FHA-MTT_data

The dataset was generated during the development of the FHA-MTT algorithm, which aims to enable automated health assessment of fish based on swimming behavior. It includes video recordings of crucian carp (Carassius auratus) exhibiting both healthy and diseased states, together with annotation files used for training object detection and keypoint recognition models. In addition, the dataset contains tracking results produced by different multi-object tracking algorithms. FHA-MTT integrates object and keypoint detection with trajectory-based behavioral analysis, providing an efficient and reliable framework for evaluating the health status of fish in aquaculture environments.