检索结果-内蒙古大学图书馆

Multimodal 3D object detection Based on Sparse Interaction in Internet of Vehicles

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2025年第2期74卷 2174-2186页

作者： Li, Hui Ge, Tongao Bai, Keqiang Nie, Gaofeng Xu, Lingwei Ai, Xiaoxue Cao, Song Qingdao Univ Sci & Technol Dept Informat Sci & Technol Qingdao 266061 Peoples R China Beijing Univ Posts & Telecommun State key Lab Networking & Switching Technol Beijing 100876 Peoples R China Guangxi Minzu Univ Guangxi Key Lab Hybrid Computat & IC Design Anal Nanning 530006 Peoples R China Southwest Univ Sci & Technol Sch Informat Engn Mianyang 621010 Sichuan Peoples R China

Combining the Internet of Vehicles with autonomous driving visual perception can enhance vehicle intelligence. Vehicles use the 3D object detection algorithm to perceive their surroundings and share detection results with other vehicles using the internet of vehicles technology, improving the efficiency of intelligent transportation systems. Multimodal information fusion of LiDAR and cameras can improve the performance of 3D object detection. However, the different modality information is inhomogeneous, multimodal 3D object detection still has challenges, such as difficult semantic alignment of modal elements and inadequate fusion. To mitigate these challenges, we first propose the sparse interaction with centroid query (SICQ) for voxel-level features from different modalities, which aligns different modal semantic information through more precise and fine-grained interaction. Then, we propose the dense fusion with multi-scale masked attention (DFMMA), using multi-scale feature masks from bird's-eye-view (BEV)-level multimodal features to improve performance for small object feature perception. Finally, we propose the multimodal grid encoder with positional information (MGEPI), through positional information implicitly guiding and the transformer-based attention mechanism for grid-level features, improves the perception of detection scene context spatial information and enhances the robustness of the algorithm. Additionally, this paper performs comprehensive experiments on the popular KITTI dataset and demonstrates that our algorithm has superior 3D object detection performance.

关键词： Three-dimensional displays Feature extraction object detection Laser radar Point cloud compression Cameras Semantics Vehicle technology multimodal fusion 3D object detection Internet of Vehicles

来源：评论

学校读者我要写书评

暂无评论

Shape-Dependent Dynamic Label Assignment for Oriented Remote Sensing object detection

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 132-146页

作者： Zhang, Xue Wu, Yanxia Zhang, Guoyin Yuan, Ye Cheng, Guangliang Wu, Yulei Harbin Engn Univ Coll Comp Sci & Technol Harbin 150001 Peoples R China Univ Liverpool Dept Comp Sci Liverpool L69 3BX England Univ Bristol Fac Sci & Engn Bristol BS8 1UB England

Oriented remote sensing object detection (ORSOD) has gained increasing significance in both military and civilian applications due to the necessity of accurately identifying objects with varying shapes and orientations in remote sensing data. Traditional ORSOD methods often employ fixed label assignment strategies to differentiate between positive and negative samples. However, most of them frequently overlook the impact of object shape on sample quality, leading to an imbalanced distribution of positive samples and exacerbating the inconsistency between classification and regression tasks, thereby limiting detection performance. To address these challenges, we propose a novel shape-dependent assignment (SDA) method that dynamically differentiates positive and negative samples based on object shape. It introduces a new metric for evaluating sample box quality by considering angular differences relative to ground truth (GT) boxes and adjusts the sample scoring threshold according to the aspect ratio of each GT box. In addition, we present a DIoU-adaptive weighting (DAW) module that enhances the interaction between classification and regression tasks by leveraging the distance-IoU metric. This approach not only balances the quantity of samples but also improves their quality, enabling more effective training schemes for samples of varying qualities. We validate our proposed methods through extensive experiments on three challenging ORSOD datasets: DOTA-1.0, HRSC2016, and UCAS-AOD. The results demonstrate that our approach achieves significant improvements, especially for objects with large aspect ratios.

关键词： Training Remote sensing Detectors object detection Shape Location awareness Measurement Sensors object recognition Correlation High-quality samples label assignment objects with large aspect ratios oriented remote sensing object detection (ORSOD)

来源：评论

学校读者我要写书评

暂无评论

AEFFNet: Attention Enhanced Feature Fusion Network for Small object detection in UAV Imagery

引用

IEEE ACCESS 2025年 13卷 26494-26505页

作者： Nian, Zhaoyu Yang, Wenzhu Chen, Hao Hebei Univ Sch Cyber Secur & Comp Baoding 071002 Hebei Peoples R China Hebei Machine Vis Engn Res Ctr Baoding 071002 Hebei Peoples R China

