TL;DR
A novel model integrating multi-scale attention and adaptive feature fusion to enhance detection accuracy and robustly handles the inherent complexities of underwater environments is proposed.
Experimental results demonstrate that the proposed Bidirectional weighted Concat with Efficient multi-scale Attention You Only Look Once (BCEA-YOLO) method outperforms competing methods for underwater object detection, and edge deployment tests on the NVIDIA Jetson platform validate its real-time inference efficiency.
Results support the effectiveness of the proposed framework for mixed-scale underwater object detection, including small-scale objects, and compare with the YOLOv11 baseline.
A novel underwater target detection framework that integrates feature enhancement with semantic-spatial guided fusion, built upon the RT-DETR architecture, that significantly reduces false positives and missed detections while maintaining real-time performance is proposed.
A dynamic image feature fusion backbone module, termed DyC2F (dynamic lightweight convolution to fusion), is developed, which enhances the modeling of local textures and weak boundary features while maintaining low computational complexity.
HA-DETR performs differentiated processing and adaptive enhancement on features across semantic levels to improve representational capacity and demonstrate HA-DETR’s superiority on DUO and UTDAC2020 datasets.
The proposed UW-D-FINE, an enhanced real-time detector addressing underwater object detection challenges through three key innovations, enhances the backbone by integrating parallel multi-scale convolutional branches with omnidirectional depthwise convolutions, enabling more effective extraction of discriminative featu...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
