State-of-the-art multiple-object tracking methods are frequently applied to people or vehicle tracking, but rarely involve underwater-object tracking. Compared with the processing in non-underwater photos or videos, underwater fish tracking is challenging due to variations in light conditions, water turbidity levels, shape deformations, and the similar appearances of fish. This article proposes a robust underwater fish-school tracking algorithm (FSTA). The FSTA is based on the tracking-by-detection paradigm. To solve the problem of low recognition accuracy in an underwater environment, we add an amendment detection module that uses prior knowledge to modify the detection result. Second, we introduce an underwater data association algorithm for aquatic non-rigid organisms that recombines representation and location information to refine the data matching process and improve the tracking results. The Resnet50-IBN network is used as a re-identification network to track fish. We introduce a triplet loss function based on a centroid to train the feature extraction network. The multiple-object tracking accuracy (MOTA) of the FSTA is 79.1% on the underwater dataset, which shows that it can achieve state-of-the-art performance in a complex real-world marine environment.

Computer vision in marine ranching enables real-time monitoring of underwater resources. Detecting fish presents challenges due to varying water turbidity and lighting, affecting color consistency. We propose a Foreground Region Convolutional Neural Network (FR-CNN) that combines unsupervised and supervised methods. It introduces an adaptive multiscale regression Gaussian background model to distinguish fish from noise at different scales. Probability density functions integrate spatiotemporal information for object detection, addressing illumination and water quality shifts. FR-CNN achieves 95% mAP with IoU of 0.5, reducing errors from open-source datasets. It updates anchor boxes automatically on local datasets, enhancing object detection accuracy in long-term monitoring. The results analyze fish species behaviors in relation to environmental conditions, validating the method’s practicality.