检索结果-内蒙古大学图书馆

9th International Conference on Vehicle Technology and Intelligent Transport Systems (VEHITS)

作者： Ramajo-Ballester, Alvaro de la Escalera Hueso, Arturo Armingol Moreno, Jose Maria Univ Carlos III Madrid Intelligent Syst Lab Madrid Spain

ISBN: (纸本)9789897586521

Autonomous driving has been one of the most promising research lines in the last decade. Although still far off the sought-after level 5, the research community shows great advancements in one of the most challenging tasks: the 3d perception. The rapid progress of related fields like deep Learning is one the reasons behind this success. This enables and improves the processing algorithms for the input data provided by LidAR, cameras, radars and such other devices used for environment perception. With such growing knowledge, reviewing and structuring the state-of-the-art solutions becomes a necessity in order to correctly address future research directions. This paper provides a comprehensive survey of the progress of 3d object detection in terms of sensor data, available datasets, top-performing architectures and most notable frameworks that serve as a baseline for current and upcoming works.

关键词： 3d object detection Autonomous driving deep Learning

来源：评论

学校读者我要写书评

暂无评论

SCNet3d: Rethinking the Feature Extraction Process of Pillar-Based 3d object detection

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2025年第1期26卷 770-784页

作者： Li, Junru Wang, Zhiling Gong, diancheng Wang, Chunchun Chinese Acad Sci Hefei Inst Phys Sci Hefei 230031 Peoples R China Univ Sci & Technol China Hefei 230026 Peoples R China Anhui ShineAuto Autonomous Driving Technol Co Ltd Hefei 230088 Peoples R China Anhui Engn Lab Intelligent Driving Technol & Appli Hefei 230031 Peoples R China Anhui Univ Sci & Technol Huainan 232002 Peoples R China

LidAR-based 3d object detection is essential for autonomous driving. In order to extract information from sparse and unordered point cloud data, pillar-based methods make the data compact and orderly by converting point cloud into pseudo images. However, these methods suffer from limited feature extraction capabilities, and tend to lose key information during the conversion, leading to inferior detection accuracy than voxel-based or point-based methods especially for small objects. In this paper, we propose SCNet3d, a novel pillar-based method that tackles the challenges of feature enhancement, information preservation, and small target detection from the perspectives of features and data. We first introduce a Feature Enhancement Module (FEM), which uses the attention mechanism to weight features in three dimensions, and enhances 3d features from local to global layer by layer. Then, a STMod-Convolution Network (SCNet) is designed, which achieves sufficient feature extraction and fusion of BEV pseudo images through two channels, one for basic feature and one for advanced feature. Moreover, a Shape and distance Aware data Augmentation (SdAA) approach is proposed to add more samples to the point cloud while maintaining the original shape and distance of the samples during the training process. Extensive experiments demonstrate that our SCNet3d has superior performance and excellent robustness. Remarkably, SCNet3d achieves the AP of 82.35% in the moderate Car category, 44.64% in the moderate Pedestrian category and 67.55% in the moderate Cyclist category on the KITTI test split in 3d detection benchmark, outperforming many state-of-the-art 3d detectors.

关键词： Feature extraction Three-dimensional displays Point cloud compression object detection Pedestrians data mining Automobiles Shape Finite element analysis Accuracy 3d object detection point cloud autonomous vehicle SCNet3d

来源：评论

学校读者我要写书评

暂无评论

Occlusion-guided multi-modal fusion for vehicle-infrastructure cooperative 3d object detection

引用

PATTERN RECOGNITION 2025年 157卷

作者： Chu, Huazhen Liu, Haizhuang Zhuo, Junbao Chen, Jiansheng Ma, Huimin Univ Sci & Technol Beijing Sch Comp & Commun Engn Beijing 100083 Peoples R China China North Artificial Intelligence & Innovat Res Collect Intelligence & Collaborat Lab Beijing Peoples R China

In autonomous driving, leveraging sensor data (e.g. camera, LidAR data) from both the vehicle and the infrastructure significantly improves perception capabilities. However, this integration traditionally results in increased demands on communication bandwidth. To address these challenges, we introduce Fusion2comm, an occlusion-guided feature fusion approach designed to optimize vehicle-infrastructure cooperative 3d object detection. Our innovative strategy employs an intelligent fusion of camera and LidAR data to enhance the expressiveness of features. Subsequently, it leverages a segmentation model to extract foreground features and utilizes an occlusion-based selection of communication content, effectively easing bandwidth constraints. We propose a multimodal foreground feature fusion architecture that selectively processes and transmits critical information, substantially reducing irrelevant background data transfer. An innovative occlusion confidence-aware communication technique dynamically adjusts communication regions based on occlusion levels, ensuring efficient data exchange. Fusion2comm sets a new benchmark in the dAIR-V2X dataset, achieving an average precision of 71.25% with minimal bandwidth usage of 2(21.04) bytes. Our comprehensive experimental evaluations confirm that Fusion2comm substantially advances detection precision while simultaneously improving communication efficiency.

