SAR River Image Segmentation by Active Contour Model Inspired by Exponential Cross Entropy
- PDF / 2,415,855 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 111 Downloads / 181 Views
RESEARCH ARTICLE
SAR River Image Segmentation by Active Contour Model Inspired by Exponential Cross Entropy Bin Han1 • Yiquan Wu1,2,3,4 Received: 2 March 2018 / Accepted: 9 November 2018 / Published online: 5 December 2018 Ó Indian Society of Remote Sensing 2018
Abstract Utilizing the existing active contour models to achieve accurate segmentation of SAR river images is ineffective. To address this difficult, a novel active contour model inspired by exponential cross entropy is proposed. The external energy constraint term of the proposed model is defined inspired by exponential cross entropy. Then, the means of the pixel grayscale values inside and outside the curve are utilized to modify the external energy constraint term, which can improve segmentation performance. Moreover, the Dirac function is replaced by the edge magnitude function to accelerate the curve evolution, which can improve segmentation efficiency. The extensive experiments are performed on a large number of SAR river images and the results demonstrate that the proposed model outperforms the existing active contour models in terms of both segmentation performance and segmentation efficiency. Keywords Image segmentation SAR river image Active contour model Exponential cross entropy Edge magnitude function
Introduction The extraction and identification of the river information have practical significance in many areas of the water resource investigation, the water conservation evaluation, the flood disaster prevention, the topographic map matching, the waterway planning, etc. The traditional field of surveying and mapping have some obvious drawbacks, & Bin Han [email protected] Yiquan Wu [email protected] 1
School of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China
2
Key Laboratory of Yellow River Sediment of Ministry of Water Resources, Yellow River Institute of Hydraulic Research, Yellow Water Resources Commission, Zhengzhou, China
3
Engineering Technology Research Center of Wuhan Intelligent Basin, Changjiang River Scientific Research Institute, Changjian Water Resources Commission, Wuhan, China
4
State Key Laboratory of Urban Water Resources and Environment, Harbin Institute of Technology, Harbin, China
which needs long measurement period and a lot of manpower and material resources and does not have the realtime performance. Recently, with the development of satellite remote sensing technology, it has been applied to the earth observation. Especially, the synthetic aperture radar (SAR) technology which has many advantages such as the short imaging period, the wide observation range, the strong real-time property, and the all-weather and all-day capacities has become one of the main methods to extract and identify the river information. The image segmentation is the key step of the extraction and identification of the river information utilizing the SAR river images; thus, the study on the SAR river image segmentation is of great necessity. Since Kass et al. (1988) proposed
Data Loading...
