Automated Road Extraction from High Resolution Multispectral Imagery
Road networks represent a vital component of geospatial data sets in high demand, and thus contribute significantly to extraction labor costs. Multispectral imagery has only recently become widely available at high spatial resolutions, and modeling spectral content has received limited consideration for road extraction algorithms. This paper presents a methodology that exploits spectral content for fully automated road centerline extraction. Preliminary detection of road centerline pixel candidates is performed with Anti-parallel-edge Centerline Extraction (ACE). This is followed by constructing a road vector topology with a fuzzy grouping model that links nodes from a self-organized mapping of the ACE pixels. Following topology construction, a self-supervised road classification (SSRC) feedback loop is implemented to automate the process of training sample selection and refinement for a road class, as well deriving practical spectral definitions for non-road classes. SSRC demonstrates a potential to provide dramatic improvement in road extraction results by exploiting spectral content. Road centerline extraction results are presented for three 1m color-infrared suburban scenes, which show significant improvement following SSRC.
- Research Organization:
- Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- AC05-76RL01830
- OSTI ID:
- 15020727
- Report Number(s):
- PNNL-SA-41582; 400403909; TRN: US200521%%112
- Journal Information:
- Photogrammetric Engineering and Remote Sensing, Vol. 70, Issue 12
- Country of Publication:
- United States
- Language:
- English
Similar Records
SPECTRUM analysis of multispectral imagery in conjunction with wavelet/KLT data compression
Modeling Spatial Dependencies in High-Resolution Overhead Imagery
Related Subjects
99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE
MULTISPECTRAL PHOTOGRAPHY
REMOTE SENSING
ROADS
ALGORITHMS
SPATIAL RESOLUTION
TOPOLOGY
DATA ANALYSIS
Road extraction
full automation
multispectral imagery
self-supervised road classification