Underwater Multi-object Segmentation Technology Based on Spectral Clustering with Multi-feature Weighting

被引：0
|
作者：
Liu G. [1 ]
Cao Y. [1 ]
Zeng Z. [1 ]
Zhao E. [2 ]
Xing C. [3 ]
机构：
[1] School of Engineering, Dali University, Dali
[2] College of Physics and Optoelectronic Engineering, Harbin Engineering University, Harbin
[3] School of Electrical and Information Technology, Yunnan Minzu University, Kunming
来源：
Hunan Daxue Xuebao/Journal of Hunan University Natural Sciences | 2022年 / 49卷 / 10期
基金：
中国国家自然科学基金;
关键词：
clustering; entropy method; feature selection; image segmentation; objective;
D O I：
10.16339/j.cnki.hdxbzkb.2022354
中图分类号：
学科分类号：
摘要：
Sonar image is seriously polluted by noise, which leads to the problem of low precision in underwater multi-target segmentation. Therefore，this paper proposes an underwater multi-object segmentation technique based on self-adjusting spectrum clustering，combined with the entropy weight method. The technology firstly clusters through self-tuning spectral clustering of sonar image pixel clustering processing, so that the image is divided into multiple independent areas. According to the complementarity and redundancy of multiple features, the information entropy, brightness, contrast and narrow length of each region are calculated. The entropy weight method is used to weight multiple features and select the optimal target region. Then，the optimal target region is matched with all regions by multi-feature similarity. Finally, all target regions are segmented automatically by the adaptive threshold iterative method according to the matching results of similarity. Experimental results show that there is no over-segmented of noise interference regions, and target regions segmented have higher accuracy, which verifies the effectiveness of the proposed method. © 2022 Hunan University. All rights reserved.
引用
下载
收藏
页码：51 / 60
页数：9
相关论文
共 16 条
  • [1] DIAMANT R., Target detection using features for sonar images［J］, IET Radar，Sonar & Navigation, 14, 12, pp. 1940-1949, (2020)
  • [2] Object detection in sonar images［J］, Electronics, 9, 7, (2020)
  • [3] ZHAO J H, ZHANG H M, Automatic detection and segmentation on gas plumes from multibeam water column images［J］, Remote Sensing, 12, 18, (2020)
  • [4] LIU G Y，, BIAN H Y，, SHI H．, Sonar image segmentation based on spectral matting using morphological operations［J］, Journal of Jilin University（Engineering and Technology Edition）, 42, 1, pp. 228-233, (2012)
  • [5] SHENG Y X, LIU J．, Side-scan sonar image segmentation algorithm based on super-pixels clustering［J］, Computer Engineering, 44, 6, pp. 219-225, (2018)
  • [6] WANG T, ZHANG J B．, Automatic extracting target contour of side-scan sonar images by uniting K-means clustering with mathematical morphology［J］, Marine Sciences, 43, 8, pp. 80-85, (2019)
  • [7] WEN G Q．, Robust self-tuning spectral clustering［J］, Neuro-computing, 391, pp. 243-248, (2020)
  • [8] PERONA P., Self-tuning spectral clustering［J］, Advances in Neural Information Processing Systems, 17, pp. 1601-1608, (2005)
  • [9] BHATTACHARYYA A., On a measure of divergence between two multinomial populations［J］, Sankhya, 10, pp. 401-406, (1946)
  • [10] DU Y K, GONG L X，, LI Q, Earthquake induced building damage assessment on SAR multi-texture feature fusion［J］, Remote Sensing Technology and Application, 36, 4, pp. 865-872, (2021)
12