检索结果-内蒙古大学图书馆

Cross-domain Generalization for LidAR-Based 3d object detection in Infrastructure and Vehicle Environments

SENSORS 2025年第3期25卷 767-767页

作者： Zhi, Peng Jiang, Longhao Yang, Xiao Wang, Xingzheng Li, Hung-Wei Zhou, Qingguo Li, Kuan-Ching Ivanovic, Mirjana Lanzhou Univ Sch Informat Sci & Engn Lanzhou 730000 Peoples R China Providence Univ Dept Comp Sci & Informat Engn Taichung 43301 Taiwan Univ Novi Sad Fac Sci Novi Sad 21000 Serbia

In the intelligent transportation field, the Internet of Things (IoT) is commonly applied using 3d object detection as a crucial part of Vehicle-to-Everything (V2X) cooperative perception. However, challenges arise from discrepancies in sensor configurations between vehicles and infrastructure, leading to variations in the scale and heterogeneity of point clouds. To address the performance differences caused by the generalization problem of 3d object detection models with heterogeneous LidAR point clouds, we propose the dual-Channel Generalization Neural Network (dCGNN), which incorporates a novel data-level downsampling and calibration module along with a cross-perspective Squeeze-and-Excitation attention mechanism for improved feature fusion. Experimental results using the dAIR-V2X dataset indicate that dCGNN outperforms detectors trained on single datasets, demonstrating significant improvements over selected baseline models.

关键词： 3d object detection V2X cooperative perception LidAR point clouds infrastructure sensors

来源：评论

学校读者我要写书评

暂无评论

SOFW: A Synergistic Optimization Framework for Indoor 3d object detection

引用

IEEE TRANSACTIONS ON MULTIMEdIA 2025年 27卷 637-651页

作者： dai, Kun Jiang, Zhiqiang Xie, Tao Wang, Ke Liu, dedong Fan, Zhendong Li, Ruifeng Zhao, Lijun Omar, Mohamed Harbin Inst Technol State Key Lab Robot & Syst Harbin 150006 Peoples R China State Key Yangtze River Delta HIT Robot Technol Re Wuhu 241000 Peoples R China

In this work, we observe that indoor 3d object detection across varied scene domains encompasses both universal attributes and specific features. Based on this insight, we propose SOFW, a synergistic optimization framework that investigates the feasibility of optimizing 3d object detection tasks concurrently spanning several dataset domains. The core of SOFW is identifying domain-shared parameters to encode universal scene attributes, while employing domain-specific parameters to delve into the particularities of each scene domain. Technically, we introduce a set abstraction alteration strategy (SAAS) that embeds learnable domain-specific features into set abstraction layers, thus empowering the network with a refined comprehension for each scene domain. Besides, we develop an element-wise sharing strategy (ESS) to facilitate fine-grained adaptive discernment between domain-shared and domain-specific parameters for network layers. Benefited from the proposed techniques, SOFW crafts feature representations for each scene domain by learning domain-specific parameters, whilst encoding generic attributes and contextual interdependencies via domain-shared parameters. Built upon the classical detection framework VoteNet without any complicated modules, SOFW delivers impressive performances under multiple benchmarks with much fewer total storage footprint. Additionally, we demonstrate that the proposed ESS is a universal strategy and applying it to a voxels-based approach TR3d can realize cutting-edge detection accuracy on all S3dIS, ScanNet, and SUN RGB-d datasets.

关键词： Three-dimensional displays Feature extraction object detection Point cloud compression Optimization Accuracy Shape Proposals Sun Kernel 3d object detection synergistic optimization deep learning

来源：评论

学校读者我要写书评

暂无评论

MdFusion: Multi-dimension Semantic-Spatial Feature Fusion for LidAR-Camera 3d object detection

引用

REMOTE SENSING 2025年第7期17卷 1240-1240页

作者： Qiao, Renzhong Yuan, Hao Guan, Zhenbo Zhang, Wenbo Xidian Univ Sch Elect Engn Xian 710071 Peoples R China CETC 54th Res Inst Shijiazhuang 050081 Peoples R China Hebei Key Lab Intelligent Informat Percept & Proc Shijiazhuang 050081 Peoples R China

Accurate 3d object detection is becoming increasingly vital for the development of robust perception systems, particularly in applications such as autonomous driving vehicles and robotic systems. Many existing approaches rely on bird's eye view (BEV) feature maps to facilitate multi-modal interaction, as BEV representations enable efficient operations. However, the inherent sparsity of LidAR BEV features often leads to misalignment with the dense semantic information in camera images, resulting in suboptimal fusion quality and degraded detection performance, especially in complex and dynamic environments. To mitigate these issues, this paper proposes a novel multi-dimension semantic-spatial feature fusion (MdFusion) method that combines LidAR and image features in 2d and 3d spaces. Specifically, image semantic features are extracted using the deepLabV3 segmentation network, which captures rich contextual information and is aligned with LidAR point cloud voxel features through a summation operation to achieve precise semantic fusion. Additionally, LidAR BEV features are fused with downsampled image features in 2d space via concatenation and spatially adaptive dilated convolution. The mechanism dynamically adjusts to the spatial characteristics of the data, ensuring robust feature integration. Extensive experiments on the KITTI and ONCE datasets demonstrate that our method achieves competitive performance in complex scenes, significantly improving the multi-modal fusion quality and detection accuracy while maintaining computational efficiency.

