检索结果-内蒙古大学图书馆

An Empirical Study of Ground Segmentation for 3-D Object detection

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2025年第3期26卷 3071-3083页

作者： Yang, Hongcheng Liang, Dingkang Liu, Zhe Li, Jingyu Zou, Zhikang Ye, Xiaoqing Bai, Xiang Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Baidu Inc Beijing 100085 Peoples R China

The ratio of foreground and background points directly impacts the accuracy and speed of the lidar-based 3D object detection methods. However, existing methods generally ignore the impact of ground points. Although some traditional ground segmentation algorithms are available to remove ground point clouds, they usually suffer from over-segmentation, which leads to a sub-optimal and even worse performance for the downstream 3D detection task. We conduct an in-depth analysis and attribute this phenomenon to the reason that some crucial foreground points attached to the ground (e.g., the wheels of Cars, or the feet of Pedestrians) are directly removed due to over-segmentation. To this end, we propose a new Attached Point Restoring (APR) module to recover these discarded foreground points. Experimental results demonstrate the effectiveness and generalization of APR by integrating it into various ground segmentation algorithms to boost the performance or the running time of 3D detection on KITTI and Waymo datasets. Finally, we hope this paper can serve as a new guide to inspire future research in this field. Code is available at https://***/yhc2021/GPR.

关键词： Three-dimensional displays Point cloud compression Feature extraction Object detection Accuracy Detectors detection algorithms Convolution Solid modeling Mathematical models Point cloud 3D object detection ground segmentation

来源：评论

学校读者我要写书评

暂无评论

A Multicamera detection Algorithm for Small Obstacle Characteristics in the Rail Under Complex and Variable Illumination Conditions

引用

IEEE SENSORS JOURNAL 2025年第2期25卷 3772-3781页

作者： Qiu, Yefeng He, Deqiang Jin, Zhenzhen Chen, Yanjun Shan, Sheng Cent South Univ Sch Traff & Transportat Engn Changsha 410018 Hunan Peoples R China Guangxi Univ Sch Mech Engn Guangxi Mfg Syst & Adv Mfg Technol Key Lab Nanning 530004 Peoples R China CRRC Zhuzhou Inst Co Ltd Zhuzhou 412001 Peoples R China

In addressing the challenges of false positives and missed detections of small-scale obstacles within low-illumination orbital environments, a multiscale detection algorithm MTD R-CNN based on multicamera is proposed. The proposed model contains three stages. In stage 1, the LCSwin Transformer is proposed to complete aggregating detailed features and global relationships. In stage 2, the SAFPN is proposed to realize hierarchical feature interaction at different scales. In stage 3, dynamic instance interactive head multiplexing and multiple loss sets are used to obtain more decadent detection boxes. The test results of the track scene under different illumination conditions show that 1) the accuracy of the MTD R-CNN is 95.2%, surpassing the performance of existing models;2) the detection accuracy of small obstacles is improved by 3.7%-26.4%, thereby highlighting the model's superior perceptual capabilities for detecting such obstacles;and 3) the operation speed of the model is 36.63 ms to meet the real-time processing criteria. In summary, the model effectively improves the detection performance of small obstacles under low-light light conditions and has been applied in Nanning Metro Line 5.

关键词： Feature extraction Transformers Lighting Rails Head detection algorithms Accuracy Cameras Proposals Convolution Multicamera multiscale detection rail transit small obstacle weak illumination

来源：评论

学校读者我要写书评

暂无评论

Unbiased High-Precision Cloud detection for Advanced Himawari Imager Using Automatic Machine Learning

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 6217-6231页

作者： Liu, Bochun Ge, Jinming Mu, Qingyu Zhang, Chi Hu, Xiaoyu Du, Jiajing Wu, Yanyan Wang, Bo Li, Xiang Huang, Jianping Fu, Qiang Lanzhou Univ Coll Atmospher Sci Key Lab Semiarid Climate Change Minist Educ Lanzhou 730000 Peoples R China Peking Univ Chongqing Res Inst Big Data Chongqing 401333 Peoples R China Univ Washington Dept Atmospher Sci Seattle WA 98195 USA

