Extraction Method of Scallop Area in Gravel Seabed Images for Fishery Investigation

Koichiro ENOMOTO  Masashi TODA  Yasuhiro KUWAHARA  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E93-D   No.7   pp.1754-1760
Publication Date: 2010/07/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.E93.D.1754
Print ISSN: 0916-8532
Type of Manuscript: Special Section PAPER (Special Section on Machine Vision and its Applications)
Category: 
Keyword: 
scallop,  fishery resource investigation,  automatic counting,  image processing,  

Full Text: PDF(1.2MB)
>>Buy this Article


Summary: 
The quantity and state of fishery resources must be known so that they can be sustained. The fish culture industry is also planning to investigate resources. The results of investigations are used to estimate the catch size, times fish are caught, and future stocks. We have developed a method for extracting scallop areas from gravel seabed images to assess fish resources and also developed an automatic system that measures their quantities, sizes, and states. Japanese scallop farms for fisheries are found on gravel and sand seabeds. The seabed images are used for fishery investigations, which are absolutely necessary to visually estimate, and help us avoid using the acoustic survey. However, there is no automatic technology to measure the quantities, sizes, and states of resources, and so the current investigation technique is the manual measurement by experts. There are varied problems in automating technique. The photography environments have a high degree of noise, including large differences in lighting. Gravel, sand, clay, and debris are also included in the images. In the gravel field, we can see scallop features, such as colors, striped patterns, and fan-like shapes. This paper describes the features of our image extracting method, presents the results, and evaluates its effectiveness.