2015 International Symposium of Computer Application and Information Technology (IsCait 2015)

279 / 1971-01-01 00:00:00

Fish Detection And Ghost Suppression Based On Didson

The dual-frequency identification sonar (DIDSON) can obtain clear video data from murky and darkness under water environment. Fish detection is the prerequisite for the fish tracking and recognition. First, the noise characteristics of image and fish body statistical characteristics of brightness were obtained by experimental analysis. Therefore, a novel fish detection method was proposed, and then, a ghost suppression method was used to improve the detection accuracy. Finally, the isolation noise was removed by a morphological filter. Experimental results indicate that the proposed detection method is better than the classical methods in aspect of fish body contour sharpness and fish size accuracy , and can satisfy the application requirements for real-time tracking and recognition.