Fast semantic segmentation of surface engineering activity area based on multi-feature U-Net

doi:10.13474/j.cnki.11-2246.2021.376

Abstract

Abstract: In order to effectively monitor the engineering activities with filling, digging, mining and stripping behaviors, this paper proposes a remote sensing multi-feature semantic segmentation model for pixel-level surface engineering activity extraction. In this model, GF-2 optical remote sensing images are used as the data source, and U-Net is used as deep neural network. By manual labeling, the surface engineering activity image samples are constructed for model training with multi-dimensional features, so as to achieve the effect of surface engineering activity extraction. The experimental result shows that the overall extraction accuracy of this method is 87.36%, and the average accuracy is 86.78%, which is better than KNN and SVM. The proposed method provides a technical reference for the automatic supervision of engineering activities.

Key words: optical remote sensing image, multi-feature, U-Net model, deep learning, surface engineering activity area

CLC Number:

P237

HUANG Lei, CHEN Erdonghao. Fast semantic segmentation of surface engineering activity area based on multi-feature U-Net[J]. Bulletin of Surveying and Mapping, 2021, 0(12): 75-78.

References

[1] 曹斌,邱振戈,朱述龙,等.BP神经网络遥感水深反演算法的改进[J].测绘通报,2017(2):40-44.
[2] 樊彦丽.基于多特征的SVM高分辨率遥感影像分类研究[D].北京:中国地质大学(北京), 2018.
[3] 张慧,王坤峰,王飞跃.深度学习在目标视觉检测中的应用进展与展望[J].自动化学报,2017, 43(8):1289-1305.
[4] 侯一民,周慧琼,王政一.深度学习在语音识别中的研究进展综述[J].计算机应用研究,2017, 34(8):2241-2246.
[5] 彭欣.基于深度学习的数字图书馆跨媒体语义检索方法研究[J].情报探索,2018,1(2):16-19.
[6] CHEN Y, LIN Z, ZHAO X, et al. Deep learning-based classification of hyperspectral data[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, 7(6):2094-2107.
[7] LUUS F P S, SALMON B P, VAN D B F, et al. Multiview deep learning for land-use classification[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 12(12):2448-2452.
[8] LI R R, LIU W J, YANG L, et al. Deep U-Net:a deep fully convolutional network for pixel-level sea-land segmentation[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018, 11(11):3954-3962.
[9] 刘尚旺,崔智勇,李道义.基于U-Net网络多任务学习的遥感图像建筑地物语义分割[J].国土资源遥感,2020,32(4):74-83.
[10] 郝建明.面向地理国情普查的高分辨率遥感影像半自动解译技术研究[D].重庆:重庆交通大学, 2016.
[11] XU Y Y, WU L,XIE Z, et al. Building extraction in very high resolution remote sensing imagery using deep learning and guided filters[J]. Remote Sensing, 2018, 10(1):144.
[12] PENG D F, ZHANG Y J, GUAN H Y. End-to-end change detection for high resolution satellite images using improved U-Net++[J]. Remote Sensing, 2019, 11(11):1382.
[13] 于佩鑫,周询,刘素红,等.东北黑土区侵蚀沟遥感影像特征提取与识别[J].遥感学报, 2018, 22(4):611-620.

[1]	LIU Li, DONG Xianmin, LIU Juan, WEN Xuehu. A new method of remote sensing interpretation production based on integration of human-machine and intelligence [J]. Bulletin of Surveying and Mapping, 2022, 0(7): 118-123,137.
[2]	CAI Roudan. An intelligent identification method of user identity based on asynchronous trajectory [J]. Bulletin of Surveying and Mapping, 2022, 0(7): 158-162,167.
[3]	TENG Wenxin, ZHANG Jianchen, SHAO Jie. Lane-level high-precision positioning algorithm based on integrated spatio-temporal proximity and CNN [J]. Bulletin of Surveying and Mapping, 2022, 0(6): 1-5,61.
[4]	ZHANG Jinhe, QIN Yuluo, ZHANG Zaiyan, SONG Weidong, ZHU Hongbo. Rural road crack segmentation method in complex scene [J]. Bulletin of Surveying and Mapping, 2022, 0(5): 74-78,88.
[5]	SHI Yun, SHI Longlong, NIU Minjie, ZHAO Kan. Multi-task automatic identification of loess landslide based on one-stage instance segmentation network [J]. Bulletin of Surveying and Mapping, 2022, 0(4): 26-31.
[6]	WANG Xue, LIANG Ke, SUI Lichun, ZHONG Mianqing, ZHU Jianfeng. Rural buildings extraction based on deep learning model with dilated convolution and pyramid representation [J]. Bulletin of Surveying and Mapping, 2022, 0(4): 61-65.
[7]	LUO Guowei, YE Jiayuan, WANG Jinfeng. Multi-source POI matching method based on multi-feature similarity [J]. Bulletin of Surveying and Mapping, 2022, 0(4): 96-100.
[8]	GAO Ming, ZHOU Xinxin, LIU Qi, YANG Guangdi, WU Changbin. Automatic monitoring of farmland occupation by farm house based on deep learning network [J]. Bulletin of Surveying and Mapping, 2022, 0(3): 47-53.
[9]	SUN Qinqin, CAI Guoyin, YANG Liuzhong, ZHANG Ning, DU Mingyi. Research on urban land use extraction at the metropolitan scale [J]. Bulletin of Surveying and Mapping, 2022, 0(2): 62-66.
[10]	ZHANG Ziqiang, LIU Tao, DU Ping, SUO Xuhong, YANG Guolin. Classification of building group patterns using graph residual neural network [J]. Bulletin of Surveying and Mapping, 2022, 0(1): 1-7.
[11]	CHE Zijie, GAO Fei, WU Zhaofu, LI Zhenxuan. Multi-source remote sensing image flood disaster information extraction and change analysis based on improved U-Net network [J]. Bulletin of Surveying and Mapping, 2022, 0(1): 26-32.
[12]	CHENG Rui, GAO Jian, XING Qiang, SUN Zhongchang. An optimized Faster R-CNN small target detection method [J]. Bulletin of Surveying and Mapping, 2021, 0(9): 21-27.
[13]	CHUN Jin, ZHANG Xinchang, GUO Haijing, ZHANG Jianguo, JIN Shicheng. Spatial sampling of population based on multi-source information and deep learning feature extraction [J]. Bulletin of Surveying and Mapping, 2021, 0(8): 42-47.
[14]	LI Zihao, TANG Chao. Analysis of intelligent identification algorithm for shield tunnel cracks based on high-definition industrial camera [J]. Bulletin of Surveying and Mapping, 2021, 0(8): 83-87,101.
[15]	WANG Xuewen, ZHAO Qingzhan, TIAN Wenzhong, LONG Xiang, JIANG Ping. Influence of U-Net model on the accuracy of shelter forest extraction with different spatial resolutions [J]. Bulletin of Surveying and Mapping, 2021, 0(6): 39-43.