Acta Geodaetica et Cartographica Sinica ›› 2018, Vol. 47 ›› Issue (7): 950-958.doi: 10.11947/j.AGCS.2018.20170596

Previous Articles     Next Articles

Road Extraction from High-resolution Remote Sensing Images Based on Adaptive Circular Template and Saliency Map

LIAN Renbao1,2, WANG Weixing1, LI Juan1   

  1. 1. Collage of Physics and Information Engineering, Fuzhou University, Fuzhou 360018, China;
    2. Collage of Electronics and Information Science, Fujian Jiangxia University, Fuzhou 360018, China
  • Received:2017-10-18 Revised:2017-12-27 Online:2018-07-20 Published:2018-07-25
  • Supported by:
    The National Natural Science Foundation of China(No. 61170147);The Fujian Jiangxia University Youth Foundation(No. JXZ2016001)

Abstract: In order to solve the problem that the existing template matching algorithms need to manually set template sizes, it is proposed that an adaptive circular template algorithm for extracting the road information in a high-resolution remote sensing image.Firstly, an improved local morphological gradient map is constructed to calculate the size of the circular template automatically;then, a modified road saliency map is made.It is designed that a new algorithm to search for the most likely center points of a road between the start and the end points by the way of iterative interpolation.The comprehensive utilization of the saliency information and the angles of geometric during the search process make the algorithm have the better recognition effect.The experimental results show that the proposed algorithm can be applied to high-resolution remote sensing images of different conditions, to extract the road information more effectively.

Key words: circular template, road extraction, high-resolution remote sensing image, saliency map, morphological gradient, adaptive template

CLC Number: