相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Geochemistry & Geophysics
Yuzhen Niu et al.
Summary: In this study, an efficient encoder-decoder network with estimated ship direction was proposed for ship detection in SAR images. The network achieved state-of-the-art performance by extracting multiple-level features and addressing the challenge of overlapped annotations.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Automation & Control Systems
Niki Martinel et al.
Summary: Vehicle reidentification is crucial for intelligent surveillance systems and smart transportation, but it faces challenges such as occlusions, color and illumination changes, and orientation issues. Researchers have proposed an approach to learn robust feature representations without the need for extra-labeled data and increasing computational complexity.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Computer Science, Artificial Intelligence
Haoran Wang et al.
Summary: Global average pooling (GAP) allows CNNs to localize discriminative information using only image-level labels. To address the issue of missing information due to viewpoint changes and intraclass variations, we propose a new module called Spatial Rescaling (SpaRs) layer, which helps CNNs focus on a broader area in the feature map. The SpaRs layer consistently improves performance in reidentification models and demonstrates superiority in fine-grained and general image classification benchmarks.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Automation & Control Systems
Bangyong Sun et al.
Summary: This article discusses the poor generalization issue of the metric model in person reidentification and proposes a semi-supervised consistent projection metric-learning method. Experimental results show that the proposed method achieves the best performance.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Engineering, Civil
Aihua Zheng et al.
Summary: Vehicle re-identification is crucial for large-scale intelligent monitoring in smart cities, but existing methods are mostly supervised, time-consuming, and limited in real-life scenarios. Unsupervised person re-identification methods show impressive performance through domain adaption or clustering techniques, but cannot be directly applied to vehicle re-identification due to huge appearance variations in vehicle images. To address this issue, a novel viewpoint-aware clustering algorithm is proposed for unsupervised vehicle re-identification, achieving promising performance in various scenarios according to experiments on benchmark datasets.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Computer Science, Information Systems
Yunlong Gao et al.
Summary: Ship detection in SAR images is an important task in image processing. Traditional algorithms rely on handmade features or predefined thresholds, while deep learning algorithms have shown promise. This paper proposes an improved YOLOv4 algorithm based on attention mechanism to enhance ship detection performance. Experimental results demonstrate that the proposed method achieves high accuracy and efficiency on a public SAR dataset.
Article
Engineering, Civil
Zhongxia Xiong et al.
Summary: This paper presents a vehicle Re-ID framework integrating image processing and traffic flow models, which combines visual information with the IDM car-following model to improve matching rate and identify lane changes, overtaking, or driving on a sideroad.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2021)
Article
Computer Science, Information Systems
Zhenfeng Shao et al.
Summary: This paper introduces a ReID framework with internal and external spatial-temporal constraints, named IESC-ReID, which utilizes residual spatial attention module and Laplace-based constraint to enhance performance. Results from intensive experiments consistently show performance improvement over several state-of-the-art ReID algorithms.
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
(2021)
Article
Physics, Multidisciplinary
Wentao Mao et al.
Summary: This paper proposes an online detection method of bearing early fault based on deep transfer learning, which combines a new state assessment method and a deep dual temporal domain adaptation model to improve detection accuracy and robustness in both online and offline stages. Experimental results show that the proposed method outperforms other methods in early fault detection.
Article
Computer Science, Information Systems
Hao Sheng et al.
Summary: Vehicle reidentification is an important task aiming to identify vehicles across images, but the pose barrier problem significantly influences the results. Pose robust features (PRFs) are proposed, containing pose-invariant features (PIFs) and pose discriminative features (PDFs), which together alleviate the influence of the pose barrier problem. The experiments showed that PIF and PDF are complementary and PRF performs competitively compared to state-of-the-art approaches.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Artificial Intelligence
Amir Ghahremani et al.
Summary: Maritime vessel re-identification is a computer vision task involving matching vessel identities across different camera views. This study introduces a new dataset and performs baseline analysis, comparing performances of 10 deep learning architectures to propose best practices. A novel multi-branch deep learning architecture, MVR-net, is proposed to address the challenging problem of vessel re-identification, outperforming existing networks in evaluation on the new dataset.
MACHINE VISION AND APPLICATIONS
(2021)
Review
Engineering, Marine
Dalei Qiao et al.
Summary: The primary task of marine surveillance is to construct a perfect marine situational awareness (MSA) system that serves to safeguard national maritime rights and interests and to maintain blue homeland security. Progress in maritime wireless communication, developments in artificial intelligence, and automation of marine turbines together imply that intelligent shipping is inevitable in future global shipping. This paper reviews the research of deep learning in situational awareness of the ocean surface and provides a foundation for further investigation in related fields.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2021)
Article
Environmental Sciences
Linhao Li et al.
Summary: This paper proposes a domain adaptive ship detection method that minimizes domain discrepancies through image-level and instance-level adaption, enhancing the accuracy and generalization ability of ship detection.
Article
Computer Science, Artificial Intelligence
Guangyi Chen et al.
Summary: The paper introduces an attention pyramid method for person re-identification, which imitates human visual perception by learning attention regions at multiple scales. The method outperforms state-of-the-art techniques on large-scale benchmarks with limited computational cost, and can be easily integrated into existing models.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Environmental Sciences
Yohei Koga et al.
Article
Geochemistry & Geophysics
Zhongling Huang et al.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2020)
Article
Engineering, Marine
Lei Du et al.
Proceedings Paper
Computer Science, Software Engineering
H. G. J. Groot et al.
PROCEEDINGS OF THE 15TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS, VOL 5: VISAPP
(2020)
Article
Computer Science, Information Systems
Dalei Qiao et al.
Article
Computer Science, Information Systems
Dalei Qiao et al.
Article
Computer Science, Artificial Intelligence
Hao Luo et al.
PATTERN RECOGNITION
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Amir Ghahremani et al.
COMPUTATIONAL SCIENCE - ICCS 2019, PT V
(2019)
Article
Engineering, Civil
Dilip K. Prasad et al.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Basura Fernando et al.
2013 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2013)
Article
Computer Science, Artificial Intelligence
Sinno Jialin Pan et al.
IEEE TRANSACTIONS ON NEURAL NETWORKS
(2011)