Clouds play a pivotal role in the global radiation budget and energy cycle, making accurate cloud detection via satellite remote sensing essential for understanding their evolutions. However, existing machine learning-based cloud detection algorithms have limitations, particularly in data preprocessing and feature engineering, and few are designed to cover the entire geostationary satellite observation region. In this study, we integrate three deviation elimination schemes for cloud cover differences and various surface type characterization modes to develop an unbiased, high-precision cloud detection algorithm for the advanced Himawari imager (AHI) onboard Himawari-8, leveraging automatic machine learning (AutoML) techniques. In addition, we provide a new perspective on model interpretability by incorporating concepts from cooperative game theory. Our results indicate that cloud detection algorithms constructed separately for different surfaces yield better results than those applied uniformly across the entire region by inputting surface feather. The optimal algorithm achieves unbiased cloud detection across multiple surfaces by adjusting the output threshold of the mapping function, allowing for cloud detection results with varying confidence levels as required. The true skill statistic of the optimal AutoML-based cloud detection algorithm is 87.32%, which is 13.72% higher than that of the AHI official cloud mask. The deviation rate of the optimal algorithm is only 0.79%, significantly lower than the 20.48% of the AHI official cloud mask. Long-term cloud frequency (CF) tests show that our optimal algorithm's CF distribution is more consistent with cloud-aerosol lidar with orthogonal polarization results compared with the AHI official products.

关键词： Clouds detection algorithms Training Accuracy Spaceborne radar Meteorology Machine learning Instruments Data models Spatial resolution Automatic machine learning (AutoML) geostationary satellite marginal contribution unbiased cloud detection

来源：评论

学校读者我要写书评

暂无评论

A Diversified Population Migration-Based Multiobjective Evolutionary Algorithm for Dynamic Community detection

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2025年第1期9卷 145-159页

作者： Zhang, Lei Qin, Chaofan Yang, Haipeng Xiong, Zishan Cao, Renzhi Cheng, Fan Anhui Univ Sch Comp Sci & Technol Informat Mat & Intelligent Sensing Lab Anhui Prov Hefei 230039 Peoples R China Pacific Lutheran Univ Sch Comp Sci Tacoma WA 98447 USA

Dynamic community detection, which is capable of revealing changes in community structure over time, has garnered increasing attention in research. While evolutionary clustering methods have proven to be effective in tackling this issue, they often have a tendency to favor what are referred to as elite solutions, inadvertently neglecting the potential value of non-elite alternatives. Although elite solutions can ensure population convergence, they may result in negative population migration due to the lack of diversity when the network changes. In contrast, when the network undergoes changes, non-elite solutions could better adapt to the changed network, thereby can help the algorithm find accurate community structures in the new environment. To this end, we propose a diversified population migration strategy that consists of two-stages, i.e., solution selection and solution migration. In the first stage, we use elite solutions not only to ensure convergence but also non-elite solutions to maintain diversity and cope with network changes. In the second stage, the migration solutions are refined by using incremental changes between the two consecutive snapshots of networks. Based on the proposed strategy, we suggest a diversified population migration-based multiobjective evolutionary algorithm named DPMOEA. In DPMOEA, we design new genetic operators that utilize incremental changes between networks to make the population evolve in the right direction. Our experimental results demonstrate that the proposed method outperforms state-of-the-art baseline algorithms and can effectively solve the dynamic community detection problem.

