DENS-YOLOv6: a small object detection model for garbage detection on water surface

Li, Ning; Wang, Mingliang; Yang, Gaochao; Li, Bo; Yuan, Baohua; Xu, Shoukun

doi:10.1007/s11042-023-17679-7

Cited by 4 publications

(3 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Within the domain of water surface object detection, contemporary research has been predominantly concentrated on the refinement of detection algorithms for small targets and the engineering of lightweight model architectures. Li et al [42] introduced the DENS-YOLOv6 model, tailored for the detection of aquatic debris, which incorporates an adaptive noise suppression module to curtail the disruptive effects of noise on the detection of diminutive objects at the water's surface. Zhang et al [13] leveraged reparameterization techniques for feature extraction and propose a spatial to depth convolution strategy to enhance the detection of small targets on water surfaces.…”

Section: Water Surface Object Detectionmentioning

confidence: 99%

Enhanced Water Surface Object Detection with Dynamic Task-Aligned Sample Assignment and Attention Mechanisms

Zhao,

Qiu,

Chen

2024

Sensors

View full text Add to dashboard Cite

The detection of objects on water surfaces is a pivotal technology for the perceptual systems of unmanned surface vehicles (USVs). This paper proposes a novel real-time target detection system designed to address the challenges posed by indistinct bottom boundaries and foggy imagery. Our method enhances the YOLOv8s model by incorporating the convolutional block attention module (CBAM) and a self-attention mechanism, examining their impact at various integration points. A dynamic sample assignment strategy was introduced to enhance the precision of our model and accelerate its convergence. To address the challenge of delineating bottom boundaries with clarity, our model employs a two-strategy approach: a threshold filter and a feedforward neural network (FFN) that provides targeted guidance for refining these boundaries. Our model demonstrated exceptional performance, achieving a mean average precision (mAP) of 47.1% on the water surface object dataset, which represents a 1.7% increase over the baseline YOLOv8 model. The dynamic sample assignment strategy contributes a 1.0% improvement on average precision at the intersection over union (IoU) threshold of 0.5 (AP0.5), while the FFN strategy fine-tunes the bottom boundaries and achieves an additional 0.8% improvement in average precision at IoU threshold of 0.75 (AP0.75). Furthermore, ablation studies have validated the versatility of our approach, confirming its potential for integration into various detection frameworks.

show abstract

Section: Water Surface Object Detectionmentioning

confidence: 99%

Enhanced Water Surface Object Detection with Dynamic Task-Aligned Sample Assignment and Attention Mechanisms

Zhao,

Qiu,

Chen

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…C(x, y) = A(x, y) 2 + B(x, y) 2 + D 45 (x, y) 2 + D 135 (x, y) 2 (13) where D 45 (x, y) and D 45 (x, y) stand for the two newly added gradient components.…”

Section: Calculation Of Gradient Magnitude and Gradient Directionmentioning

confidence: 99%

“…In the field of water-floating garbage detection and management, many advanced universal object detection algorithms, such as YOLOv7, have achieved significant success [ 11 , 12 ]. However, compared to the object detection methods of other fields, the identification process of water-floating garbage faces the following problems: (1) from the perspective of environmental protection, water-floating garbage is located against a diverse and complex background, which makes it difficult to distinguish water-floating garbage; (2) from the perspective of object detection, small-target water-floating garbage contains limited features, and their appearance changes significantly during the floating process, resulting in the unsatisfactory detection performance of deep learning algorithms for water-floating garbage [ 13 ]. In addition, there is a lack of publicly available datasets in this field, which leads to a lack of sufficient data when training deep learning models, making it difficult to fully validate the algorithm and extend its generalization ability.…”

Section: Introductionmentioning

confidence: 99%

APM-YOLOv7 for Small-Target Water-Floating Garbage Detection Based on Multi-Scale Feature Adaptive Weighted Fusion

Jiang,

Wu,

et al. 2023

Sensors

View full text Add to dashboard Cite

As affected by limited information and the complex background, the accuracy of small-target water-floating garbage detection is low. To increase the detection accuracy, in this research, a small-target detection method based on APM-YOLOv7 (the improved YOLOv7 with ACanny PConv-ELAN and MGA attention) is proposed. Firstly, the adaptive algorithm ACanny (adaptive Canny) for river channel outline extraction is proposed to extract the river channel information from the complex background, mitigating interference of the complex background and more accurately extracting the features of small-target water-floating garbage. Secondly, the lightweight partial convolution (PConv) is introduced, and the partial convolution-efficient layer aggregation network module (PConv-ELAN) is designed in the YOLOv7 network to improve the feature extraction capability of the model from morphologically variable water-floating garbage. Finally, after analyzing the limitations of the YOLOv7 network in small-target detection, a multi-scale gated attention for adaptive weight allocation (MGA) is put forward, which highlights features of small-target garbage and decreases missed detection probability. The experimental results showed that compared with the benchmark YOLOv7, the detection accuracy in the form of the mean Average Precision (mAP) of APM-YOLOv7 was improved by 7.02%, that of mmAP (mAP0.5:0.95) was improved by 3.91%, and Recall was improved by 11.82%, all of which meet the requirements of high-precision and real-time water-floating garbage detection and provide reliable reference for the intelligent management of water-floating garbage.

show abstract

Yolo5-Based UAV Surveillance for Tiny Object Detection on Airport Runways

Sri Hari,

Ambalam,

Ruban Kumar

et al. 2023

2023 International Conference on Data Science, Agents &Amp; Artificial Intelligence (ICDSAAI)

View full text Add to dashboard Cite

DENS-YOLOv6: a small object detection model for garbage detection on water surface

Cited by 4 publications

References 42 publications

Enhanced Water Surface Object Detection with Dynamic Task-Aligned Sample Assignment and Attention Mechanisms

Enhanced Water Surface Object Detection with Dynamic Task-Aligned Sample Assignment and Attention Mechanisms

APM-YOLOv7 for Small-Target Water-Floating Garbage Detection Based on Multi-Scale Feature Adaptive Weighted Fusion

Yolo5-Based UAV Surveillance for Tiny Object Detection on Airport Runways

Contact Info

Product

Resources

About