AutoFish: Dataset and Benchmark for Fine-grained Analysis of Fish
This provides a benchmark for automated fish documentation to support sustainable fisheries management, but it is incremental as it builds on existing methods like Mask2Former and MobileNetV2.
The authors introduced AutoFish, a new dataset of 1,500 images for fine-grained fish analysis, with baseline instance segmentation achieving 89.15% mAP and length estimation reaching 0.62cm MAE without occlusion.
Automated fish documentation processes are in the near future expected to play an essential role in sustainable fisheries management and for addressing challenges of overfishing. In this paper, we present a novel and publicly available dataset named AutoFish designed for fine-grained fish analysis. The dataset comprises 1,500 images of 454 specimens of visually similar fish placed in various constellations on a white conveyor belt and annotated with instance segmentation masks, IDs, and length measurements. The data was collected in a controlled environment using an RGB camera. The annotation procedure involved manual point annotations, initial segmentation masks proposed by the Segment Anything Model (SAM), and subsequent manual correction of the masks. We establish baseline instance segmentation results using two variations of the Mask2Former architecture, with the best performing model reaching an mAP of 89.15%. Additionally, we present two baseline length estimation methods, the best performing being a custom MobileNetV2-based regression model reaching an MAE of 0.62cm in images with no occlusion and 1.38cm in images with occlusion. Link to project page: https://vap.aau.dk/autofish/.