A Novel Algorithm of Road Network Detection for DMC+4HRSI
DMC+4 is a small satellite of Internationa Disaster Monitoring Constellation, which was designed as a proof of concept constellation, capable of multi spectral imaging of any part of the world every day. It is unique in that each satellite is independently owned and controlled by five separate nations, Algeria, Nigeria, Turkey, UK and China, but all satellites have been equally spaced around a sun-synchronous orbit to provide daily imaging capability. The DMC satellites provide a unique Earth Observation data that enables daily revisit anywhere in the world. In order to ensure the utilization DMC+4 small satellite image in geological survey, land use, environmental and disaster monitoring, preliminary deep processing system had been developed for receiving, preprocessing, and data distribution. The thematic information extraction algorithms of water, shoal, settlements, and roads had been studied with the DMC+4 images, and important progress had been made. The paper proposes a new road network detection algorithm aimed at the features of DMC+4 high resolution satellite images (HRSI) whose panchromatic image has a high resolution of 4m. In the high resolution remotely sensed image, road network has the following features: (1) the width of the road varies slightly and slowly; (2) the direction of the road varies slowly; (3) the local mean grey level of the road varies slowly; (4) the road is relatively long. Moreover, due to the increase of the resolution, the noises such as bridges, cars and trees along the road and its edge also increase. A novel road network detection algorithm namely Scansnake is proposed in the paper, and tested on the DMC+4 images. Compared to die traditional algorithm, this algorithm is an innovation. A large amount of experiments have proved that Scansnake algorithm has the advantage of object tracking under a series of complex conditions such as the variation of the width of the road and the change of grey feature distribution.
Jianming Gong Xiaomei Yang Min Wang Jian Lu Zongjian Lin Hai Jin
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China;State key Lab o State key Lab of Resources and Environment Information System, CAS, Beijing, China School of Geographic Sciences, Nanjing Normal University, Nanjing, China Chinese Academy of Surveying and Mapping, Beijing, China
国际会议
The 12th Conference of the International Association for Mathematical Geology(第12届国际数学地质大会)
北京
英文
553-556
2007-08-26（万方平台首次上网日期，不代表论文的发表时间）