As a significant role for traffic management, city planning, road monitoring, GPS navigation and map updating, the technology of road extraction from a remote sensing （RS） image has been a hot research topic in rece...As a significant role for traffic management, city planning, road monitoring, GPS navigation and map updating, the technology of road extraction from a remote sensing （RS） image has been a hot research topic in recent years. In this paper, after analyzing different road features and road models, the road extraction methods were classified into the classification-based methods, knowledge-based methods, mathematical morphology, active contour model, and dynamic programming. Firstly, the road features, road model, existing difficulties and interference factors for road extraction were analyzed. Secondly, the principle of road extraction, the advantages and disadvantages of various methods and research achievements were briefly highlighted. Then, the comparisons of the different road extraction algorithms were performed, including road features, test samples and shortcomings. Finally, the research results in recent years were summarized emphatically. It is obvious that only using one kind of road features is hard to get an excellent extraction effect. Hence, in order to get good results, the road extraction should combine multiple methods according to the real applications. In the future, how to realize the complete road extraction from a RS image is still an essential but challenging and important research topic.展开更多
相比基于特征点的传统图像特征匹配算法,基于深度学习的特征匹配算法能产生更大规模和更高质量的匹配.为获取较大范围且清晰的路面裂缝图像,并解决弱纹理图像拼接过程中发生的匹配对缺失问题,本文基于深度学习LoFTR(detector-free local...相比基于特征点的传统图像特征匹配算法,基于深度学习的特征匹配算法能产生更大规模和更高质量的匹配.为获取较大范围且清晰的路面裂缝图像,并解决弱纹理图像拼接过程中发生的匹配对缺失问题,本文基于深度学习LoFTR(detector-free local feature matching with Transformers)算法实现路面图像的拼接,并结合路面图像的特点,提出局部拼接方法缩短算法运行的时间.先对相邻图像做分割处理,再通过LoFTR算法产生密集特征匹配,根据匹配结果计算出单应矩阵值并实现像素转换,然后通过基于小波变换的图像融合算法获得局部拼接后的图像,最后添加未输入匹配网络的部分图像,得到相邻图像的完整拼接结果.实验结果表明,与基于SIFT(scale-invariant feature transform)、SURF(speeded up robust features)、ORB(oriented FAST and rotated BRIEF)的图像拼接方法比较,研究所提出的拼接方法对路面图像的拼接效果更佳,特征匹配阶段产生的匹配结果置信度更高.对于两幅路面图像的拼接,采用局部拼接方法耗费的时间较改进之前缩短了27.53%.研究提出的拼接方案是高效且准确的,能够为道路病害监测提供总体病害信息.展开更多
基金financially supported by the Special Fund for Basic Scientific Research of Central Colleges(No.2013G2241019)Shaanxi Province Science and Technology Fund(No.2013KW03)Xi'an City Science and Technology Fund(No.CX1252(8))
文摘As a significant role for traffic management, city planning, road monitoring, GPS navigation and map updating, the technology of road extraction from a remote sensing （RS） image has been a hot research topic in recent years. In this paper, after analyzing different road features and road models, the road extraction methods were classified into the classification-based methods, knowledge-based methods, mathematical morphology, active contour model, and dynamic programming. Firstly, the road features, road model, existing difficulties and interference factors for road extraction were analyzed. Secondly, the principle of road extraction, the advantages and disadvantages of various methods and research achievements were briefly highlighted. Then, the comparisons of the different road extraction algorithms were performed, including road features, test samples and shortcomings. Finally, the research results in recent years were summarized emphatically. It is obvious that only using one kind of road features is hard to get an excellent extraction effect. Hence, in order to get good results, the road extraction should combine multiple methods according to the real applications. In the future, how to realize the complete road extraction from a RS image is still an essential but challenging and important research topic.
文摘相比基于特征点的传统图像特征匹配算法,基于深度学习的特征匹配算法能产生更大规模和更高质量的匹配.为获取较大范围且清晰的路面裂缝图像,并解决弱纹理图像拼接过程中发生的匹配对缺失问题,本文基于深度学习LoFTR(detector-free local feature matching with Transformers)算法实现路面图像的拼接,并结合路面图像的特点,提出局部拼接方法缩短算法运行的时间.先对相邻图像做分割处理,再通过LoFTR算法产生密集特征匹配,根据匹配结果计算出单应矩阵值并实现像素转换,然后通过基于小波变换的图像融合算法获得局部拼接后的图像,最后添加未输入匹配网络的部分图像,得到相邻图像的完整拼接结果.实验结果表明,与基于SIFT(scale-invariant feature transform)、SURF(speeded up robust features)、ORB(oriented FAST and rotated BRIEF)的图像拼接方法比较,研究所提出的拼接方法对路面图像的拼接效果更佳,特征匹配阶段产生的匹配结果置信度更高.对于两幅路面图像的拼接,采用局部拼接方法耗费的时间较改进之前缩短了27.53%.研究提出的拼接方案是高效且准确的,能够为道路病害监测提供总体病害信息.
