Ye JianHua, Zhang YunDa, Li Pan, Guo Ze, Zeng Shoujin, Wei Tieping
Fujian Key Laboratory of Intelligent Machining Technology and Equipment, FuZhou 350118, China.
Fujian University of Technology, School of Mechanical and Automotive Engineering, FuZhou 350118, China.
Mar Pollut Bull. 2025 Sep;218:118189. doi: 10.1016/j.marpolbul.2025.118189. Epub 2025 May 21.
Detecting dense, small litter on water surfaces presents a significant challenge in the field of unmanned litter-cleaning vehicles. Dense small objects on water surfaces are easily influenced by various factors, including ripples, reflections, and changing lighting conditions. Existing detection methods often fail to effectively mine multidimensional global features and tend to overlook the impact of feature conflicts on small object detection. To overcome these challenges, we propose the Dense Small Floating Litter Detection Network (DSFLDNet), which incorporates multidimensional attention mechanisms in both the spatial and frequency domains. We have designed spatial and channel attention modules that utilize multiple sets of orthogonal frequency filters to enhance the network's sensitivity to small objects against complex water surface backgrounds. In our backbone architecture, we enhance feature extraction capabilities through parallel information extraction and channel blending techniques. A feature fusion approach that combines a feature pyramid with multidimensional attention mechanisms is implemented to mitigate conflicts between features at different levels, thereby improving overall detection accuracy. The proposed model demonstrates optimal experimental performance on both custom private datasets and publicly available data. Specifically, it achieves an accuracy of 93.1 %, a recall rate of 93.9 %, and a mean average precision of 97.3 % on the Dense Small Object Datasets, with a processing frame rate of 107 frames per second. Moreover, this model has been successfully deployed on an unmanned vessel for real-time detection, proving to be an effective tool for cleaning and recycling debris from water surfaces.
在无人垃圾清理车辆领域，检测水面上密集、细小的垃圾是一项重大挑战。水面上的密集小物体很容易受到各种因素的影响，包括涟漪、反射和不断变化的光照条件。现有的检测方法往往无法有效地挖掘多维全局特征，并且容易忽视特征冲突对小物体检测的影响。为了克服这些挑战，我们提出了密集小漂浮垃圾检测网络（DSFLDNet），该网络在空间和频率域中都融入了多维注意力机制。我们设计了空间和通道注意力模块，利用多组正交频率滤波器来增强网络在复杂水面背景下对小物体的敏感度。在我们的骨干架构中，通过并行信息提取和通道融合技术增强特征提取能力。实现了一种将特征金字塔与多维注意力机制相结合的特征融合方法，以减轻不同层次特征之间的冲突，从而提高整体检测精度。所提出的模型在自定义私有数据集和公开可用数据上均展示了最佳的实验性能。具体而言，在密集小物体数据集上，它达到了93.1%的准确率、93.9%的召回率和97.3%的平均精度，处理帧率为每秒107帧。此外，该模型已成功部署在一艘无人船上进行实时检测，证明是一种从水面清理和回收垃圾的有效工具。
