computer Vision, 128, 642-656(2020).

[19] [19] ERTAM F, AYDIN G. Data classification with deeplearning using Tensflow[C]2017 International Conference on Computer Science Engineering (UBMK), Antalya. USA:IEEE,2017: 755758.