Dynamic Multitarget Detection Algorithm of Voxel Point Cloud Fusion Based on PointRCNN

Luo, Xizhao; Zhou, Feng; Tao, Chongben; Yang, Anjia; Zhang, Peiyun; Chen, Yonghua

doi:10.1109/tits.2022.3176390

Cited by 12 publications

(5 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This section calculates the correlation values between point cloud features and image features. The specific calculation formula is shown in Equations ( 6) and (7).…”

Section: Calculating the Correlation Valuesmentioning

confidence: 99%

See 1 more Smart Citation

3D Object Detection under Urban Road Traffic Scenarios Based on Dual-Layer Voxel Features Fusion Augmentation

Jiang,

Ren,

2024

Sensors

View full text Add to dashboard Cite

To enhance the accuracy of detecting objects in front of intelligent vehicles in urban road scenarios, this paper proposes a dual-layer voxel feature fusion augmentation network (DL-VFFA). It aims to address the issue of objects misrecognition caused by local occlusion or limited field of view for targets. The network employs a point cloud voxelization architecture, utilizing the Mahalanobis distance to associate similar point clouds within neighborhood voxel units. It integrates local and global information through weight sharing to extract boundary point information within each voxel unit. The relative position encoding of voxel features is computed using an improved attention Gaussian deviation matrix in point cloud space to focus on the relative positions of different voxel sequences within channels. During the fusion of point cloud and image features, learnable weight parameters are designed to decouple fine-grained regions, enabling two-layer feature fusion from voxel to voxel and from point cloud to image. Extensive experiments on the KITTI dataset demonstrate the significant performance of DL-VFFA. Compared to the baseline network Second, DL-VFFA performs better in medium- and high-difficulty scenarios. Furthermore, compared to the voxel fusion module in MVX-Net, the voxel feature fusion results in this paper are more accurate, effectively capturing fine-grained object features post-voxelization. Through ablative experiments, we conducted in-depth analyses of the three voxel fusion modules in DL-VFFA to enhance the performance of the baseline detector and achieved superior results.

show abstract

“…This section calculates the correlation values between point cloud features and image features. The specific calculation formula is shown in Equations ( 6) and (7).…”

Section: Calculating the Correlation Valuesmentioning

confidence: 99%

“…With the rapid development of deep learning technology, many classical multimodal fusion frameworks have emerged in recent years [ 5 , 6 , 7 , 8 ]. Multi-view 3D networks (MV3D) [ 9 ] takes in the front view of the laser point cloud, the bird’s-eye view of the laser point cloud, and an RGB image for feature extraction.…”

Section: Introductionmentioning

confidence: 99%

3D Object Detection under Urban Road Traffic Scenarios Based on Dual-Layer Voxel Features Fusion Augmentation

Jiang,

Ren,

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Within the LiDAR-based models, there are two further subdivisions: those that convert 3D point clouds to images/voxels, and those that operate directly on raw data. Extensive research has been conducted in each of these areas, utilizing traditional data-processing methods as well as machine learning [18], deep learning [19,20], and swarm intelligence-based approaches [21,22].…”

Section: Related Workmentioning

confidence: 99%

Denoising and Reducing Inner Disorder in Point Clouds for Improved 3D Object Detection in Autonomous Driving

Wang

Jin

et al. 2023

Electronics

Self Cite

View full text Add to dashboard Cite

In the field of autonomous driving, precise spatial positioning and 3D object detection have become increasingly critical due to advancements in LiDAR technology and its extensive applications. Traditional detection models for RGB images face challenges in handling the intrinsic disorder present in LiDAR point clouds. Although point clouds are typically perceived as irregular and disordered, an implicit order actually exists, owing to laser arrangement and sequential scanning. Therefore, we propose Frustumformer, a novel framework that leverages the inherent order of LiDAR point clouds, reducing disorder and enhancing representation. Our approach consists of a frustum-based method that relies on the results of a 2D image detector, a frustum patch embedding that exploits the new data representation format, and a single-stride transformer network for original resolution feature fusion. By incorporating these components, Frustumformer effectively exploits the intrinsic order of point clouds and models long-range dependencies to further improve performance. Ablation studies verify the efficacy of the single-stride transformer component and the overall model architecture. We conduct experiments on the KITTI dataset, and Frustumformer outperforms existing methods.

show abstract

“…In addition, the huge amount of raw point clouds significantly escalates the computational demands of the model, posing challenges in meeting real-time requirements. Several methods [7,11,45] employ the Farthest Point Sampling (FPS) to acquire a fixed number of key points. However, key points obtained through FPS-based algorithms often include numerous background points, introducing irrelevant background features into the model training process.…”

Section: Introductionmentioning

confidence: 99%

DS-Trans: A 3D Object Detection Method Based on a Deformable Spatiotemporal Transformer for Autonomous Vehicles

Zhu,

Xu,

Tao

et al. 2024

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Facing the significant challenge of 3D object detection in complex weather conditions and road environments, existing algorithms based on single-frame point cloud data struggle to achieve desirable results. These methods typically focus on spatial relationships within a single frame, overlooking the semantic correlations and spatiotemporal continuity between consecutive frames. This leads to discontinuities and abrupt changes in the detection outcomes. To address this issue, this paper proposes a multi-frame 3D object detection algorithm based on a deformable spatiotemporal Transformer. Specifically, a deformable cross-scale Transformer module is devised, incorporating a multi-scale offset mechanism that non-uniformly samples features at different scales, enhancing the spatial information aggregation capability of the output features. Simultaneously, to address the issue of feature misalignment during multi-frame feature fusion, a deformable cross-frame Transformer module is proposed. This module incorporates independently learnable offset parameters for different frame features, enabling the model to adaptively correlate dynamic features across multiple frames and improve the temporal information utilization of the model. A proposal-aware sampling algorithm is introduced to significantly increase the foreground point recall, further optimizing the efficiency of feature extraction. The obtained multi-scale and multi-frame voxel features are subjected to an adaptive fusion weight extraction module, referred to as the proposed mixed voxel set extraction module. This module allows the model to adaptively obtain mixed features containing both spatial and temporal information. The effectiveness of the proposed algorithm is validated on the KITTI, nuScenes, and self-collected urban datasets. The proposed algorithm achieves an average precision improvement of 2.1% over the latest multi-frame-based algorithms.

show abstract

Dynamic Multitarget Detection Algorithm of Voxel Point Cloud Fusion Based on PointRCNN

Cited by 12 publications

References 52 publications

3D Object Detection under Urban Road Traffic Scenarios Based on Dual-Layer Voxel Features Fusion Augmentation

3D Object Detection under Urban Road Traffic Scenarios Based on Dual-Layer Voxel Features Fusion Augmentation

Denoising and Reducing Inner Disorder in Point Clouds for Improved 3D Object Detection in Autonomous Driving

DS-Trans: A 3D Object Detection Method Based on a Deformable Spatiotemporal Transformer for Autonomous Vehicles

Contact Info

Product

Resources

About