Improved Multistage Road Detection Algorithm with Robust Ground Point and Building Point Extraction
For road network extraction, different techniques have been developed in which multistage road network extraction model using Probabilistic Support Vector Machine (PSVM), Dominant Singular Measure (DSM) and Constraint Satisfaction Neural Network-Complementary Information Integration (CSNN-CII) algorithms has better outcomes compared with the other extraction frameworks. However, the road network extraction in urban regions has complexity due to the presence of buildings, narrow roads and shadow features which are similar to the road features. Hence, the integration of robust ground points and building point's extraction is proposed with the multistage road network extraction model in this paper. The robust ground point extraction phase consists of skewness and kurtosis based balancing algorithm for removing the non-road points from ground points by measuring the optimal intensity threshold and rotating neighborhood algorithm for eliminating the narrow roads from the road network model. Furthermore, the building points extraction is performed based on the modeling of shadows. The building points are extracted by Canny edge detection and Hough transform for generating the line segments based on the extracted edges. Then, K-medians clustering algorithm is applied for producing the color HSV segmented image and shadow image information. The extracted ground, building and road points are integrated by using CSNN-CII algorithm. Then, Region Part Segmentation (RPS) is applied for separating the roads from non-road regions. Finally, the Medial-Axis-Transform (MAT)-based hypothesis verification is used for automatically complete the road network extraction framework. The experimental results show that the ground and building point extraction based road network model achieves better performance.
No Reference information available - sign in for access.
No Citation information available - sign in for access.
No Supplementary Data.
No Article Media
Document Type: Research Article
Publication date: November 1, 2017
More about this publication?
- Journal of Computational and Theoretical Nanoscience is an international peer-reviewed journal with a wide-ranging coverage, consolidates research activities in all aspects of computational and theoretical nanoscience into a single reference source. This journal offers scientists and engineers peer-reviewed research papers in all aspects of computational and theoretical nanoscience and nanotechnology in chemistry, physics, materials science, engineering and biology to publish original full papers and timely state-of-the-art reviews and short communications encompassing the fundamental and applied research.
- Editorial Board
- Information for Authors
- Submit a Paper
- Subscribe to this Title
- Terms & Conditions
- Ingenta Connect is not responsible for the content or availability of external websites