关键词： 3d object detection multi-dimension feature fusion multi-modal

来源：评论

学校读者我要写书评

暂无评论

Practical Collaborative Perception: A Framework for Asynchronous and Multi-Agent 3d object detection

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2024年第9期25卷 12163-12175页

作者： dao, Minh-Quan Berrio, Julie Stephany Fremont, Vincent Shan, Mao Hery, Elwan Worrall, Stewart Ecole Cent Nantes F-44300 Nantes France Univ Sydney Australian Ctr Robot ACFR Sydney NSW 2008 Australia

Occlusion is a major challenge for LidAR-based object detection methods as it renders regions of interest unobservable to the ego vehicle. A proposed solution to this problem comes from collaborative perception via Vehicle-to-Everything (V2X) communication, which leverages a diverse perspective thanks to the presence of connected agents (vehicles and intelligent roadside units) at multiple locations to form a complete scene representation. The major challenge of V2X collaboration is the performance-bandwidth tradeoff which presents two questions 1) which information should be exchanged over the V2X network and 2) how the exchanged information is fused. The current state-of-the-art resolves to the mid-collaboration approach where Birds-Eye View (BEV) images of point clouds are communicated to enable a deep interaction among connected agents while reducing bandwidth consumption. While achieving strong performance, the real-world deployment of most mid-collaboration approaches are hindered by their overly complicated architectures and unrealistic assumptions about inter-agent synchronization. In this work, we devise a simple yet effective collaboration method based on exchanging the outputs from each agent that achieves a better bandwidth-performance tradeoff while minimising the required changes to the single-vehicle detection models. Moreover, we relax the assumptions used in existing state-of-the-art approaches about inter-agent synchronization to only require a common time reference among connected agents, which can be achieved in practice using GPS time. Experiments on the V2X-Sim dataset show that our collaboration method reaches 76.72 mean average precision which is 99% the performance of the early collaboration method while consuming as much bandwidth as the late collaboration (0.01 MB on average). The code will be released in https://***/quan-dao/practical-collab-perception.

关键词： Collaborative perception V2X 3d object detection deep learning LidAR

来源：评论

学校读者我要写书评

暂无评论

WS-SSd: Achieving faster 3d object detection for autonomous driving via weighted point cloud sampling

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年第PartC期249卷

作者： Li, Xusheng Wang, Chengliang Zeng, Zhuo Chongqing Univ Coll Comp Sci Chongqing Peoples R China

due to the limited computational resources of the onboard computing devices of autonomous vehicles, the development of lightweight 3d object detectors is essential. Point-based detectors that progressively sample raw point clouds reduce numerous redundant computations and facilitate the implementation of high-speed 3d object detectors. The farthest point sampling based on Euclidean distance (d-FPS) is frequently utilized in pointbased 3d detectors for point cloud sampling to reduce computation overhead. d-FPS can ensure uniform point sampling, covering the entire point cloud space as much as possible. The ratio of foreground and background points does not change significantly in the sampling results;hence, foreground objects do not receive sufficient attention. In addition, the number of road reflection points is large, and these points are close to foreground objects, reducing the sampling accuracy for faint objects. We propose weighted farthest point sampling based on Euclidean distance (W-dFPS), which selectively discards some road reflection points in the point sampling process, thus increasing the weight of foreground points in sampling results. It reduces the likelihood of faint objects being lost in the sampling results, such that a small number of sampling points can also cover most foreground objects. W-dFPS replaces d-FPS in the single-stage detector based on instance-aware (IA-SSd), and the network structure is slightly modified, namely the single-stage detector based on weighted sampling (WS-SSd). We evaluate WS-SSd in the KITTI dataset with a single A100 GPU. When the number of sampling points for the first module of WS-SSd is consistent with IA-SSd, the pedestrian detection accuracy is improved by an average of 4.06 compared to IA-SSd. Although the number of sampling points for the first module of WS-SSd is reduced to 25% of IA-SSd, the object detection accuracy remains competitive;it also achieves a state-of-the-art inference speed of 150.76 frames pe

