Fish catching by visual servoing and observed intelligence of the fish

This paper presents a vision related technique for a manipulator real-time visual servoing to catch fish and intelligent observation of the fish trying to escape from the net attached at the robot hand. The visual recognition method utilizes both the global and local search features of genetic algorithm (GA) and the unprocessed gray-scale image (or raw-image) in order to perform recognition of a known target object being imaged. Also, in GA process, the computation of the fitness function is based on the configuration of an object model designated as surface-strips model. The raw-image is used since it is more tolerant to contrast variations from an input image to the next one, and does not require any filtering processing time, which is useful for real-time recognition. The global GA is utilized together with the local GA in order to recognize the target shape and detect the position and orientation simultaneously, and to increase the GA's convergence speed so as to provide faster and better recognition results. Experiments to track a fish by hand-eye camera and catch it with a net attached to the hand of the manipulator were carried out. The effectiveness of the proposed technique is demonstrated.