A deep convolutional network approach with attention mechanism for green sea urchin detection and localization

Green sea urchin, Strongylocentrotus droebachiensis, exerts considerable influence on marine benthic habitats in Arctic and sub-Arctic regions, including kelp forests. Additionally, the species’ gonads (roe) are a highly prized delicacy on Asian markets. To assess and monitor ecological conditions in coastal regions due to sea urchin overgrazing or to establish aquaculture of green sea urchins, computer-assisted autonomous detection might be desirable. However, the accuracy of underwater identification of green sea urchins is affected by a number of factors, including low picture quality, scattering and absorption of light, overlap or occlusion of underwater species, differences in the sizes of the species, and the presence of background objects. In this work, we present a multi-step process for the autonomous identification of green sea urchins in natural habitats using an underwater image dataset consisting of 2,400 images. The process includes augmentation, color correction and enhancement based on the state-of-the-art YOLOv7 object detector. The results of the experiments demonstrate that the proposed framework is capable of accurately recognizing green sea urchins in various underwater scenes and for varying distances between the camera and the target with a mean Average Precision (mAP) of 83.6%.