[2] EslamiM, Eslami M, FaezK, Faez K. V6130-V6135[C](2010).

[3] ZhengS, ZhengS, ZhengS, Zheng S, LiuJ, LiuJ, LiuJ, Liu J, ShiW, ShiW, ShiW, Shi W. Road central contour extraction from high resolution satellite image using tensor voting framework[C]. Dalian, 3248-3253(2006).

[4] ZhuD, ZhuD, Zhu D, WenX, WenX, Wen X, LingC, LingC, Ling C. Road extraction based on the algorithms of MRF and hybrid model of SVM and FCM[C]. Yunnan, 1-4(2011).

[5] Wegner J D, WegnerJ D, WegnerJ D, Montoya ZegarraJ A, Montoya ZegarraJ A, Montoya Zegarra J A, SchindlerK, SchindlerK, Schindler K. A higher-order CRF model for road network extraction[C]. OR, 1698-1705(2013).

[6] Wegner J D, WegnerJ D, WegnerJ D, Montoya ZegarraJ A, Montoya ZegarraJ A, Montoya Zegarra J A, SchindlerK, SchindlerK, Schindler K. Road networks as collections of minimum cost paths[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 108, 128-137(2015).

[7] DasS, DasS, Das S, Mirnalinee T T, MirnalineeT T, MirnalineeT T, VargheseK, VargheseK, Varghese K. Use of salient features for the design of a multistage framework to extract roads from high-resolution multispectral satellite images[J]. IEEE Transactions on Geoscience and Remote Sensing, 49, 3906-3931(2011).

[9] ZhangZ, ZhangZ, ZhangZ, Zhang Z, WangY, WangY, WangY, Wang Y, LiuQ, LiuQ, LiuQ, Liu Q. A CNN based functional zone classification method for aerial images[C], 5449-5452(2016).

[10] MaggioriE, MaggioriE, MaggioriE, Maggiori E, TarabalkaY, TarabalkaY, TarabalkaY, Tarabalka Y, CharpiatG, CharpiatG, CharpiatG, Charpiat G. Convolutional neural networks for large-scale remote-sensing image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 55, 645-657(2017).

[11] MnihV, Mnih V, Hinton G E, HintonG E. Learning to detect roads in high-resolution aerial images[C]. Greek, 210-223(2010).

[12] WeiY, WeiY, Wei Y, WangZ, WangZ, Wang Z, XuM, XuM, Xu M. Road structure refined CNN for road extraction in aerial image[J]. IEEE Geoscience and Remote Sensing Letters, 14, 709-713(2017).

[13] RonnebergerO, RonnebergerO, Ronneberger O, FischerP, FischerP, Fischer P, BroxT, BroxT, Brox T. U-Net: Convolutional networks for biomedical image segmentation[C]. Germany, 234-241(2015).

[14] HeK, HeK, HeK, He K, ZhangX, ZhangX, ZhangX, Zhang X, RenS, RenS, RenS, Ren S. Deep residual learning for image recognition[C], 770-778(2016).

[15] SinghP, Singh P, DashR, Dash R. A two-step deep convolution neural network for road extraction from aerial images[C]. India, 660-664(2019).

[16] HongZ, HongZ, HongZ, Hong Z, MingD, MingD, MingD, Ming D, ZhouK, ZhouK, ZhouK, Zhou K. Road extraction from a high spatial resolution remote sensing image based on richer convolutional features[J]. IEEE Access, 6, 46988-47000(2018).

[17] ZhongZ, ZhongZ, ZhongZ, Zhong Z, LiJ, LiJ, LiJ, Li J, CuiW, CuiW, CuiW, Cui W. Fully convolutional networks for building and road extraction: preliminary results[C], 1591-1594(2016).

[18] FuG, FuG, FuG, Fu G, LiuC, LiuC, LiuC, Liu C, ZhouR, ZhouR, ZhouR, Zhou R. Classification for high resolution Rremote sensing imagery using a fully convolutional network[J]. Remote Sensing, 9, 498(2017). https://doi.org/10.3390/rs9050498

[19] PanboonyuenT, PanboonyuenT, PanboonyuenT, Panboonyuen T, JitkajornwanichK, JitkajornwanichK, JitkajornwanichK, Jitkajornwanich K, LawawirojwongS, LawawirojwongS, LawawirojwongS, Lawawirojwong S. Road segmentation of remotely-sensed images using deep convolutional neural networks with landscape metrics and conditional random fields[J]. Remote Sensing, 9, 680(2017). https://doi.org/10.3390/rs9070680

[20] Qin X B, QinX B, QinX B, QinX B, Zhang Z C, ZhangZ C, ZhangZ C, ZhangZ C, Huang C Y, HuangC Y, HuangC Y, HuangC Y. BASNet: Boundary-aware salient object detection[C]. Long Beach, 7479-7489(2019).

[21] Devalla S K, DevallaS K, DevallaS K, DevallaS K, Renukanand P K, RenukanandP K, RenukanandP K, RenukanandP K, Sreedhar B K, SreedharB K, SreedharB K, SreedharB K. DRUNET: A dilated-residual u-net deep learning network to digitally stain optic nerve head tissues in optical coherence tomography images[J]. Biomedical Optics Express, 9, 3244-3265(2018).

[22] Mnih V. Machine learning for aerial image labeling[D](2013).

[23] Chen L C, ChenL C, ChenL C, ChenL C, PapandreouG, PapandreouG, PapandreouG, Papandreou G, SchroffF, SchroffF, SchroffF, Schroff F. Rethinking atrous convolution for semantic image segmentation[webpage]. https://arxiv.org/abs/1706.05587

[24] Chen L C, ChenL C, ChenL C, ChenL C, ZhuY, ZhuY, ZhuY, Zhu Y, PapandreouG, PapandreouG, PapandreouG, Papandreou G. Encoder-decoder with atrous separable convolution for semantic image segmentation[webpage]. https://arxiv.org/abs/1802.02611

[25] BadrinarayananV, BadrinarayananV, Badrinarayanan V, KendallA, KendallA, Kendall A, CipollaR, CipollaR, Cipolla R. SegNet: A deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 2481-2495(2017).

[26] ChaurasiaA, Chaurasia A, CulurcielloE, Culurciello E. LinkNet: Exploiting encoder representations for efficient semantic segmentation[C]. United states, 1-4(2017).