Iterative nearest edge algorithm for aerial image road dataset preparation

doi:10.11947/j.AGCS.2023.20210331

Abstract

Abstract: The quality and efficiency of dataset preparation are common basic issues that are concerned in the field of remote sensing image intelligent processing. Aiming at the difficulty of preparing the road extraction dataset for aerial image, this paper proposes an iterative algorithm for the optimization of the nearest edge feature to prepare the road extraction dataset for aerial image. The algorithm first establishes the homography transformation relationship between aerial image and satellite image through manual assistance, and projects the satellite image onto the aerial image to realize the coarse registration of the satellite image to the aerial image based on the four-point method. Then, the edge detection operator is used to extract the edge features of the image after the rough registration. Finally, the precise registration of the image is completed by the iterative nearest edge optimization algorithm, which improves the preparation accuracy of the road dataset of the aerial image. At the end of the thesis, a road extraction dataset preparation experiment is carried out, which proves that the road dataset preparation method proposed in this paper can significantly improve the efficiency of road dataset preparation while meeting the accuracy requirements of the dataset.

Key words: road dataset, aerial image, N-point method, homography, iterative closest edge algorithm

CLC Number:

P237

YANG Dongfang, ZHAO Jiawei, LI Yongfei, XIAO Peng, YANG Jinglan. Iterative nearest edge algorithm for aerial image road dataset preparation[J]. Acta Geodaetica et Cartographica Sinica, 2023, 52(1): 82-92.

