Video Scene Detection of Burst Swimming by Fry of Farmed-raised Bluefin Tuna

As a method for supporting aquaculture for bluefin tuna, this paper presents a video scene detection when a burst swimming is provoked by fry of farmed-raised bluefin tuna in land-based tanks due to environmental stimuli. From the fact the fry often die crashing to the tank’s wall and between the fry because of the burst swimming, this automated monitoring could use for analyzing environmental stimuli around the tanks when the burst swimming occurs and result in decrease of the death number of the fry. In the proposed method, the fry which swim in a land-based tank are monitored by a video camera and the video scenes at the burst swimming are detected by discriminant analysis with a feature value which represents fry’s acceleration using sequential frames of the moving image. Preparing the moving images which include scenes of the burst swimming by the fry, performances of the proposed method were examined. From experimental results, recall ratio of the scene detection has shown more than 57% in linear discriminant analysis and more than 98% in discriminant analysis by Mahalanobis distance.