Abstract
To accurately achieve side scan sonar (SSS) image target detection, a novel target detection algorithm based on a neutrosophic set (NS) and diffusion maps (DMs) is proposed in this paper. Firstly, the neutrosophic subset images were obtained by transforming the input SSS image into the NS domain. Secondly, the shadowed areas of the SSS image were detected using the single gray value threshold method before the diffusion map was calculated. Lastly, based on the diffusion map, the target areas were detected using the improved target scoring equation defined by the diffusion distance and texture feature. The experiments using SSS images of single clear and unclear targets, with or without shadowed areas, showed that the algorithm accurately detects targets. Experiments using SSS images of multiple targets, with or without shadowed areas, showed that no false or missing detections occurred. The target areas were also accurately detected in SSS images with complex features such as sand wave terrain. The accuracy and effectiveness of the proposed algorithm were assessed.
Highlights
Side-scan sonar (SSS) is often used in ocean engineering to obtain high-resolution seabed images, and to detect and recognize underwater targets [1,2,3,4]
Grasso et al [8] proposed a small target detection method based on local gray level information and a mathematical morphology operation, but the method only fitted those SSS images obtained by an automated underwater vehicle (AUV) platform
Mishne et al [9,10] studied an image anomaly region detection method based on a diffusion map, but the method did not account for the problems caused by the shadowed areas of a target, the complexity of the noise, or the features of the sea bottom being influenced in the SSS image
Summary
Side-scan sonar (SSS) is often used in ocean engineering to obtain high-resolution seabed images, and to detect and recognize underwater targets [1,2,3,4]. Accurate target detection from SSS images is influenced by (1) complex marine environment noise and the special towed operation mode of SSS equipment, (2) false targets such as the shadowed areas of a target and sandy slope topography, (3) the high resolution and large amount of data of SSS images, (4) difficulties in estimating parameters, and (5) the difficulty of obtaining sufficient sample data. An NS provides a powerful tool to address the uncertainty problem, being suitable for processing SSS images influenced by complex marine noise This is helpful for accurate target detection from SSS images. The diffusion distance defined in a DM provides useful metrics for anomaly (target) detection, and no prior knowledge or sample data is needed This is useful for detecting targets in SSS images in complex marine environments in which the target’s shape features are difficult to model and the indicator samples are difficult to acquire. The T subset is considered the de-noised image and its target areas are highlighted. (2) Because shadowed areas are produced in a sound wave that is blocked by the raised target, the shadowed areas of a target can be detected using the simple gray threshold method. (3) The diffusion map is calculated by the T subset in which the shadow’s position is removed, and the target area of an SSS image is detected with the improved target scoring equation defined by the diffusion distance and the fractal texture feature. (4) With the aid of a mathematical morphology operation, the center contour of the target’s area in the inputted SSS image is obtained
Sign-in/Register to view highlights & summary 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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