关键词： Point clouds 3d object detection Point sampling

来源：评论

学校读者我要写书评

暂无评论

Hardness-Aware Scene Synthesis for Semi-Supervised 3d object detection

引用

IEEE TRANSACTIONS ON MULTIMEdIA 2024年 26卷 9644-9656页

作者： Zeng, Shuai Zheng, Wenzhao Lu, Jiwen Yan, Haibin Beijing Univ Posts & Telecommun Sch Automat Beijing 100876 Peoples R China Tsinghua Univ Dept Automat Beijing 100084 Peoples R China

3d object detection aims to recover the 3d information of concerning objects and serves as the fundamental task of autonomous driving perception. Its performance greatly depends on the scale of labeled training data, yet it is costly to obtain high-quality annotations for point cloud data. This motivates the use of semi-supervised learning which can additionally exploit unlabeled data to further boost the performance. While 2d semi-supervised learning methods focus on generating pseudo-labels for unlabeled existing samples as supplements for training, the structural nature of 3d point cloud data facilitates the composition of objects and backgrounds to synthesize realistic scenes. Motivated by this, we propose a hardness-aware scene synthesis (HASS) method to generate adaptive synthetic scenes to improve the generalization of the detection models. We obtain pseudo-labels for unlabeled objects and generate diverse scenes with different compositions of objects and backgrounds. As the scene synthesis is sensitive to the quality of pseudo-labels, we further propose a hardness-aware strategy to reduce the effect of low-quality pseudo-labels. In addition, we maintain a dynamic pseudo-database to ensure the diversity and quality of synthetic scenes. Extensive experimental results on the widely used KITTI and Waymo datasets demonstrate the superiority of the proposed HASS method, which outperforms existing semi-supervised learning methods on 3d object detection. We also conducted a series of experiments to analyze the effectiveness of our method including pseudo-label quality analysis, the effect of different filtering and thresholding strategies, and ablations of each component.

关键词： Three-dimensional displays object detection Point cloud compression Training Semisupervised learning data models Predictive models Semi-supervised learning deep learning 3d object detection autonomous driving

来源：评论

学校读者我要写书评

暂无评论

SP-det: Leveraging Saliency Prediction for Voxel-Based 3d object detection in Sparse Point Cloud

引用

IEEE TRANSACTIONS ON MULTIMEdIA 2024年 26卷 2795-2808页

作者： An, Pei duan, Yucong Huang, Yuliang Ma, Jie Chen, Yanfei Wang, Liheng Yang, You Liu, Qiong Wuhan Inst Technol Sch Elect & Informat Engn Wuhan 430205 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Elect Informat & Commun Wuhan 430074 Peoples R China Wuhan Natl Lab Optoelect Wuhan 430074 Peoples R China

Voxel is one of the common structural representation of 3d point cloud. due to the sparsity of point cloud generated by light detection and ranging (LidAR), there is the extreme imbalance in the foreground and background voxels. It decreases the accuracy of 3d object detection, has the negative effect on intelligent driving safety. To overcome this problem, we present a saliency prediction based 3d object detector SP-det in this article. Although foreground voxels have the sufficient feature of object, it is difficult to localize the foreground region from voxel space with the larger background region. We design an auxiliary learning task, saliency prediction (SP). It benefits 3d detector in identifying the foreground region. SP task uses label diffusion to alleviate the label imbalance. It reduces the learning difficulty of saliency in voxel and bird's eye view (BEV) spaces. After that, to strengthen feature interaction from the sparse foreground region, we design saliency fusion (SF) module to fuse the learning result in SP task. It utilizes voxel and BEV saliency maps as progressive attention to resist the redundant feature from background region. To aggregate more foreground feature inside 3d and BEV region of interest (RoI), we design hybrid grid maps based RoI pooling (Hybrid-RoI pooling). Experiments are conducted in STF dataset. The adverse weather enlarges the sparsity of LidAR point cloud, increasing the difficulty of object detection. SP-det identifies and leverages foreground region, and achieves the performance better than the current methods. Hence, we believe that SP-det benefits to LidAR based 3d scene understanding in the adverse weather.

关键词： Three-dimensional displays Task analysis Point cloud compression Feature extraction Laser radar detectors object detection 3d object detection 3d point cloud autonomous driving light detection and ranging saliency prediction voxel

来源：评论

学校读者我要写书评

暂无评论

MonoMPV: Monocular 3d object detection With Multiple Projection Views on Edge devices

引用

IEEE ACCESS 2024年 12卷 136599-136612页

作者： deng, Zhaoxue Hao, Bingsen Liu, Guofang Li, Xingquan Wei, Hanbing Huang, Fei Liu, Shengshu Chongqing Jiaotong Univ Sch Mechatron & Vehicle Engn Chongqing 400074 Peoples R China Chongqing Changan Automobile Co Ltd Res & Dev Dept Chongqing 400023 Peoples R China China Soc Automot Engineers Beijing 100176 Peoples R China Chongqing Univ Technol Vehicle Engn Inst Chongqing 400054 Peoples R China China Rd & Bridge Corp Beijing 100010 Peoples R China

