2025年2月25日 · Abstract: Underwater object detection (UOD) plays an important role in the exploitation of marine ecological resources. Different from terrestrial images, the complex underwater environment leads to significant degradation in underwater images, which brings great difficulty in accurate object detection.

2023年1月14日 · To alleviate these issues, we first present a new real-world UOD dataset called RUOD that places UOD in the context of general scene understanding. The dataset contains 14,000 high-resolution images, 74,903 labeled objects, and 10 common aquatic categories.

2024年5月1日 · Firstly, a real-time UIE method is employed to generate enhanced images, which can improve the visibility of objects in low-contrast areas. Secondly, a cross-domain feature interaction module is introduced to facilitate the interaction and mine complementary information between raw and enhanced image features.

It contains over 1500 images with pixel annotations for eight object categories: fish (vertebrates), reefs (invertebrates), aquatic plants, wrecks/ruins, human divers, robots, and sea-floor. The images are rigorously collected during oceanic explorations and human-robot collaborative experiments, and annotated by human participants. Download

2023年6月25日 · Firstly, a real-time UIE method is employed to generate enhanced images, which can improve the visibility of objects in low-contrast areas. Secondly, a cross-domain feature interaction module is introduced to facilitate the interaction and mine complementary information between raw and enhanced image features.

2024年3月28日 · To address these challenges, we introduce EnYOLO, an integrated real-time framework designed for simultaneous UIE and UOD with domain-adaptation capability. Specifically, both the UIE and UOD task heads share the same network backbone and utilize a lightweight design.

2023年9月1日 · As a straightforward solution, degraded underwater images can be pre-processed by underwater image enhancement (UIE) and super-resolution (SR) technologies, so that the UOD-related schemes can better capture the characteristics of diverse underwater objects, effectively improving the detection precision.

To tackle these issues, we resort to developing a domain-adaptive one-shot landmark detection framework for handling multi-domain medical images, named Universal One-shot Detection (UOD). UOD consists of two stages and two corresponding universal models which are designed as combinations of domain-specific modules and domain-shared modules.

2024年6月7日 · This paper proposes a dual-branch joint learning network (DJL-Net) for UOD tasks, which adopts a well-designed dual-branch structure to achieve joint learning of image processing and object detection tasks.

2023年10月1日 · Overview of UOD framework. In stage I, two universal models are learned via contrastive learning for matching similar patches from original image and augmented one-shot sample image and generating pseudo labels. In stage II, DATR is designed to better capture global context information among all domains for detecting more accurate landmarks.