Detecting Abnormal Fish Behavior Using Motion Trajectories In Ubiquitous Environments

Monitoring fish farms as controlling water quality and abnormal fish behaviors inside fish pond are one of the most costly and difficult task to do for fish farmers. Fish farmers normally do these tasks manually, which requires them to dedicate lots of time and money. Way for detecting fish behaviors is presented in this paper by identifying the fish and analyzing their trajectories in a difficult water environment. First of all, we used an image enhancement algorithm to color-enhance water pictures and to enhance fish detection. We then used an algorithm for object detection to identify fish. Finally, we used a classification algorithm to detect fish abnormal behavior. Our aim is making an automated system that monitors the fish farm to reduce costs and time for the fish farmers and provide them with more efficient and easy ways to perform their operations.