Stereo priori RCNN based car detection on point level for autonomous driving

Tao, Chongben; He, Haotian; Xu, Fenglei; Cao, JieCheng

doi:10.1016/j.knosys.2021.107346

Cited by 25 publications

(8 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In rainy conditions, the quality of LiDAR point clouds is noticeably affected due to several reasons: (1) The presence of raindrops leads to scattering and absorption of the laser beam in the atmosphere, resulting in a reduction of beam intensity. This may cause a weakening of the received signal by the LiDAR, lowering sensitivity and detectable range.…”

Section: Results Of the Nuscenes Datasetmentioning

confidence: 99%

“…One significant task within this domain is to accurately acquire 3D positional and classification information of surrounding objects for vehicles under complex weather conditions and road environments. Currently, numerous 3D detection algorithms employ deep learning methods to extract features from images [1][2][3][4][5][6], point clouds [7][8][9][10][11][12], and fusion data [13][14][15][16][17][18][19][20], achieving remarkable results on commonly used public datasets [21][22][23]. However, the data acquired during the vehicle's travel exhibits spatiotemporal continuity, and existing methods predominantly focus on single-frame data, neglecting to fully exploit the semantic correlations between historical information.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Section: Results Of the Nuscenes Datasetmentioning

confidence: 99%

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

show abstract

“…The outcomes indicate that this algorithm can effectively extract the important boundaries of the spacecraft and filter out background information and noise. A point level vehicle detection method based on three-dimensional prior cyclic CNN for automatic driving was proposed by Tao C et al [ 11 ]. in the study, which combines traditional Regional Proposal Network (RPN) and Mask-branch mechanism.…”

Section: Related Workmentioning

confidence: 99%

Traffic flow detection method based on improved SSD algorithm for intelligent transportation system

Su,

Shu

2024

PLoS ONE

View full text Add to dashboard Cite

With the development of the new generation communication system in China, the application of intelligent transportation system is more extensive, which brings higher demands for vehicle flow detection and monitoring. Traditional traffic flow detection modes often cannot meet the high statistical accuracy requirement and high-speed detection simultaneously. Therefore, an improved Inception module is integrated into the single shot multi box detector algorithm. An intelligent vehicle flow detection model is constructed based on the improved single shot multi box detector algorithm. According to the findings, the convergence speed of the improved algorithm was the fastest. When the test sample was the entire test set, the accuracy and precision values of the improved method were 93.6% and 96.0%, respectively, which were higher than all comparison target detection algorithms. The experimental results of traffic flow statistics showed that the model had the highest statistical accuracy, which converged during the training phase. During the testing phase, except for manual statistics, all methods had the lowest statistical accuracy on motorcycles. The average accuracy and precision of the designed model for various types of images were 96.9% and 96.8%, respectively. The calculation speed of this intelligent model was not significantly improved compared to the other two intelligent models, but it was significantly higher than manual monitoring methods. Two experimental data demonstrate that the intelligent vehicle flow detection model designed in this study has higher detection accuracy. The calculation speed has no significant difference compared with the traditional method, which is helpful to the traffic flow management in intelligent transportation system.

show abstract

“…Automatic driving vehicles require the accurate detection of surrounding objects to enable appropriate planning from subsequent decision-making algorithms. In recent years, deep-learning-based object detection algorithms [1][2][3][4][5][6][7][8][9] have achieved remarkable results, and many publicly available datasets have been used to evaluate algorithm performance. These models often rely on supervised training on large-scale datasets with ground truth annotations.…”

Section: Introductionmentioning

confidence: 99%

An Object Detection Method Based on Feature Uncertainty Domain Adaptation for Autonomous Driving

Zhu

et al. 2023

Applied Sciences

Self Cite

View full text Add to dashboard Cite

The environment perception algorithm in autonomous driving is trained in the source domain, leading to domain drift and reduced detection accuracy in the target domain due to shifts in background feature distribution. To address this issue, a domain adaptive object detection algorithm based on feature uncertainty is proposed, which can improve the detection performance of object detection algorithms in unlabeled data. Firstly, a local alignment module based on channel information is proposed, which can obtain the model’s uncertainty about different domain data based on the feature channels obtained through the feature extraction network, achieving adaptive dynamic local alignment. Secondly, an instance-level alignment module guided by local feature uncertainty is proposed, which can obtain the corresponding instance-level uncertainty through ROI mapping. To improve the domain invariance of bounding box regression, a multi-class, multi-regression instance-level uncertainty alignment module is proposed, which can achieve spatial decoupling of classification and regression tasks, further improving the model’s domain adaptive ability. Finally, the effectiveness of the proposed algorithm is validated on Cityscapes, KITTI, and real vehicle data.

show abstract

Stereo priori RCNN based car detection on point level for autonomous driving

Cited by 25 publications

References 27 publications

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

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

Traffic flow detection method based on improved SSD algorithm for intelligent transportation system

An Object Detection Method Based on Feature Uncertainty Domain Adaptation for Autonomous Driving

Contact Info

Product

Resources

About