关键词： Heuristic algorithms Accuracy Optimization Image edge detection Fans detection algorithms Symbols Community detection dynamic network diversity evolutionary clustering

来源：评论

学校读者我要写书评

暂无评论

SVDD: SAR Vehicle Dataset Construction and detection

引用

IEEE ACCESS 2025年 13卷 18107-18122页

作者： Gao, Dan Wu, Xiaofang Wen, Zhijin Xu, Yue Chen, Zhengchao Acad Mil Sci Peoples Liberat Army Inst Syst Engn Beijing 100191 Peoples R China Chinese Acad Sci Aerosp Informat Res Inst Key Lab Remote Sensing & Digital Earth Beijing 100094 Peoples R China

With the advent of high-quality SAR images and the rapid development of computing technology, the object detection algorithms based on convolution neural network have attracted a lot of attention in the field of SAR object detection. At present, the main dataset for SAR target detection in China focus on ships, there is a lack of SAR vehicle detect datasets, and complex ground scenes can affect vehicle detection performance. To solve these problems, we proposed a lightweight SAR vehicle detection algorithm, aiming to improve the vehicle detection accuracy and simplify the model complexity. First, we constructed a multi-band SAR vehicle detection dataset (SVDD) with annotations as the training dataset of the object detection model. Then, we introduced dual conv into the RT-DETR model. Dual conv uses group convolution technology to filter the convolutional network to reduce model parameters, so we can achieve a lightweight and real-time end-to-end detection. Finally, we used the mmdetection framework as a benchmark and test the robust performance under different conditions. Experimental results show that the AP50 of we proposed method reaches 98.5%, achieving excellent detection performance.

关键词： Object detection Feature extraction detection algorithms Vehicle detection Synthetic aperture radar Accuracy Real-time systems Transformers Computational modeling Complexity theory Deep learning object detection synthetic aperture radar datasets vision transformer

来源：评论

学校读者我要写书评

暂无评论

Temporal-Spatial Information Fusion Network for Multiframe Infrared Small Target detection

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Ma, Tianlei Wang, Hao Liang, Jing Wang, Yaonan Peng, Jinzhu Kai, Zhiqiang Liu, Xinhao Zhengzhou Univ Sch Elect & Informat Engn Zhengzhou 450001 Peoples R China State Key Lab Intelligent Agr Power Equipment Luoyang 471039 Peoples R China Hunan Univ Coll Robot Changsha 410082 Peoples R China Hunan Univ Coll Elect & Informat Engn Changsha 410082 Peoples R China

The detection of small targets in infrared technology is of paramount importance in sectors like early warning and aerospace engineering. However, existing detection methods primarily focus on spatial information in single frames, neglecting the rich temporal information present in sequential frames. Our solution proposes a multiframe infrared small target detection method based on the fusion of temporal-spatial information, achieving the interaction of the reference frames and the current frame. First, to improve the capture features with sufficient distinguishability in the time domain, a temporal feature refinement transformer (TFRT) based on deformable attention is constructed, obtaining fine-grained features with a global temporal context representation. Furthermore, a spatial-temporal feature fusion transformer (SFFT) is designed based on cross-attention mechanism. This module adaptively fuses fine-grained temporal features from the reference frame with spatial features from the current frame, facilitating cross-frame spatial-temporal information interaction and enhancing the spatial features of small targets. Finally, a 3-D depthwise separable convolution (3DDSC) and 2-D depthwise separable convolution (DSC) is introduced to establish a weight-sharing temporal and spatial feature extraction network, respectively, thereby reducing the computational complexity and parameter count of the model. Experimental results on public datasets demonstrate that by effectively integrating temporal and spatial information, the model exhibits stronger anti-interference capabilities. It can effectively suppress false alarms while ensuring target detection, thereby reducing computational resource consumption.

关键词： Convolution Feature extraction Current transformers Object detection Computational modeling detection algorithms Attention mechanisms Three-dimensional displays Data mining Clutter Depthwise convolution (DWC) feature enhancement infrared small target object detection temporal-spatial information fusion transformer

