RESEARCH ACTUALITY AND THOUGHTS ON THE AUTOMATIC EXTRACTION OF LINEAR OBJECTS FROM REMOTE SENSING IMAGES
Fu Yong, Qin Zhiyuan and Gong Jingjing (Institute of Surveying and Mapping, Information Engineering University, Zhengzhou 450052)
Automatic recognition and acquisition of the objective information from remotely sensed images is a main developing direction of remote sensing data processing. As a classical question,automatic linear feature extraction from remote sensing images has attracted extensive attention. Automatic and semiautomatic road extraction is still a research hotspot. In this paper, by analyzing the basic road features in remote sensing images, the essential thought of road extraction is discussed, the actuality of semiautomatic road extraction home and abroad is summarized, the popular methods of road extraction are concluded and finally the thoughts and the plans of further research on this subject are presented.