Detection of linear features in SAR images: application to road network extraction

1998 ◽  
Vol 36 (2) ◽  
pp. 434-453 ◽  
Author(s):  
F. Tupin ◽  
H. Maitre ◽  
J.-F. Mangin ◽  
J.-M. Nicolas ◽  
E. Pechersky
Keyword(s):  
Road Network ◽  
Sar Images ◽  
Linear Features ◽  
Road Network Extraction

Road network extraction from spot panchromatic data

CISM journal ◽  
1989 ◽  
Vol 43 (2) ◽  
pp. 121-126 ◽  
Author(s):  
Douglas O’Brien
Keyword(s):  
Mathematical Morphology ◽  
Road Network ◽  
Processing Time ◽  
Binary Representation ◽  
Digital Imagery ◽  
Data Bases ◽  
Linear Features ◽  
Practical Solution ◽  
The Road ◽  
Road Network Extraction

The efficient revision of cartographic data bases using digital imagery implies some form of feature extraction. At present classification techniques can be used to extract certain area outlines, but the automatic detection of linear features such as roads is difficult. One possible method of extracting these features is through mathematical morphology. Mathematical morphology is a form of image treatment that has been applied to remote sensing in recent years. It is possible to extract a binary representation of the road network in an image using this approach, and then treat the results to remove extraneous features. The results demonstrate this process extracts, to a large extent, the information desired. Several caveats must be considered before viewing this as a practical solution. These include processing time, areas where it can be applied, and content of the results.

scholarly journals A Multiscale Method for Road Network Extraction from High-Resolution SAR Images Based on Directional Decomposition and Regional Quality Evaluation

2021 ◽  
Vol 13 (8) ◽  
pp. 1476
Author(s):  
Wenjing He ◽  
Hongjun Song ◽  
Yuanyuan Yao ◽  
Xinlin Jia
Keyword(s):  
High Resolution ◽  
Road Network ◽  
Quality Evaluation ◽  
Multiscale Method ◽  
Tensor Voting ◽  
Threshold Method ◽  
Sar Images ◽  
Practical Applications ◽  
Road Network Extraction ◽  
Disaster Assessment

Road network is an important part of modern transportation. For the demands of accurate road information in practical applications such as urban planning and disaster assessment, we propose a multiscale method to extract road network from high-resolution synthetic aperture radar (SAR) images, which consists of three stages: potential road area segmentation, preliminary network generation, and road network refinement. Multiscale analysis is implemented using an image pyramid framework together with a fixed-size filter. First, a directional road detector is designed to highlight road targets in feature response maps. Subsequently, adaptive fusion is performed independently at each image scale, followed by a threshold method to produce potential road maps. Then, binary maps are decomposed according to the obtained direction information. For each connected component (CC), quality evaluation is conducted to further distinguish road segments and polynomial curve fitting is adopted as a thinning method. Multiscale information fusion is realized through the weighted sum of road curves. Finally, tensor voting and spatial regularization are employed to generate the final road network. Experiments on three TerraSAR images demonstrate the effectiveness of the proposed algorithm to extract road network completely and correctly.

Road Network Extraction From Low-Contrast SAR Images

2019 ◽  
Vol 16 (6) ◽  
pp. 907-911 ◽  
Author(s):  
Tao Zeng ◽  
Qiang Gao ◽  
Zegang Ding ◽  
Jing Chen ◽  
Gen Li
Keyword(s):  
Road Network ◽  
Sar Images ◽  
Low Contrast ◽  
Road Network Extraction
Sign in / Sign up

Export Citation Format

Share Document