来源：评论

学校读者我要写书评

暂无评论

Vessel detection Based on SDGSAT-1s Thermal Infrared and Low-Light Data

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Wang, Tao Li, Kun Dou, Xianhui Han, Qijin Zhao, Hang Zeng, Jian Lan, Qiongqiong Wu, You Zhao, Yue Shang, Yongjie Qian, Yonggang Chinese Acad Sci Aerosp Informat Res Inst Key Lab Digital Earth Sci Beijing 100094 Peoples R China Univ Chinese Acad Sci Coll Resources & Environm Beijing 100049 Peoples R China Int Res Ctr Big Data Sustainable Dev Goals Beijing 100094 Peoples R China Minist Nat Resources Land Satellite Remote Sensing Applicat Ctr Beijing Peoples R China China Ctr Resources Satellite Data & Applicat Beijing Peoples R China Surveying & Mapping Stn Xian 710000 Peoples R China Minist Nat Resources Geodet Survey Team 1 Beijing 100083 Peoples R China

The Sustainable Development Goals Science Satellite-1 (SDGSAT-1) is equipped with both low-light and thermal infrared imagers, which can detect infrared radiation and weak light information emitted by vessels. Compared to similar products, its spatial resolution has undergone a significant improvement. Existing remote sensing vessel detection methods only consider the use of single-source data for vessel detection, fail to effectively utilize the complementary information in multisource data, and have difficulty processing the complex vessel shapes of high-resolution satellite data, resulting in unsatisfactory detection results. In view of the sparse distribution of vessels at sea, this article proposes a new vessel target detection method using SDGSAT-1 high-resolution thermal infrared and low-light satellite data. Specifically, guided filtering is used to fuse thermal infrared and low-light data, the background and foreground are separated by partial sum of tensor core norms (PSTNN) model, and then the ordering points to identify the clustering structure (OPTICS) clustering algorithm and intercluster merging are used for detection. This article established a vessel dataset by choosing Shanghai Port, Hong Kong Port, and the Gulf of Mexico and then applied the algorithm. The detection accuracy and recall rate were found to be 97.67% and 97.80% respectively, which were significantly superior to other algorithms. This algorithm overcomes the complex background noise in the dataset and achieves good detection results.

关键词： Remote sensing Data models Tensors Ocean temperature Filtering detection algorithms Atmospheric modeling YOLO Temperature distribution Satellites Guided filtering local structure tensor low-light remote sensing ordering points to identify the clustering structure (OPTICS) partial sum of tensor core norms (PSTNN) Sustainable Development Goals Science Satellite-1 (SDGSAT-1) thermal infrared remote sensing vessel detection

来源：评论

学校读者我要写书评

暂无评论

ArcSE: A Dual-Branch Semantic Segmentation Model for Robust PantographCatenary Arcing detection in Complex Environments

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Quan, Wei Xu, Xiaoqian Liu, Xiaolin Wang, Xiaoyu Gao, Shibin Southwest Jiaotong Univ Sch Elect Engn Chengdu 610097 Peoples R China

The pantograph-catenary system (PCS) is a key equipment for electric trains to obtain electrical energy from the traction power supply system. As an abnormal phenomenon in the PCS, pantograph-catenary arcing (PCA) directly affects the current collection quality and operational safety of electric trains. Therefore, it is very important to achieve precise detection of PCA. At present, aiming at the difficulties in detecting small arcing and the poor performance of arcing detection in complex environments in the visual detection task of PCA, a semantic segmentation model arcing segmentation (ArcSE) based on feature enhancement is proposed. This model designs a PCA segmentation model that includes semantic feature branches (SFBs), detail feature branches (DFBs), and feature enhancement mechanisms (FEMs). To address the difficulty of detecting small arcing, a dual-branch structure is designed, which utilizes the semantic information extracted from the SFB to adjust the detail feature map in the DFB, filters out interfering features, and retains small arcing features. Aiming at the difficulty of identifying arcing targets in complex scenes, an FEM is designed, merging the arcing features with the detailed features at different scales through a multiscale features fusion strategy. At the same time, based on the learnable visual center module, the difference between arcing features and background features is further strengthened, effectively improving the robustness of the model. Experiments were conducted on the constructed dataset to validate the effectiveness of ArcSE, with a segmentation accuracy of 89.70% and an inference speed of 14.91 ms.