References

[1] 肖俊文. 基于深度学习的遥感图像自适应道路提取方法研究[D]. 成都:成都信息工程大学,2019. XIAO Junwen. Research on adaptive road extraction method from remote sensing image based on deep learning[D]. Chengdu: Chengdu University of Information Technology, 2019.
[2] 赵阳. 基于深度学习的遥感图像道路提取[D]. 西安: 西安电子科技大学, 2019. ZHAO Yang. Remote sensing image road extraction based on deep learning[D]. Xi'an: Xidian University, 2019.
[3] 张永宏, 何静, 阚希, 等. 遥感图像道路提取方法综述[J]. 计算机工程与应用, 2018, 54(13): 1-10, 51. ZHANG Yonghong, HE Jing, KAN Xi, et al. Summary of road extraction methods for remote sensing images[J]. Computer Engineering and Applications, 2018, 54(13): 1-10, 51.
[4] KESTUR R, FAROOQ S, ABDAL R, et al. UFCN: a fully convolutional neural network for road extraction in RGB imagery acquired by remote sensing from an unmanned aerial vehicle[J]. Journal of Applied Remote Sensing, 2018, 12(1): 016020.
[5] 何磊, 李玉霞, 彭博, 等. 基于生成对抗网络的无人机图像道路提取[J]. 电子科技大学学报, 2019, 48(4): 580-585. HE Lei, LI Yuxia, PENG Bo, et al. Road extraction with UAV images based on generative adversarial networks[J]. Journal of University of Electronic Science and Technology of China, 2019, 48(4): 580-585.
[6] 季顺平, 魏世清.遥感影像建筑物提取的卷积神经元网络与开源数据集方法[J]. 测绘学报,2019,48(4):448-459. DOI: 10.11947/j.AGCS.2019.20180206. JI Shunping, WEI Shiqing. Building extraction via convolutional neural networks from an open remote sensing building dataset[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48(4):448-459. DOI: 10.11947/ j.AGCS.2019.20180206.
[7] 戴激光, 王杨, 杜阳, 等. 光学遥感影像道路提取的方法综述[J]. 遥感学报, 2020, 24(7): 804-823. DAI Jiguang, WANG Yang, DU Yang, et al. Development and prospect of road extraction method for optical remote sensing image[J]. Journal of Remote Sensing, 2020, 24(7): 804-823.
[8] 鲁德辉. 基于深度学习的遥感影像道路自动提取研究[D]. 成都: 电子科技大学, 2020. LU Dehui. Research on road automatic extraction of remote sensing image based on deep learning[D]. Chengdu: University of Electronic Science and Technology of China, 2020.
[9] 谢婷婷. 基于深度学习的遥感图像道路检测[D]. 汕头: 汕头大学, 2018. XIE Tingting. Road detection in remote sensing image based on deep learning[D]. Shantou: Shantou University, 2018.
[10] 管来福. 基于深度学习的高分辨率遥感图像道路提取方法研究[D]. 武汉: 湖北工业大学, 2020. GUAN Laifu. Research on road extraction method of high resolution remote sensing image based on deep learning[D]. Wuhan: Hubei University of Technology, 2020.
[11] KUSHNIR M, SHIMSHONI I. Epipolar geometry estimation for urban scenes with repetitive structures[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(12): 2381-2395.
[12] 段嘉旭. 基于单应性估计的多帧超声TOFD图像配准与降噪技术研究[D]. 成都: 西南交通大学, 2017. DUAN Jiaxu. Image registration and denoising of multi-frame ultrasonic TOFD images based on homography estimation[D]. Chengdu: Southwest Jiaotong University, 2017.
[13] 孙商文, 刘宇, 徐昭洪, 等. 基于全局最优变换矩阵的图像拼接方法[J]. 兵器装备工程学报, 2020, 41(11): 207-211. SUN Shangwen, LIU Yu, XU Zhaohong, et al. Image stitching based on global optimal homography matrix[J]. Journal of Ordnance Equipment Engineering, 2020, 41(11): 207-211.
[14] CANNY J. A computational approach to edge detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(6): 679-698.
[15] 王智文. 几种边缘检测算子的性能比较研究[J]. 制造业自动化,2012,34(11):14-16. WANG Zhiwen. Comparative research of capability of several detection operators for edge detection [J]. Manufacturing Automation, 2012, 34(11):14-16.
[16] 厉丹, 钱建生, 芦楠楠, 等. 图像边缘检测技术的改进[J]. 计算机工程与应用, 2010, 46(18): 164-166. LI Dan, QIAN Jiansheng, LU Nannan, et al. Improving of image edge detection technique[J]. Computer Engineering and Applications, 2010, 46(18): 164-166.
[17] 高力, 金飞, 江振治, 等. 顾及形变的影像边缘ICP匹配技术[J]. 测绘通报, 2019(12): 40-44. GAO Li, JIN Fei, JIANG Zhenzhi, et al. ICP image matching technology considering distorted image edge[J]. Bulletin of Surveying and Mapping, 2019(12): 40-44.
[18] 张波. 基于ICP和SVD的眼底图像配准研究[D]. 长春: 吉林大学, 2009. ZHANG Bo. Research on the ICP and the SVD of the fundus images registration methods[D]. Changchun: Jilin University, 2009.
[19] YAN Li, DAI Jicheng, TAN Junxiang, et al. Global fine registration of point cloud in LiDAR SLAM based on pose graph[J]. Journal of Geodesy and Geoinformation Science, 2020, 3(2): 26-35.
[20] ABDOLLAHI A, PRADHAN B, SHUKLA N, et al. Deep learning approaches applied to remote sensing datasets for road extraction: a state-of-the-art review[J]. Remote Sensing, 2020, 12(9): 1444.
[21] HE Hao, WANG Shuyang, WANG Shicheng, et al. A road extraction method for remote sensing image based on encoder decoder network[J]. Journal of Geodesy and Geoinformation Science, 2020, 3(2): 16-25.
[22] 宋廷强, 刘童心, 宗达, 等. 改进U-Net网络的遥感影像道路提取方法研究[J]. 计算机工程与应用, 2021, 57(14): 209-216. SONG Tingqiang, LIU Tongxin, ZONG Da, et al. Research on road extraction method from remote sensing images based on improved U-net network[J]. Computer Engineering and Applications, 2021, 57(14): 209-216.
[23] RUSSELL B C, TORRALBA A, MURPHY K P, et al. LabelMe: a database and web-based tool for image annotation[J]. International Journal of Computer Vision, 2008, 77(1): 157-173.
[24] 刘子伟. 融合结构化道路区域分割的车道线检测与跟踪算法研究[D]. 武汉: 武汉理工大学, 2019. LIU Ziwei. Research on lane detection and tracking algorithm based on structured road segmentation[D]. Wuhan: Wuhan University of Technology, 2019.
[25] DAI Yuchao, ZHANG Jing, HE Mingyi, et al. Salient object detection from multi-spectral remote sensing images with deep residual network[J]. Journal of Geodesy and Geoinformation Science, 2019, 2(2): 101-110.
[26] 王舒洋, 慕晓冬, 贺浩, 等. 航拍图像跨数据域特征迁移道路提取方法[J]. 测绘学报, 2020, 49(5): 611-621. DOI: 10.11947/j.AGCS.2020.20190274. WANG Shuyang, MU Xiaodong, HE Hao, et al. Feature-representation-transfer based road extraction method for cross-domain aerial images[J]. Acta Geodaetica et Cartographica Sinica, 2020, 49(5): 611-621. DOI: 10.11947/j.AGCS.2020.20190274.
[27] WANG Kexian, ZHENG Shunyi, LI Rui, et al. A deep double-channel dense network for hyperspectral image classification[J]. Journal of Geodesy and Geoinformation Science, 2021, 4(4): 46-62.
[28] LYU Jingguo, YANG Xingbin, ZHANG Danlu, et al. High-resolution remote sensing image semi-global matching method considering geometric constraints of connection points and image texture information[J]. Journal of Geodesy and Geoinformation Science, 2021, 4(4):97-112.