Dynamically Tunable Multidimensional Feature Focusing and Diffusion Networks for Water Surface Debris Detection

With the increasing level of industrialization, water surface debris detection has emerged as a significant research topic. However, challenges such as complex backgrounds, overlapping targets, and reflections on water surfaces often hinder effective waste detection, resulting in low model accuracy...

Full description

Saved in:
Bibliographic Details
Main Authors: Chong Zhang, Jie Yue, Jianglong Fu
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11122446/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849340434532270080
author Chong Zhang
Jie Yue
Jianglong Fu
author_facet Chong Zhang
Jie Yue
Jianglong Fu
author_sort Chong Zhang
collection DOAJ
description With the increasing level of industrialization, water surface debris detection has emerged as a significant research topic. However, challenges such as complex backgrounds, overlapping targets, and reflections on water surfaces often hinder effective waste detection, resulting in low model accuracy and unreliable recognition. To address these challenges, the Water Surface Debris DEtection TRansformer (WSD-DETR) was proposed. First, a Self-moving Point Convolutional Gating Network (SPCG-Net) was designed, which integrated an adaptive point-moving mechanism with a convolutional gating linear unit to enhance the flexibility and accuracy of feature extraction. Second, an Attention-based Re-parameterization of Intra-scale Feature Interactions (ARIFI) module was constructed to process high-level features extracted from the backbone. This module employed a single-scale transformer encoder with Re-parameterized Batch Normalization (RepBN) to improve focus on small and medium-sized targets in water surface waste detection, thereby capturing relationships between semantic concepts and conceptual entities. Furthermore, a Focal-Diffuse Feature Pyramid Network (FD-FPN) was introduced to accurately capture and integrate key feature information through focused feature fusion techniques while utilizing cross-scale diffusion analysis to efficiently transfer and enhance feature information across different scales. This approach significantly improved feature expression capability and overall model performance. Experimental results indicated that WSD-DETR achieved a precision of 88.1%, and reduced model parameters by 12.6% compared to the Real-Time DEtection TRansformer (RT-DETR), and increased mAP@50 and mAP@50:90 values by 4.4% and 5.5%, respectively. These outcomes demonstrated substantial potential for water surface debris detection.
format Article
id doaj-art-e74a5aee112949f7a6bdf33254ce6e3a
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-e74a5aee112949f7a6bdf33254ce6e3a2025-08-20T03:43:55ZengIEEEIEEE Access2169-35362025-01-011314174814176410.1109/ACCESS.2025.359772711122446Dynamically Tunable Multidimensional Feature Focusing and Diffusion Networks for Water Surface Debris DetectionChong Zhang0https://orcid.org/0009-0001-3951-5365Jie Yue1Jianglong Fu2https://orcid.org/0009-0007-6902-3699School of Information Engineering, Hebei University of Architecture, Zhangjiakou, ChinaSchool of Information Engineering, Hebei University of Architecture, Zhangjiakou, ChinaSchool of Information Engineering, Hebei University of Architecture, Zhangjiakou, ChinaWith the increasing level of industrialization, water surface debris detection has emerged as a significant research topic. However, challenges such as complex backgrounds, overlapping targets, and reflections on water surfaces often hinder effective waste detection, resulting in low model accuracy and unreliable recognition. To address these challenges, the Water Surface Debris DEtection TRansformer (WSD-DETR) was proposed. First, a Self-moving Point Convolutional Gating Network (SPCG-Net) was designed, which integrated an adaptive point-moving mechanism with a convolutional gating linear unit to enhance the flexibility and accuracy of feature extraction. Second, an Attention-based Re-parameterization of Intra-scale Feature Interactions (ARIFI) module was constructed to process high-level features extracted from the backbone. This module employed a single-scale transformer encoder with Re-parameterized Batch Normalization (RepBN) to improve focus on small and medium-sized targets in water surface waste detection, thereby capturing relationships between semantic concepts and conceptual entities. Furthermore, a Focal-Diffuse Feature Pyramid Network (FD-FPN) was introduced to accurately capture and integrate key feature information through focused feature fusion techniques while utilizing cross-scale diffusion analysis to efficiently transfer and enhance feature information across different scales. This approach significantly improved feature expression capability and overall model performance. Experimental results indicated that WSD-DETR achieved a precision of 88.1%, and reduced model parameters by 12.6% compared to the Real-Time DEtection TRansformer (RT-DETR), and increased mAP@50 and mAP@50:90 values by 4.4% and 5.5%, respectively. These outcomes demonstrated substantial potential for water surface debris detection.https://ieeexplore.ieee.org/document/11122446/Dynamic tunable networksfeature focusing and diffusionneural networksobject detectionprogressive learning
spellingShingle Chong Zhang
Jie Yue
Jianglong Fu
Dynamically Tunable Multidimensional Feature Focusing and Diffusion Networks for Water Surface Debris Detection
IEEE Access
Dynamic tunable networks
feature focusing and diffusion
neural networks
object detection
progressive learning
title Dynamically Tunable Multidimensional Feature Focusing and Diffusion Networks for Water Surface Debris Detection
title_full Dynamically Tunable Multidimensional Feature Focusing and Diffusion Networks for Water Surface Debris Detection
title_fullStr Dynamically Tunable Multidimensional Feature Focusing and Diffusion Networks for Water Surface Debris Detection
title_full_unstemmed Dynamically Tunable Multidimensional Feature Focusing and Diffusion Networks for Water Surface Debris Detection
title_short Dynamically Tunable Multidimensional Feature Focusing and Diffusion Networks for Water Surface Debris Detection
title_sort dynamically tunable multidimensional feature focusing and diffusion networks for water surface debris detection
topic Dynamic tunable networks
feature focusing and diffusion
neural networks
object detection
progressive learning
url https://ieeexplore.ieee.org/document/11122446/
work_keys_str_mv AT chongzhang dynamicallytunablemultidimensionalfeaturefocusinganddiffusionnetworksforwatersurfacedebrisdetection
AT jieyue dynamicallytunablemultidimensionalfeaturefocusinganddiffusionnetworksforwatersurfacedebrisdetection
AT jianglongfu dynamicallytunablemultidimensionalfeaturefocusinganddiffusionnetworksforwatersurfacedebrisdetection