关键词： 3d object detection Vehicle-infrastructure cooperative Vehicle-vehicle cooperative Occlusion Autonomous driving

来源：评论

学校读者我要写书评

暂无评论

MSSF: A 4d Radar and Camera Fusion Framework With Multi-Stage Sampling for 3d object detection in Autonomous driving

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2025年第6期26卷 8641-8656页

作者： Liu, Hongsi Liu, Jun Jiang, Guangfeng Jin, Xin Univ Sci & Technol China Dept Elect Engn & Informat Sci Hefei 230027 Peoples R China Eastern Inst Technol Ningbo Inst Digital Twin Ningbo 315201 Zhejiang Peoples R China

As one of the automotive sensors that have emerged in recent years, 4d millimeter-wave radar has a higher resolution than conventional 3d radar and provides precise elevation measurements. But its point clouds are still sparse and noisy, making it challenging to meet the requirements of autonomous driving. Camera, as another commonly used sensor, can capture rich semantic information. As a result, the fusion of 4d radar and camera can provide an affordable and robust perception solution for autonomous driving systems. However, previous radar-camera fusion methods have not yet been thoroughly investigated, resulting in a large performance gap compared to LidAR-based methods. Specifically, they ignore the feature-blurring problem and do not deeply interact with image semantic information. To this end, we present a simple but effective multi-stage sampling fusion (MSSF) network based on 4d radar and camera. On the one hand, we design a fusion block that can deeply interact point cloud features with image features, and can be applied to commonly used single-modal backbones in a plug-and-play manner. The fusion block encompasses two types, namely, simple feature fusion (SFF) and multi-scale deformable feature fusion (MSdFF). The SFF is easy to implement, while the MSdFF has stronger fusion abilities. On the other hand, we propose a semantic-guided head to perform foreground-background segmentation on voxels with voxel feature re-weighting, further alleviating the problem of feature blurring. Extensive experiments on the View-of-delft (Vod) and TJ4dRadset datasets demonstrate the effectiveness of our MSSF. Notably, compared to state-of-the-art methods, MSSF achieves a 7.0% and 4.0% improvement in 3d mean average precision on the Vod and TJ4dRadSet datasets, respectively. It even surpasses classical LidAR-based methods on the Vod dataset.

关键词： Three-dimensional displays Radar Point cloud compression Radar imaging Cameras object detection Feature extraction Laser radar doppler radar Sensors 3d object detection 4d radar camera multi-modal fusion deep learning autonomous driving

来源：评论

学校读者我要写书评

暂无评论

LXLv2: Enhanced LidAR Excluded Lean 3d object detection with Fusion of 4d Radar and Camera

引用

IEEE ROBOTICS ANd AUTOMATION LETTERS 2025年第3期10卷 2862-2869页

作者： Xiong, Weiyi Zou, Zean Zhao, Qiuchi He, Fengchun Zhu, Bing Beihang Univ Sch Automat Sci & Elect Engn Beijing 100191 Peoples R China Continental Autonomous Mobil Shanghai Co Ltd Shanghai 201807 Peoples R China

As the previous state-of-the-art 4d radar-camera fusion-based 3d object detection method, LXL utilizes the predicted image depth distribution maps and radar 3d occupancy grids to assist the sampling-based image view transformation. However, the depth prediction lacks accuracy and consistency, and the concatenation-based fusion in LXL impedes the model robustness. In this work, we propose LXLv2, where modifications are made to overcome the limitations and improve the performance. Specifically, considering the position error in radar measurements, we devise a one-to-many depth supervision strategy via radar points, where the radar cross section (RCS) value is further exploited to adjust the supervision area for object-level depth consistency. Additionally, a channel and spatial attention-based fusion module named CSAFusion is introduced to improve feature adaptiveness. Experimental results on the View-of-delft and TJ4dRadSet datasets show that the proposed LXLv2 can outperform LXL in detection accuracy, inference speed and robustness, demonstrating the effectiveness of the model.