The rapid advancement of unmanned aerial vehicle (UAV) technology has markedly increased the use of drone-captured imagery across various applications, necessitating enhanced accuracy and real-time performance in UAV image detection. Addressing the specific challenges posed by small and densely distributed objects in such images, we introduce an attention enhanced feature fusion network (AEFFNet) designed specifically for small object detection in UAV imagery. Firstly, a hybrid attention module with associated multi-axis frequency and spatial attention was designed to enhance the feature extraction of small objects. Secondly, an adjacent layer feature fusion module is innovatively proposed in order to boost the detection capabilities for small and occluded objects. Finally, a series experiments are conducted on the VisDrone2023 dataset, which involves a large number of small objects photographed by drones. Our evaluations, conducted on the VisDrone2023 dataset, demonstrate substantial improvements over the YOLOv8m baseline model, with a 3.0% increase in mean Average Precision (mAP) and a 4.4% rise in AP50.

关键词： Feature extraction Autonomous aerial vehicles Head Detectors Attention mechanisms Neck Location awareness Accuracy YOLO Semantics object detection small object detection attention mechanism multi-scale feature fusion

来源：评论

学校读者我要写书评

暂无评论

Fast object detection and Localization in Ultrawide Swath Rotating Scan Remote Sensing Images

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 4767-4779页

作者： Deng, Zhiming Zhang, Tianyu Wei, Cheng Cao, Xibin Harbin Inst Technol Sch Astronaut Harbin 150001 Peoples R China

In the field of remote sensing, rotating scan optical satellites are an important innovation, offering the unique advantage of capturing extensive ground coverage areas with high precision. However, unlike traditional remote sensing images, the inherent characteristics of rotating scan remote sensing images make fast object detection and localization a more challenging task because of the ultrawide swath results in extremely high image resolution;changes in the rotation angle cause variations in resolution;the large variation in object size;and side-looking imaging introduces greater geometric distortions. A common solution is to divide the large remote sensing image into smaller (uniform) patches, and then, apply object detection to each small patch. In this article, we investigate image cropping strategies to address these challenges. Specifically, we propose an adaptive image cropping method (AICM) for rotating scan remote sensing images. Starting from the resolution changes caused by variations in the rotation angle, we establish a ground sampling distance model that varies with the rotation angle, achieving adaptive image cropping under different ground sampling distances. Verification on ultrawide swath rotating scan remote sensing images shows that, compared with the traditional fixed stride cropping method, AICM improves the average inference speed by 7.39% and increases the mean average precision by 7.54%.

关键词： object detection remote sensing images remote sensing images rotating scan rotating scan ultrawide swath ultrawide swath

来源：评论

学校读者我要写书评

暂无评论

Improving Performance of Real-Time object detection in Edge Device Through Concurrent Multi-Frame Processing

引用

IEEE ACCESS 2025年 13卷 1522-1533页

作者： Kim, Seunghwan Kim, Changjong Kim, Sunggon Seoul Natl Univ Sci & Technol Dept Comp Sci & Engn Seoul 01811 South Korea

As the performance and accuracy of machine learning and AI algorithms improve, the demand for adopting computer vision techniques to solve various problems, such as autonomous driving and AI robots, increases. To meet such demand, IoT and edge devices, which are small enough to be adopted in various environments while having sufficient computing capabilities, are being widely adopted. However, as devices are utilized in IoT and edge environments, which have harsh restrictions compared to traditional server environments, they are often limited by low computational and memory resources, in addition to the limited electrical power supply. This necessitates a unique approach for small IoT devices that are required to run complex tasks. In this paper, we propose a concurrent multi-frame processing scheme for real-time object detection algorithms. To do this, we first divide the video into individual frames and group the frames according to the number of cores in the device. Then, we allocate a group of frames per core to perform the object detection, resulting in parallel detection of multiple frames. We implement our scheme in YOLO (You Only Look Once), one of the most popular real-time object detection algorithms, on a state-of-the-art, resource-constrained IoT edge device, Nvidia Jetson Orin Nano, using real-world video and image datasets, including MS-COCO, ImageNet, PascalVOC, DOTA, animal videos, and car-traffic videos. Our evaluation results show that our proposed scheme can improve the diverse aspect of edge performance and improve the runtime, memory consumption, and power usage by up to 445%, 69%, and 73%, respectively. Additionally, it demonstrates improvements of $2.10\times $ over state-of-the-art model optimization.

