The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLII-3/W3
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-3/W3, 201–207, 2017
https://doi.org/10.5194/isprs-archives-XLII-3-W3-201-2017
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-3/W3, 201–207, 2017
https://doi.org/10.5194/isprs-archives-XLII-3-W3-201-2017

  20 Oct 2017

20 Oct 2017

FOREST ROADIDENTIFICATION AND EXTRACTIONOF THROUGH ADVANCED LOG MATCHING TECHNIQUES

W. Zhang1, B. Hu1, and L. Quist2 W. Zhang et al.
  • 1Dept. of Earth and Space Science and Engineering, York University, 4700 Keele St, Toronto, Canada
  • 2Hearst Forest Management Inc., 1589 Highway 11 West, Hearst, Canada

Keywords: Forest road extraction, LiDAR, template matching, LoG, segmentation, tensor voting

Abstract. A novel algorithm for forest road identification and extraction was developed. The algorithm utilized Laplacian of Gaussian (LoG) filter and slope calculation on high resolution multispectral imagery and LiDAR data respectively to extract both primary road and secondary road segments in the forest area. The proposed method used road shape feature to extract the road segments, which have been further processed as objects with orientation preserved. The road network was generated after post processing with tensor voting. The proposed method was tested on Hearst forest, located in central Ontario, Canada. Based on visual examination against manually digitized roads, the majority of roads from the test area have been identified and extracted from the process.