关键词： Radar Radar cross-sections Three-dimensional displays Radar imaging Radar detection object detection Laser radar Cameras Feature extraction depth measurement 3d object detection 4d imaging radar autonomous driving camera deep learning multi-modal fusion

来源：评论

学校读者我要写书评

暂无评论

An Efficient Ungrouped Mask Method With two Learnable Parameters for 3d object detection

引用

IEEE TRANSACTIONS ON MULTIMEdIA 2025年 27卷 1003-1017页

作者： Guo, Shuai Shi, Lei Jiang, Xiaoheng Lv, Pei Liu, Qidong Hu, Yazhou Ji, Rongrong Xu, Mingliang Zhengzhou Univ Sch Comp & Artificial Intelligence Zhengzhou 450000 Peoples R China Zhengzhou Univ Engn Res Ctr Intelligent Swarm Syst Zhengzhou 450000 Peoples R China Xiamen Univ Sch Informat Dept Artificial Intelligence Media Analyt & Comp Lab Xiamen 361005 Peoples R China Xiamen Univ Inst Artificial Intelligence Xiamen 361005 Peoples R China Xiamen Univ Fujian Engn Res Ctr Trusted Artificial Intelligenc Xiamen 361005 Peoples R China Peng Cheng Lab Shenzhen Peoples R China

In 3d point cloud-based object detection, attention mechanism in Group-Free (Liu et al.,2021) learns direct relationships between proposals and all seed points, providing each proposal with a global context in the form of a cross-attention map. However, our analysis and experimental comparison show that the attention mechanism assigns inappropriately large attention weights to certain seed points far from a proposal, which is not conducive to detecting objects correctly. In this work, we alleviate the above problem by proposing a mask method. For an initial proposal, our method first calculates a spatial distance-based mask, which measures the spatial relationship between all seed points and the proposal. Then, we fuse the mask into cross-attention layers in stacked attention modules and get a refined cross-attention map. In essence, our mask gives each proposal a local context;after it is fused with the global context given by the attention mechanism, the refined cross-attention map could suppress the negative impact of some distant seed points on a proposal. We present two alternative strategies to compute the mask, a hard mask, and a soft mask. Experimental results demonstrate that the soft mask brings better performance. In the soft mask, for each initial proposal's 3d-box shape, we use a parametric approximate ellipsoid as the basis of the mask's calculation, which has only two learnable parameters. Experimental results show our work could outperform Group-Free 0.7 mAP@0.25 at the cost of increasing inference time by less than 1%. The performance of our algorithm on the public dataset SUN RGB-d is 63.7 mAP@0.25 and 45.5 mAP@0.5, which is the best performance among algorithms that preserve the irregular of seed points.

关键词： Proposals Transformers Three-dimensional displays Feature extraction object detection Point cloud compression Pipelines 3d object detection deep learning masked cross attention

来源：评论

学校读者我要写书评

暂无评论

Investigating 3d object detection using stereo camera and LidAR fusion with bird's-eye view representation

引用

NEUROCOMPUTING 2025年 620卷

作者： Nie, Xin Zhu, Lin He, Zhicheng Cheng, Aiguo Zhong, Shengshi Li, Eric Hunan Univ State Key Lab Adv Design & Manufacture Technol Veh Changsha 410082 Peoples R China Wuling New Energy Automobile Co Ltd Liuzhou 545007 Peoples R China Teesside Univ Sch Comp Engn & Digital Technol Middlesbrough England

Multi-sensor fusion for 3d object detection is a crucial development in autonomous vehicle technology. Current research primarily explores the combination of monocular cameras with LidARs. However, there is a notable gap in the integration of stereo cameras with LidARs. A significant drawback of the fusion between monocular cameras and LidARs is its vulnerability to sensor failures, which can completely disable the system. This paper presents a novel end-to-end framework called SLBEVFusion, which leverages the effective combination of stereo cameras and LidARs for 3d object detection. The framework utilizes the rich semantic and depth data from stereo images along with spatial data from LidAR point clouds to improve detection accuracy. Moreover, it addresses sensor failures by isolating the data streams of each sensor and implementing straightforward feature fusion in Bird's Eye View (BEV) space. Comprehensive testing on the challenging KITTI dataset demonstrates that our approach significantly enhances performance in 3d object detection by merging stereo cameras with LidARs.

关键词： 3d object detection Autonomous driving Stereo images BEV features LidAR-Stereo fusion

来源：评论

学校读者我要写书评

暂无评论

Point-Level Fusion and Channel Attention for 3d object detection in Autonomous driving

引用

SENSORS 2025年第4期25卷 1097-1097页

作者： Shen, Juntao Fang, Zheng Huang, Jin Southwest Jiaotong Univ Sch Elect Engn Chengdu 611756 Peoples R China Sichuan Inst Land Sci & Technol Sichuan Ctr Satellite Applicat Technol Chengdu 610072 Peoples R China

