Related references
Note: Only part of the references are listed.
Article
Chemistry, Analytical
Yipu Li et al.
Summary: In this paper, a multi-scale collaborative perception network YOLOv5s-FP was proposed for precise pear detection and recognition. The network achieved higher average precision compared to other typical object detection networks, with lower detection time and computational cost. It also exhibited stronger robustness to occlusion and illumination changes, detecting pears of different sizes in highly dense, overlapping environments and non-normal illumination areas. Therefore, the proposed YOLOv5s-FP network is practical for real-time and accurate detection of in-field pears, and can contribute to monitoring pear growth status and implementing automated harvesting in unmanned orchards.
Article
Chemistry, Multidisciplinary
Xinyi Liu et al.
Summary: Both transformer and one-stage detectors have not widely used effective domain adaptive techniques. In this paper, we propose a novel improved YOLO model called CAST-YOLO, which implements cross-domain object detection through knowledge distillation. Extensive experiments show that our method outperforms existing methods in foggy weather adaptive detection, significantly improving the detection results.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Information Systems
Changqing Wang et al.
Summary: A novel mask detection algorithm based on the YOLO-GBC network is proposed to address the problems of inaccurate recognition and high missed detection rate in actual scenes. The algorithm integrates global attention mechanism, cross-layer cascade method, and content-aware reassembly of features to improve key information extraction and model accuracy. Experimental results show that the algorithm achieves an average accuracy of 91.2% in the mask detection dataset, 2.3% higher than the baseline YOLOv5, with a detection speed of 64FPS. The accuracy and recall have also been improved, enhancing the task of correctly wearing masks.
Article
Chemistry, Analytical
Alessandro Betti et al.
Summary: In this work, a simple, fast, and efficient network called YOLO-S is proposed for small target detection task. It utilizes a small feature extractor and skip connection, along with a reshape-passthrough layer, to promote feature reuse and combine low-level positional information with high-level information. The performance of YOLO-S is evaluated on AIRES and VEDAI datasets, and it outperforms four baselines in terms of accuracy. The experiments demonstrate that transitional learning on a combined dataset can enhance overall accuracy. YOLO-S is faster than YOLOv3 and only slightly slower than Tiny-YOLOv3, while achieving higher accuracy on VEDAI dataset. It is also suitable for search and rescue operations according to simulations on SARD dataset. Additionally, YOLO-S has a smaller model size and lower computational complexity, making it deployable for low-power industrial applications.
Article
Engineering, Electrical & Electronic
Fang Chen et al.
Summary: This work aims to develop an effective method for marine oil spill segmentation in SAR images by investigating the distribution representation of SAR images. The proposed method utilizes the probability distribution representation of oil spill SAR images to guide the segmentation process. Experimental evaluations demonstrate the effectiveness of the proposed method for different types of marine oil spill SAR image segmentation.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2022)
Article
Chemistry, Multidisciplinary
Pawel Tysiac et al.
Summary: In recent years, there has been an increasing use of satellite sensors for detecting and tracking oil spills. Satellite images are highly valuable for oil spill analysis, allowing for identification of the source of leakage and assessment of potential damage. However, the methodological approach to specific leakage cases is still unclear. This study focuses on remote sensing analysis of environmental changes through the development of oil spill detection processing methods, including long-term analysis of surface water changes.
APPLIED SCIENCES-BASEL
(2022)
Article
Chemistry, Analytical
Xianli Lang et al.
Summary: This paper proposes an enhanced lightweight YOLOv5 algorithm for the identification of magnetic ring surface defects. By adding the YOLOv5 neck network, applying the Mosaic data enhancement technique, and inserting the SE attention module in the network, the performance and robustness of the algorithm are improved.
Article
Green & Sustainable Science & Technology
Haohao Zou et al.
Summary: In this study, a traffic sign detection algorithm YOLO-FAM based on YOLOv5 is proposed to recognize small-scale and complex traffic signs in the driving environment. By using a lightweight network and introducing multi-scale information, the detection accuracy is improved, and it is effectively applied to traffic sign recognition in complex scenes, contributing to traffic planning and avoiding traffic congestion.
Article
Engineering, Marine
Rong Chen et al.
Summary: Marine oil spills pose a significant threat to marine ecological safety, and quickly identifying oil films is crucial for emergency response. This study proposes a method using machine learning techniques to extract marine oil spills based on marine radar images. The results show high accuracy in oil spill extraction with minimal false positives.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2022)
Article
Environmental Sciences
Bo Li et al.
Summary: This paper proposes a marine oil spill detection scheme based on X-band shipborne radar image and machine learning, which can monitor oil spills in the ocean rapidly and effectively, providing data support for emergency response.
Article
Computer Science, Artificial Intelligence
Rong Chen et al.
Summary: This study presents a scientific method for oil film extraction using X-band radar images. The proposed technology is more intelligent and can provide technical support for future marine oil spill emergency response.
PEERJ COMPUTER SCIENCE
(2022)
Article
Engineering, Marine
Jin Xu et al.
Summary: Oil spill accidents have caused serious harm to the marine environment. This paper proposes a method for automatically detecting oil spills in shipborne radar images using LBP texture feature and K-means algorithm. This method can provide a guarantee for real-time monitoring of oil spill accidents.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2021)
Article
Computer Science, Artificial Intelligence
Jin Xu et al.
PEERJ COMPUTER SCIENCE
(2020)
Article
Computer Science, Information Systems
Bingxin Liu et al.
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2019)
Article
Environmental Sciences
Jin Xu et al.
ENVIRONMENTAL FORENSICS
(2019)
Article
Environmental Sciences
Jin Xu et al.
Article
Computer Science, Information Systems
Dongmei Song et al.
Article
Geochemistry & Geophysics
Tao Chen et al.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2017)
Article
Engineering, Ocean
Yebao Wang et al.
MARINE GEORESOURCES & GEOTECHNOLOGY
(2017)
Article
Oceanography
Fangjie Yu et al.
Article
Chemistry, Analytical
Peng Liu et al.
Article
Environmental Sciences
Yongfeng Cao et al.
Article
Environmental Sciences
Linlin Xu et al.
REMOTE SENSING OF ENVIRONMENT
(2014)
Article
Engineering, Electrical & Electronic
Huihui Song et al.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2013)
Article
Computer Science, Artificial Intelligence
J Sauvola et al.
PATTERN RECOGNITION
(2000)
