Résumé:
Fish tracking is an important topic in computer vision. The growth of high-powered computers, the evolution of high-quality video cameras with low cost and the growing need for automated video analysis have caused more interest in the development of object tracking algorithms. In the sea things are completely different, the spread of light and sound are not uniform. Therefore, visibility becomes increasingly di cult due to the physical properties of the water. Two devices can observe underwater: camera and sonar. Each of these sensors has certain advantages and limitations. Merging features from both sensors can offer new information that cannot be provided before. In this paper, we monitor fish species to ensure their traceability by combining optical and acoustical characteristics. This process can be extended to many areas, as well as, fish recognition and monitoring. Experimental results on a suite of …