关键词： YOLO Image edge detection Performance evaluation Computational modeling Streaming media Real-time systems Load modeling Runtime Parallel processing Memory management Edge devices machine learning object detection performance optimization

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of ESP32-Based Edge Computing for object detection

引用

SENSORS 2025年第6期25卷 1656-1656页

作者： Chang, Yeong-Hwa Wu, Feng-Chou Lin, Hung-Wei Chang Gung Univ Dept Elect Engn Taoyuan City 333 Taiwan Ming Chi Univ Technol Dept Elect Engn New Taipei City 243 Taiwan

This paper explores the application of the ESP32 microcontroller in edge computing, focusing on the design and implementation of an edge server system to evaluate performance improvements achieved by integrating edge and cloud computing. Responding to the growing need to reduce cloud burdens and latency, this research develops an edge server, detailing the ESP32 hardware architecture, software environment, communication protocols, and server framework. A complementary cloud server software framework is also designed to support edge processing. A deep learning model for object recognition is selected, trained, and deployed on the edge server. Performance evaluation metrics, classification time, MQTT (Message Queuing Telemetry Transport) transmission time, and data from various MQTT brokers are used to assess system performance, with particular attention to the impact of image size adjustments. Experimental results demonstrate that the edge server significantly reduces bandwidth usage and latency, effectively alleviating the load on the cloud server. This study discusses the system's strengths and limitations, interprets experimental findings, and suggests potential improvements and future applications. By integrating AI and IoT, the edge server design and object recognition system demonstrates the benefits of localized edge processing in enhancing efficiency and reducing cloud dependency.

关键词： edge computing tiny machine learning ESP32 object detection

来源：评论

学校读者我要写书评

暂无评论

Enhancing object detection in Underground Mines: UCM-Net and Self-Supervised Pre-Training

引用

SENSORS 2025年第7期25卷 2103-2103页

作者： Zhou, Faguo Zou, Junchao Xue, Rong Yu, Miao Wang, Xin Xue, Wenhui Yao, Shuyu China Univ Min & Technol Beijing Sch Artificial Intelligence Beijing 100083 Peoples R China

Accurate real-time monitoring of underground conditions in coal mines is crucial for effective production management. However, limited computational resources and complex environmental conditions in mine shafts significantly impact the recognition and computational capabilities of detection models. This study utilizes a comprehensive dataset containing 117,887 images from five common underground mining tasks: mine personnel detection, large coal lump identification, conveyor chain monitoring, miner behavior recognition, and hydraulic support shield inspection. We propose the ESFENet backbone network, incorporating a Global Response Normalization (GRN) module to enhance feature capture stability while employing depthwise separable convolutions and HGRNBlock modules to reduce parameter volume and computational complexity. Building upon this foundation, we propose UCM-Net, a detection model based on the YOLO architecture. Furthermore, a self-supervised pre-training method is introduced to generate mine-specific pre-trained weights, providing the model with more semantic features. We propose utilizing the combined backbone and neck portions of the detection model as the encoder of an image-masking pre-training structure to strengthen feature acquisition and improve the performance of small models in self-supervised learning. Experimental results demonstrate that UCM-Net outperforms both baseline models and the state-of-the-art YOLOv12 model in terms of accuracy and parameter efficiency across the five mine datasets. The proposed architecture achieves 21.5% parameter reduction and 14.8% computational load decrease compared to baseline models while showing notable performance improvements of 1.3% (mAP50:95) and 0.8% (mAP50) in miner behavior recognition. The self-supervised pre-training framework effectively enhances training efficiency, enabling UCM-Net to attain an average mAP50 of 94.4% across all five datasets. The research outcomes can provide key technical support f

关键词： object detection coal mine self-supervised pre-training YOLO feature extraction

来源：评论

学校读者我要写书评

暂无评论

Automotive DNN-Based object detection in the Presence of Lens Obstruction and Video Compression

引用

IEEE ACCESS 2025年 13卷 36575-36589页

作者： Baris, Gabriele Li, Boda Chan, Pak Hung Avizzano, Carlo Alberto Donzella, Valentina Univ Warwick WMG Coventry CV4 7AL England St Anna Sch Adv Studies Inst Mech Intelligence I-56127 Pisa Italy

Recent advances in sensing, processing, machine learning, and communication technologies are accelerating assisted and automated functions development for commercial vehicles. Environmental perception sensor data streams are processed to generate a correct and complete situational awareness. It is of utmost importance to assess the robustness of the sensor data pipeline, particularly in the case of data degradation in a noisy and variable environment. Sensor data reduction and compression techniques are key for higher levels of driving automation, as there is an expectation that traditional automotive vehicle wired networks will not be able to support the needed sensor datarates (i.e. more than 10 perception sensors, including cameras, LiDARs, and RADARs, generating tens of Gb/s of data). This work proposes for the first time to consider video compression for camera data transmission on vehicle wired networks in the presence of highly noisy data, e.g. partially obstructed camera field of view. The effects are discussed in terms of machine learning vehicle detection accuracy drop, and also visualising how detection performance spatially varies on the frames using the recently introduced metric, the Spatial Recall Index (SRI). The presented parametric obstruction noise model is generated to emulate real-world patterns, whereas compression is based on the well-established AVC/H.264. While Deep Neural Networks' (DNNs') performance is stable with lossy compression (up to 70:1) of 'ideal' data, when noise is added there is a significant accuracy degradation, in the range of a 7%-90% decrease. The proposed compression and noise tuning of the DNN training improves the performance up to 35%, enhancing the noise and compression robustness of the system. However, in the presence of compression combined with extreme levels of noise (i.e. more than 80% of pixels affected), DNN performance significantly degrades, up to a 90% decrease, even with re-training. This issue needs to be