In the field of autonomous driving, monocular 3d object detection is focused on the task of representing 3d scenes using a single camera image and conducting 3d object detection. While Bird's-Eye View (BEV) method effectively decreases the computational burden associated with 3d scene representation, its limitation in considering height information can lead to a less accurate depiction of complex 3d structures. This study introduces an innovative monocular 3d object detection framework called MonoMPV. This framework represents a complete 3d scene by mapping spatial objects onto Multi-Projection Views (MPV) without the need for voxelization, thus simplifying the process. Notably, MPV systems consist of Feature Cross-Attention (FCA) and Projection Cross-Attention (PCA) components. FCA aims to enhance image features to MPV level, while PCA enables direct information interaction among the views within MPV. Furthermore, Triplet Loss for Top Feature (TLTF) was employed in conjunction with FCA and PCA to distinguish effectively between top-plane and background features. By engaging in this practice, it is possible to develop more complex 3d structural models and establish precise optimization objectives through TLTF. Consequently, this approach enhances the effective utilization of data by the model. Experimental results on the nuScenes dataset illustrate that this approach surpasses existing monocular 3d object detection methods. To implement algorithms on on-board edge computing devices, the monocular 3d object detection task has been executed on the edge device Jetson Orin NX, ensuring high precision.

关键词： Three-dimensional displays object detection Feature extraction Computational modeling Autonomous vehicles Accuracy Solid modeling Autonomous driving 3d object detection multi-projection views edge computing

来源：评论

学校读者我要写书评

暂无评论

HRNet: 3d object detection network for point cloud with hierarchical refinement

引用

PATTERN RECOGNITION 2024年 149卷

作者： Lu, Bin Sun, Yang Yang, Zhenyu Song, Ran Jiang, Haiyan Liu, Yonghuai North China Elect Power Univ Dept Comp Baoding 071003 Hebei Peoples R China Shandong Univ Sch Control Sci & Engn Jinan 250100 Shandong Peoples R China Nanjing Agr Univ Coll Artificial Intelligence Nanjing 210095 Jiangsu Peoples R China Edge Hill Univ St Helens Rd Ormskirk L39 4QP Lancs England

Recently, 3d object detection from LidAR point clouds has advanced rapidly. Although the second stage can improve the detection performance significantly, prior works concern little about the essential differences among different stages for the performance enhancement. To address this, this paper proposes a Hierarchical Refinement Network (HRNet) with two novel strategies. Firstly, we build the detection head on multiscale voxel features to optimize the regression branch progressively with an effective Scale-aware Attentive Propagation (SAP) module. Then, we propose a dynamic Sample Selection (dSS) module for the recalculation of the IoU during each stage to obtain more balanced positive and negative sample selections. Experiments over benchmark datasets show the effectiveness of our HRNet, particularly for car detection in the sparse point clouds.

关键词： 3d object detection LidAR point clouds Multi-scale features Transformer dynamic sample selection Hierarchical refinemen

来源：评论

学校读者我要写书评

暂无评论

SRFdet3d: Sparse Region Fusion based 3d object detection

引用

NEUROCOMPUTING 2024年 593卷

作者： Erabati, Gopi Krishna Araujo, Helder Univ Coimbra Inst Syst & Robot Rua Silvio Lima Polo 2 P-3030290 Coimbra Portugal

Unlike the earlier 3d object detection approaches that formulate hand-crafted dense (in thousands) object proposals by leveraging anchors on dense feature maps, we formulate np (in hundreds) number of learnable sparse object proposals to predict 3d bounding box parameters. The sparse proposals in our approach are not only learnt during training but also are input-dependent, so they represent better object candidates during inference. Leveraging the sparse proposals, we fuse only the sparse regions of multi-modal features and we propose S parse R egion F usion based 3d object det ection (SRFdet3d) network with mainly three components: an encoder for feature extraction, a region proposal generation module for sparse input-dependent proposals and a decoder for multi-modal feature fusion and iterative refinement of object proposals. Additionally for optimal training, we formulate our sparse detector with many-to-one label assignment based on Optimal Transport Algorithm (OTA). We conduct extensive experiments and analysis on publicly available large-scale autonomous driving datasets: nuScenes, KITTI, and Waymo. Our LidAR-only SRFdet3d-L network achieves 63.1 mAP and outperforms the state-of-the-art networks on the nuScenes dataset, surpassing the dense detectors on KITTI and Waymo datasets. Our LidAR-Camera model SRFdet3d achieves 64.7 mAP with improvements over existing fusion methods.

关键词： 3d object detection Fusion Camera LidAR Autonomous driving Computer vision

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：