关键词： Feature extraction Semantics Transformers Accuracy detection algorithms Semantic segmentation Interference Data mining Shape Safety Dual branch feature enhancement pantograph-catenary arcing (PCA) robust arcing detection semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing Image detection Method Combining Dynamic Convolution and Attention Mechanism

引用

IEEE ACCESS 2025年 13卷 47271-47290页

作者： Zhang, Yunfei Chen, Ming Chen, Cong China Geol Survey Urumqi Nat Resources Comprehens Survey Ctr Urumqi 830057 Peoples R China Univ Sanya Sch Informat & Intelligent Engn Sanya 572022 Peoples R China Hainan Trop Ocean Univ Sch Marine Informat Engn Sanya 572022 Peoples R China

Small object detection in remote sensing images is challenging. Traditional CNN downsampling often leads to the loss of small object details and missed detections. This paper proposes an improved YOLOv8 algorithm, incorporating adaptive feature extraction and multi-scale fusion modules to enhance feature representation, effectively capturing the details of small objects. We introduced the AFGCAttention mechanism to strengthen the network's focus on key regions while suppressing irrelevant background information, improving the model's ability to recognize small objects. To address the resolution loss issue in small object detection, we adopted the CARAFE (Content-Aware ReAssembly of FEatures) upsampling operator. By performing content-aware reassembly of feature maps, CARAFE avoids the blurriness and information loss commonly associated with traditional upsampling methods, demonstrating significant advantages in reconstructing the details of small objects, resulting in clearer and more accurate boundaries. Additionally, to improve the accuracy of bounding box regression, we integrated the GIoU loss function to optimize the geometric matching between ground truth and predicted boxes, addressing the problem of inaccurate bounding box localization for small objects and enhancing localization precision. Experimental results demonstrate that the proposed algorithm significantly improves the precision of small object detection and maintains robustness in complex backgrounds. The improved model achieved an mAP of 83.0%, with accuracy improvements of 85.0%, 2.0%, and 5.0% compared to the baseline. Compared with existing detection methods, this approach shows outstanding performance in detection accuracy, localization precision, and computational efficiency, particularly excelling in small object detection.

关键词： Feature extraction Object detection Accuracy Remote sensing Transformers Attention mechanisms Computational modeling Computer vision detection algorithms Convolutional neural networks AFGCAttention module C2f-DCNv2-MPCA optimization module CARAFE upsampling operator GIoU loss function remote sensing image object detection YOLOv8

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Face Forgery detection for Facial Payment Systems

引用

IEEE CONSUMER ELECTRONICS MAGAZINE 2025年第3期14卷 80-86页

作者： Guo, Siyou Li, Qilei Gao, Mingliang Zhang, Guisheng Pan, Jinfeng Jeon, Gwanggil Shandong Univ Technol Zibo Peoples R China Queen Mary Univ London London E1 4NS England Incheon Natl Univ Incheon South Korea Shandong Univ Technol Sch Elect & Elect Engn Zibo Peoples R China

The development of generative adversarial networks (GANs) has revolutionized image generation and editing. However, the capacity to create realistic images presents serious security concerns, particularly in the context of face-based payment systems. Deepfakes leverages GANs to generate manipulated videos or images, which may present opportunities for identity theft and fraudulent transactions. For instance, perpetrators employ Deepfakes technology to forge identifying information about victims, such as transplanting their faces into fake videos or images to make it appear like they are performing activities they have never done before. To address this growing concern, this study proposes a deep learning-based detection method utilizing an improved convolutional neural network model. The proposed model comprises two key modules, namely the multiscale attention (MA) module and the halo attention (HA) module. Specifically, MA is designed to recognize faces and other details in the forged image. HA is built to focus on localized regions of the image. Experimental results show that the proposed model scores 97.12 and 99.32 on FF++ (HQ) dataset and 91.26 and 95.43 on FF++ (LQ) dataset in terms of accuracy and area under curve, respectively. The remarkable accuracy and performance make it a dependable solution for safeguarding face payment systems.

关键词： Deepfakes Face recognition Forgery Consumer electronics Image reconstruction Accuracy Security Generative adversarial networks Image processing detection algorithms

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：