Depth-Assisted Network for Indiscernible Marine Object Counting with Adaptive Motion-Differentiated Feature Encoding

Indiscernible marine object counting refers to the counting of marine objects that are visually blended with their surrounding environment. This task encounters critical challenges, including limited visibility in underwater scenes, mutual occlusion and overlap among objects, and the dynamic similarity in appearance, color, and texture between the background and foreground. To address the scarcity of video-based indiscernible object counting datasets, we have established a new dataset comprising 50 videos, from which approximately 800 frames have been extracted and annotated with around 40, 800 point-wise object labels. This dataset represents real underwater environments where indiscernible marine objects are intricately integrated with their surroundings, thereby comprehensively illustrating the aforementioned challenges in marine object counting. To address these challenges, we propose a depth-assisted network with adaptive motion-differentiated feature encoding. The network consists of a backbone encoding module and three branches: a depth-assisting branch, a density estimation branch, and a motion weight generation branch. Depth-aware features extracted by the depth-assisting branch are enhanced via a depth-enhanced encoder to improve object representation. Meanwhile, weights from the motion weight generation branch refine multi-scale perception features in the adaptive flow estimation module. Experiments demonstrate that our method not only achieves state-of-the-art performance on the proposed dataset but also yields competitive results on three video-based crowd counting datasets. The pre-trained model, code, and dataset are publicly available at https://github.com/OUCVisionGroup/VIMOC-Net.