Skip to content
Open access

An underwater object detection method integrating multi-dimensional attention and task-decoupling mechanism

Aug 2026 · Journal of Real-Time Image Processing · Vol 23 · 0 citations · 59 references

TL;DR

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.

Abstract

Underwater object detection is of significant practical importance for marine resource exploration, underwater robotic navigation, and marine ecological monitoring. However, underwater images are often severely degraded by light attenuation and scattering, suspended particulates, and complex background interference. These factors lead to low contrast, strong color distortion, and blurred object boundaries, which collectively pose substantial challenges to reliable object detection. To address these issues, this paper proposes an object detection framework specifically designed for underwater environments. First, we develop a dynamic image feature fusion backbone module, termed DyC2F (dynamic lightweight convolution to fusion). By embedding dynamic convolution into a dual-path architecture, DyC2F enhances the modeling of local textures and weak boundary features while maintaining low computational complexity. Second, a three-dimensional attention fusion mechanism, referred to as TDAF (three-dimensional attention fusion), is introduced to adaptively enhance multi-scale underwater features across channel, scale, and spatial dimensions, thereby improving the detectability of low-contrast small objects. Finally, the detection head is further optimized by incorporating a dynamic activation function, a task-decoupled alignment module, and a quality focal loss, which effectively mitigates feature conflicts between classification and localization in complex underwater backgrounds and improves prediction stability. Experimental results on representative underwater datasets demonstrate that the proposed method consistently outperforms mainstream approaches in terms of detection accuracy, robustness, and small-object recognition. Moreover, the proposed framework achieves a processing speed of 188.7 frames per second (fps), satisfying real-time detection requirements in complex underwater scenarios.

Read PDF

Similar papers

Open access Sep 2026

Underwater tiny object detection network based on multi-scale attention and adaptive feature fusion

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.

Xing-Yu Wang, Yu-Han Lin, Quan J. Wang et al. · 0 citations
Aug 2026

UW-D-FINE: degradation-aware real-time underwater object detection

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...

Han-Jie Ma, Tingting Wan, Hui-Jun Dong et al. · 0 citations
Open access Aug 2026

HFQI-YOLO: a lightweight and efficient underwater object detection algorithm

Underwater object detection plays a crucial role in fisheries resource assessment and ecological environment protection. Current underwater object detection models are characterized by large parameter sizes and high computational costs, which hinder the simultaneous achievement of lightweight deployment and high detect...

Xue-Feng Zhao, Yong-Jie Guo, Zhao-Man Zhong et al. · 0 citations
Open access Sep 2026

Underwater target detection based on target feature enhancement and semantic-position path aggregation

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.

P. Parashar, A. Kushwah · 0 citations
Conference Aug 2026

Shape-Adaptive Multi-Scale Feature Enhancement Network for Object Detection in Underwater Vehicle

Marine organisms exhibit substantial variation in appearance and shape across diverse underwater environments and are often characterized by considerably smaller object scales than their terrestrial counterparts. These properties pose significant challenges to generic object detectors, particularly in capturing shape-v...

Hao Zhou, Xin-Yu Zhao · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.