Structure Aware Single-Stage 3D Object Detection From Point Cloud

He, Chenhang; Zeng, Hui; Huang, Jianqiang; Hua, Xian-Sheng; Zhang, Lei

doi:10.1109/cvpr42600.2020.01189

Cited by 539 publications

(283 citation statements)

References 19 publications

Supporting

Mentioning

245

Contrasting

Order By: Relevance

“…3D voxel CNN and proposal generation. Voxel CNN with 3D sparse convolution [61], [81] is a popular choice of stateof-the-art 3D detectors [16], [24], [83] [3] is appended to this bird-view feature maps for high quality 3D proposal generation. As shown in Table 1, our adopted 3D voxel CNN backbone with anchor-based scheme achieves higher recall performance than the PointNet-based approaches, which establishes a strong backbone network and generates robust proposal boxes for the following proposal refinement stage.…”

Section: Preliminariesmentioning

confidence: 99%

PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection

Shi

Guo²,

Jiang³

et al. 2020

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

1,580

1,045

View full text Add to dashboard Cite

3D object detection is receiving increasing attention from both industry and academia thanks to its wide applications in various fields. In this paper, we propose the Point-Voxel Region based Convolution Neural Networks (PV-RCNNs) for accurate 3D detection from point clouds. First, we propose a novel 3D object detector, PV-RCNN-v1, which employs the voxel-to-keypoint scene encoding and keypoint-to-grid RoI feature abstraction two novel steps. These two steps deeply incorporate both 3D voxel CNN and PointNet-based set abstraction for learning discriminative point-cloud features. Second, we propose a more advanced framework, PV-RCNN-v2, for more efficient and accurate 3D detection. It consists of two major improvements, where the first one is the sectorized proposal-centric strategy for efficiently producing more representative and uniformly distributed keypoints, and the second one is the VectorPool aggregation to replace set abstraction for better aggregating local point-cloud features with much less resource consumption. With these two major modifications, our PV-RCNN-v2 runs more than twice as fast as the v1 version while still achieving better performance on the large-scale Waymo Open Dataset with 150m × 150m detection range. Extensive experiments demonstrate that our proposed PV-RCNNs significantly outperform previous state-of-the-art 3D detection methods on both the Waymo Open Dataset and the highly-competitive KITTI benchmark.

show abstract

Section: Preliminariesmentioning

confidence: 99%

PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection

Shi

Guo²,

Jiang³

et al. 2020

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

1,580

1,045

View full text Add to dashboard Cite

show abstract

“…To enhance our method's accuracy, the pointwise feature was introduced to the network. Referenced by the SA-SSD [31], the pointwise feature learning network was set as an auxiliary network that only works during training, does not play a role in predicting, avoiding additional computational overhead caused by the additional feature extracting. e penultimate layer of the neck network was set as the former feature extraction layer of the auxiliary network, which is ultimately a voxelwise category prediction network.…”

Section: Head Networkmentioning

confidence: 99%

Combined Auxiliary Networks and Bird’s Eye View Method for Real-Time Multicategory Object Recognition

Gong

Wei

Guoye

et al. 2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Object recognition based on LIDAR data is crucial in automotive driving and is the subject of extensive research. However, the lack of accuracy and stability in complex environments obstructs the practical application of real-time recognition algorithms. In this study, we proposed a new real-time network for multicategory object recognition. The manually extracted bird’s eye view (BEV) features were adopted to replace the resource-consuming 3D convolutional operation. Besides the subject network, we designed two auxiliary networks to help the network learn the pointwise features and boxwise features, aiming to improve the category and bounding boxes’ accuracy. The KITTI dataset was adopted to train and validate the proposed network. Experimental results showed that, for hard mode, the total average precision (AP) of the category reached 97.4%. For an intersection over a union threshold of 0.5 and 0.7, the total AP of regression reached 93.2% and 85.5%; especially, the AP of car’s regression reached 95.7% and 92.2%. The proposed network also showed consistent performance in the Apollo dataset with a processing duration of 37 ms. The proposed network exhibits stable and robust object recognition performance in complex environments (multiobject, unordered objects, and multicategory). And it shows sensitivity to occlusion of the LIDAR system and insensitivity to close large objects. The proposed multifunction method simultaneously achieves real-time operation, high accuracy, and stable performance, indicating its great potential value in practical application.

show abstract

“…To effectively encode the structural knowledge in SEAM, we employ the similar penalty in SA-SSD [15] for center regression. Given a training pair {x, y}, where x and y are the input observation and its ground-truth segments respectively, the network outputs both the key representation k in SEAM and the predicted segment maskŷ.…”

Section: Learning Criteriamentioning

confidence: 99%

Structure-Enhanced Attentive Learning For Spine Segmentation From Ultrasound Volume Projection Images

Zhao

Huang

Liu

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Automatic spine segmentation, based on ultrasound volume projection imaging (VPI), is of great value in clinical applications to diagnose scoliosis in teenagers. In this paper, we propose a novel framework to improve the segmentation accuracy on spine images via structure-enhanced attentive learning. Since the spine bones contain strong prior knowledge of their shapes and positions in ultrasound VPI images, we propose to encode this information into the semantic representations in an attentive manner. We first revisit the self-attention mechanism in representation learning, and then present a strategy to introduce the structural knowledge into the key representation in self-attention. By this means, the network explores both the contextual and structural information in the learned features, and consequently improves the segmentation accuracy. We conduct various experiments to demonstrate that our proposed method achieves promising performance on spine image segmentation, which shows great potential in clinical diagnosis.

show abstract

Structure Aware Single-Stage 3D Object Detection From Point Cloud

Cited by 539 publications

References 19 publications

PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection

PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection

Combined Auxiliary Networks and Bird’s Eye View Method for Real-Time Multicategory Object Recognition

Structure-Enhanced Attentive Learning For Spine Segmentation From Ultrasound Volume Projection Images

Contact Info

Product

Resources

About