As autonomous driving technology progresses, LidAR-based 3d object detection has emerged as a fundamental element of environmental perception systems. PointPillars transforms point cloud data into a two-dimensional pseudo-image and employs a 2d CNN for efficient and precise detection. Nevertheless, this approach encounters two primary challenges: (1) the sparsity and disorganization of raw point clouds hinder the model's capacity to capture local features, thus impacting detection accuracy;and (2) existing models struggle to detect small objects within complex environments, particularly regarding orientation estimation. To address these issues, we propose two enhancements: (1) point-level fusion of LidAR point clouds and RGB images, which integrates the semantic information of 2d images with the geometric features of 3d point clouds to improve model performance in intricate scenarios;(2) the incorporation of the Efficient Channel Attention mechanism to concentrate on essential features, particularly for small and sparse objects. Experimental results on the KITTI dataset indicate significant improvements, particularly in small object detection tasks, such as identifying pedestrians and cyclists. The enhanced model also demonstrates substantial gains in the Average Orientation Similarity (AOS) metric. These enhancements enhance the vehicle's ability to track and predict object trajectories in dynamic environments, critical for reliable recognition and decision-making.

关键词： autonomous driving 3d object detection multimodal fusion channel attention mechanism ECA

来源：评论

学校读者我要写书评

暂无评论

dSC3d: deformable Sampling Constraints in Stereo 3d object detection for Autonomous driving

引用

IEEE TRANSACTIONS ON CIRCUITS ANd SYSTEMS FOR VIdEO TECHNOLOGY 2025年第3期35卷 2794-2805页

作者： Chen, Jiawei Song, Qi Guo, Wenzhong Huang, Rui Fuzhou Univ Coll Comp & Data Sci Fuzhou 350116 Peoples R China Chinese Univ Hong Kong Shenzhen CUHKSZ Sch Sci & Engn Hong Kong 518172 Guangdong Peoples R China

Camera-based stereo 3d object detection estimates 3d properties of objects with binocular images only, which is a cost-effective solution for autonomous driving. The state-of-the-art methods mainly improve the detection accuracy of general objects by designing ingenious stereo matching algorithms or complex pipeline modules. Moreover, additional fine-grained annotations, such as masks or LidAR point clouds, are often introduced to deal with the occlusion problems, which brings in high manual costs for this task. To address the detection bottleneck caused by occlusion in a more cost-effective manner, we develop a novel stereo 3d object detection method named dSC3d, which achieves significant improvements for occluded objects without introducing additional supervision. Specifically, we first report the ambiguity in feature sampling, which refers to the presence of noisy features in the sampling for occluded objects. Then, we propose the Epipolar Constraint deform-Attention (ECdA) module to address the unreliable left-right correspondence computation in stereo matching caused by occlusion, which reweights epipolar features by adaptively aggregating local neighbor information. Furthermore, to ensure that 3d property estimation is based on robust object features, we propose visible regions guided constraint to explicitly guide the offset learning for feature sampling. Extensive experiments conducted on the KITTI benchmark have demonstrated the proposed dSC3d outperforms the state-of-the-art camera-based methods.

关键词： 3d object detection stereo matching binocular images binocular images occluded object occluded object autonomous driving autonomous driving autonomous driving

来源：评论

学校读者我要写书评

暂无评论

MIM: High-definition Maps Incorporated Multi-View 3d object detection

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2025年第3期26卷 3989-4001页

作者： Xiao, Jinsheng Wang, Shurui Zhou, Jian Tian, Ziyue Zhang, Hongping Wang, Yuan-Fang Wuhan Univ Sch Elect Informat Wuhan 430072 Peoples R China Wuhan Univ State Key Lab Informat Engn Surveying Mapping & Re Wuhan 430072 Peoples R China Wuhan Univ GNSS Res Ctr Wuhan 430072 Peoples R China Univ Calif Santa Barbara Dept Comp Sci Santa Barbara CA 93106 USA

3d object detection has aroused increasing interest as a crucial component of autonomous driving systems. While recent works have explored various multi-modal fusion methods to enhance accuracy and robustness, fusing multi-view images and high-definition (Hd) maps remains uncharted. Inspired by our previous work, we endeavor to introduce Hd maps to camera-based detection, prompting the design of a new framework. To address this, we first analyze the function of Hd maps in object detection to understand their benefits and the rationale for their fusion. From this analysis, we identify key disparities in view, semantics, and scale, leading to the development of MIM, a framework for Hd Maps Incorporated Multi-view 3d object detection. Hd maps are enriched in semantics by sampling unlabeled areas and encoding them into map features. Simultaneously, multi-view images are transformed into features in bird's-eye view (BEV) using the adopted baseline. These features are then fused using attention mechanisms to align scales. Experiments conducted on the nuScenes dataset demonstrate that MIM outperforms camera-based methods. Moreover, an in-depth analysis investigates how Hd maps impact object detection regarding each semantic layer. The results underscore the operational intricacies of Hd maps in perception, setting the stage for future research. Code is available at https://***/WHU-xjs/MIM-3d-det.

关键词： 3d object detection autonomous driving multi- modal fusion multi- modal fusion multi-view images high-definition maps high-definition maps high-definition maps

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：