关键词： Noise Cameras Automotive engineering Lenses Noise measurement Laser radar Video compression object detection Degradation Streams Automated vehicles object detection noise compression deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A novel middleware for adaptive and efficient split computing for real-time object detection

引用

PERVASIVE AND MOBILE COMPUTING 2025年 108卷

作者： Mendula, Matteo Bellavista, Paolo Levorato, Marco Contreras, Sharon Ladron de Guevara Univ Bologna Dept Comp Sci & Engn Bologna Italy Univ Calif Irvine Donald Bren Sch Informat & Comp Sci Irvine CA USA

Real-world applications requiring real-time responsiveness frequently rely on energy-intensive and compute-heavy neural network algorithms. Strategies include deploying distributed and optimized Deep Neural Networks on mobile devices, which can lead to considerable energy consumption and degraded performance, or offloading larger models to edge servers, which requires low-latency wireless channels. Here we present Furcifer, a novel middleware that autonomously adjusts the computing strategy (i.e., local computing, edge computing, or split computing) based on context conditions. Utilizing container-based services and low-complexity predictors that generalize across environments, Furcifer supports supervised compression as a viable alternative to pure local or remote processing in real-time environments. An extensive set of experiments coversdiverse scenarios, including both stable and highly dynamic channel environments with unpredictable changes in connection quality and load. In moderate-varying scenarios, Furcifer demonstrates significant benefits: achieving a 2x reduction in energy consumption, a 30% higher mean Average Precision score compared to local computing, and a three-fold FPS increase over static offloading. In highly dynamic environments with unreliable connectivity and rapid increases in concurrent clients, Furcifer's predictive capabilities preserves up to 30% energy, achieving a 16% higher accuracy rate, and completing 80% more frame inferences compared to pure local computing and approaches without trend forecasting, respectively.

关键词： Edge computing Split computing Machine learning object detection Image compression Middleware Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Physically Realizable Adversarial Creating Attack Against Vision-Based BEV Space 3D object detection

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2025年 34卷 538-551页

作者： Wang, Jian Li, Fan Lv, Song He, Lijun Shen, Chao Xi An Jiao Tong Univ Sch Informat & Commun Engn Shaanxi Key Lab Deep Space Explorat Intelligent In Xian 710049 Peoples R China Xi An Jiao Tong Univ Sch Cyber Sci & Engn MOE Key Lab Intelligent Networks & Network Secur Xian 710049 Peoples R China

Vision-based 3D object detection, a cost-effective alternative to LiDAR-based solutions, plays a crucial role in modern autonomous driving systems. Meanwhile, deep models have been proven susceptible to adversarial examples, and attacking detection models can lead to serious driving consequences. Most previous adversarial attacks targeted 2D detectors by placing the patch in a specific region within the object's bounding box in the image, allowing it to evade detection. However, attacking 3D detector is more difficult because the adversary may be observed from different viewpoints and distances, and there is a lack of effective methods to differentiably render the 3D space poster onto the image. In this paper, we propose a novel attack setting where a carefully crafted adversarial poster (looks like meaningless graffiti) is learned and pasted on the road surface, inducing the vision-based 3D detectors to perceive a non-existent object. We show that even a single 2D poster is sufficient to deceive the 3D detector with the desired attack effect, and the poster is universal, which is effective across various scenes, viewpoints, and distances. To generate the poster, an image-3D applying algorithm is devised to establish the pixel-wise mapping relationship between the image area and the 3D space poster so that the poster can be optimized through standard backpropagation. Moreover, a ground-truth masked optimization strategy is presented to effectively learn the poster without interference from scene objects. Extensive results including real-world experiments validate the effectiveness of our adversarial attack. The transferability and defense strategy are also investigated to comprehensively understand the proposed attack.

关键词： Three-dimensional printing Detectors Roads object detection Autonomous vehicles Pipelines Feature extraction Visualization Solid modeling Perturbation methods Physical adversarial attack visual 3D detection universal patch adversarial robustness

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

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

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

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

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：