Automatic river target detection from remote sensing images based on image decomposition and distance regularized CV model. (August 2016)

• Record Type: Journal Article
• Authors: Yu, Song; Yiquan, Wu; Yimian, Dai
• Is Part Of: Computers & electrical engineering. Volume 54(2016)
• Page Start: 285
• Page End: 295
• Publication Date: 2016-08
• Subjects: Remote sensing images -- River target detection -- Image decomposition -- Tensor diffusion -- Distance regularized CV model; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2015.12.026
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: A new river target extraction method is proposed based on image decomposition and distance regularized CV (Chan–Vese) model. The original image is decomposed based on tensor diffusion and the river target is contained in the cartoon part. The river target is extracted from the cartoon image using distance regularized CV model. Abstract: Extracting river information from remote sensing images is of great importance in the investigation and monitoring of water resources and navigation of ships. In order to extract the river target from remote sensing images more accurately, a method based on image decomposition and distance regularized CV (Chan–Vese) model is proposed. Firstly, the remote sensing image is decomposed based on tensor diffusion. The original image is decomposed into a cartoon image and a texture image and the river is contained in the cartoon part. Secondly, the cartoon image is segmented based on the distance regularized CV model. Experimental results show that, the method proposed is more accurate in extracting the river target comparing with 6 other methods including image segmentation based on CV model, region-scalable fitting energy level set model, bias field correction level set model and some methods based on image decomposition and active contour model. Graphical abstract: