Liqin Fu, Yiru Wang, Zhebin Zhang, Rui Nian, T. Yan, A. Lendasse
{"title":"一种基于去阴影的水下目标点特征检测显著性图","authors":"Liqin Fu, Yiru Wang, Zhebin Zhang, Rui Nian, T. Yan, A. Lendasse","doi":"10.23919/OCEANS.2015.7401949","DOIUrl":null,"url":null,"abstract":"The point feature detection is one of the most essential and fundamental tasks for underwater objects in ocean investigations. In this paper, a streamline AUV system that adopts the side scan sonar on board has been set up to explore our underwater visual tasks. Before attempting to detect the point features, the raw underwater sonar images must be preprocessed by shadow removal. The saliency map will be further explored with the contrast determination filter at various scales and then the point feature detection model can be completed on the basis of the saliency map. It is shown from the simulation experiments that the proposed model could achieve great performances in the point feature detection with both robustness and effectiveness.","PeriodicalId":403976,"journal":{"name":"OCEANS 2015 - MTS/IEEE Washington","volume":"11 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":"{\"title\":\"A shadow-removal based saliency map for point feature detection of underwater objects\",\"authors\":\"Liqin Fu, Yiru Wang, Zhebin Zhang, Rui Nian, T. Yan, A. Lendasse\",\"doi\":\"10.23919/OCEANS.2015.7401949\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The point feature detection is one of the most essential and fundamental tasks for underwater objects in ocean investigations. In this paper, a streamline AUV system that adopts the side scan sonar on board has been set up to explore our underwater visual tasks. Before attempting to detect the point features, the raw underwater sonar images must be preprocessed by shadow removal. The saliency map will be further explored with the contrast determination filter at various scales and then the point feature detection model can be completed on the basis of the saliency map. It is shown from the simulation experiments that the proposed model could achieve great performances in the point feature detection with both robustness and effectiveness.\",\"PeriodicalId\":403976,\"journal\":{\"name\":\"OCEANS 2015 - MTS/IEEE Washington\",\"volume\":\"11 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2015-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"5\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"OCEANS 2015 - MTS/IEEE Washington\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.23919/OCEANS.2015.7401949\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"OCEANS 2015 - MTS/IEEE Washington","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.23919/OCEANS.2015.7401949","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A shadow-removal based saliency map for point feature detection of underwater objects
The point feature detection is one of the most essential and fundamental tasks for underwater objects in ocean investigations. In this paper, a streamline AUV system that adopts the side scan sonar on board has been set up to explore our underwater visual tasks. Before attempting to detect the point features, the raw underwater sonar images must be preprocessed by shadow removal. The saliency map will be further explored with the contrast determination filter at various scales and then the point feature detection model can be completed on the basis of the saliency map. It is shown from the simulation experiments that the proposed model could achieve great performances in the point feature detection with both robustness and effectiveness.