Abstract
Extraction of Roads, Rivers and other map objects is an important step in many military and civilian applications. In this process the information is extracted which possess high efficiency and accuracy and is fed into GIS (Geographical Information System). In this paper, we have explored different algorithms with better efficiency and accuracy. Road extraction can take place for two kinds of roads namely: urban and non-urban roads. Urban roads are more complex to analyze because of their architectural complexity, occlusions created by trees, heavy traffic and extensive network, whereas non-urban roads are easier to analyze because of less structural complexity. The proposed algorithm exploits the properties of road segments to develop customized operators to accurately derive the road segments. The customized operators include directional morphological enhancement, directional segmentation and thinning. The proposed algorithm is systematically evaluated on the basis of variety of images and compared with other algorithms (Canny, Sobel, Roberts, and Morphological Segmentation). The results demonstrate that the algorithm proposed is both accurate and efficient. The data and performance measures such as completeness and correctness are calculated together with other parameters which are Peak Signal to Noise ratio, Normalized Cross Correlation, Structural Content and a statistical analysis of the comparison is presented.
Highlights
Road extraction from satellite/aerial images is an area of image processing which is vastly researched to provide accurate and efficient experimental results
When remote sensing and its applications came into use the need of road extraction was felt, since researchers started working in the area of image processing [5]
After the era of semi-automatic road extraction came the era of automatic road detection techniques which involved learning algorithms and artificial intelligence [8]
Summary
Road extraction from satellite/aerial images is an area of image processing which is vastly researched to provide accurate and efficient experimental results. Road extraction was done manually wherein a person was appointed to highlight and draw roads and its features manually but as the process was very cumbersome the need for automation was felt came semi-automatic and automatic techniques. After the era of semi-automatic road extraction came the era of automatic road detection techniques which involved learning algorithms and artificial intelligence [8]. In automated road detection neural networks were used to give effective and efficient results with least human interference These developments in the field of road extraction have increased the efficiency and accuracy of the targeted output but because of its vast application there can still be huge developments and improvements[9]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
