Filters








15,698 Hits in 6.6 sec

Relation Graph Network for 3D Object Detection in Point Clouds [article]

Mingtao Feng, Syed Zulqarnain Gilani, Yaonan Wang, Liang Zhang and Ajmal Mian
2019 arXiv   pre-print
The proposed relation graph network consists of a 3D object proposal generation module and a 3D relation module, makes it an end-to-end trainable network for detecting 3D object in point clouds.  ...  However, their power has not been fully realised for detecting 3D objects in point clouds directly without converting them to regular grids.  ...  CONCLUSION We proposed a relation graph network for 3D object detection in point clouds.  ... 
arXiv:1912.00202v1 fatcat:eookfz7syjempkfvfe2fbhcenu

PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object Detection [article]

Yanan Zhang, Di Huang, Yunhong Wang
2020 arXiv   pre-print
LiDAR-based 3D object detection is an important task for autonomous driving and current approaches suffer from sparse and partial point clouds of distant and occluded objects.  ...  On the other hand, a graph neural network module is designed, which comprehensively captures relations among points through a local-global attention mechanism as well as multi-scale graph based context  ...  To the best of our knowledge, this is the first study that considers point cloud refinement in 3D object detection. • We design a new graph neural network (AMS-GNN) module, which strengths the structure  ... 
arXiv:2012.10412v3 fatcat:sku7ehn5xrbzxlpxsn6fm7ue7i

Angle Based Feature Learning in GNN for 3D Object Detection using Point Cloud [article]

Md Afzal Ansari, Md Meraz, Pavan Chakraborty, Mohammed Javed
2021 arXiv   pre-print
In this paper, we present new feature encoding methods for Detection of 3D objects in point clouds.  ...  We used a graph neural network (GNN) for Detection of 3D objects namely cars, pedestrians, and cyclists. Feature encoding is one of the important steps in Detection of 3D objects.  ...  Related Work In the literature, few studies specifically focused on the Detection of 3D objects using Point Clouds using Graph Neural Networks.  ... 
arXiv:2108.00780v1 fatcat:qspbwd7q45cujd76cw4vq4i2oi

Deep Learning for 3D Point Clouds: A Survey [article]

Yulan Guo, Hanyun Wang, Qingyong Hu, Hao Liu, Li Liu, Mohammed Bennamoun
2020 arXiv   pre-print
It covers three major tasks, including 3D shape classification, 3D object detection and tracking, and 3D point cloud segmentation.  ...  However, deep learning on point clouds is still in its infancy due to the unique challenges faced by the processing of point clouds with deep neural networks.  ...  [125] proposed a graph neural network Point-GNN to detect 3D objects from lidar point clouds.  ... 
arXiv:1912.12033v2 fatcat:qiiyvvuulfccxaiihf2mu23k34

SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Clouds [article]

Qingdong He, Zhengning Wang, Hao Zeng, Yi Zeng, Yijun Liu
2021 arXiv   pre-print
Accurate 3D object detection from point clouds has become a crucial component in autonomous driving.  ...  Experiments on KITTI detection benchmark demonstrate the efficiency of extending the graph representation to 3D object detection and the proposed SVGA-Net can achieve decent detection accuracy.  ...  Graph neural network for 3d object detection in a point cloud.  ... 
arXiv:2006.04043v2 fatcat:p4jzhx74pnclpdgkh4uo7hrbwy

Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review [article]

Ying Li, Lingfei Ma, Zilong Zhong, Fei Liu, Dongpu Cao, Jonathan Li, Michael A. Chapman
2020 arXiv   pre-print
Although several published research papers focus on specific topics in computer vision for autonomous vehicles, to date, no general survey on deep learning applied in LiDAR point clouds for autonomous  ...  In this paper, we provide a systematic review of existing compelling deep learning architectures applied in LiDAR point clouds, detailing for specific tasks in autonomous driving such as segmentation,  ...  Besides, we also would like to thank anonymous reviewers for their insightful comments and suggestions.  ... 
arXiv:2005.09830v1 fatcat:zrja5sgtsvgulpnp7p7t4kxq54

PnP-3D: A Plug-and-Play for 3D Point Clouds [article]

Shi Qiu, Saeed Anwar, Nick Barnes
2021 arXiv   pre-print
To improve the effectiveness of existing networks in analyzing point cloud data, we propose a plug-and-play module, PnP-3D, aiming to refine the fundamental point cloud feature representations by involving  ...  With the help of the deep learning paradigm, many point cloud networks have been invented for visual analysis.  ...  Ghanem, “2d-driven 3d object detection in rgb-d and J. Kautz, “Splatnet: Sparse lattice networks for point cloud images,” in ICCV, 2017, pp. 4622–4630.  ... 
arXiv:2108.07378v2 fatcat:atpotz75ujg3rbcgm3qhkd72ay

Deep Learning on Point Clouds and Its Application: A Survey

Weiping Liu, Jia Sun, Wanyi Li, Ting Hu, Peng Wang
2019 Sensors  
The applications related to point cloud feature learning, including 3D object classification, semantic segmentation, and 3D object detection, are introduced, and the datasets and evaluation metrics are  ...  In this paper, the recent existing point cloud feature learning methods are classified as point-based and tree-based. The former directly takes the raw point cloud as the input for deep learning.  ...  Acknowledgments: The authors own many thanks to the anonymous reviewers for their instructive comments. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s19194188 fatcat:s64jm5t5xbhzjk7jxgrodehucu

3D Point Cloud Processing and Learning for Autonomous Driving [article]

Siheng Chen and Baoan Liu and Chen Feng and Carlos Vallespi-Gonzalez and Carl Wellington
2020 arXiv   pre-print
As one of the most important sensors in autonomous vehicles, light detection and ranging (LiDAR) sensors collect 3D point clouds that precisely record the external surfaces of objects and scenes.  ...  We present a review of 3D point cloud processing and learning for autonomous driving.  ...  Inspired by the success of graph neural networks in social network analysis, numerous recent research incorporate graph neural networks to handle a 3D point cloud.  ... 
arXiv:2003.00601v1 fatcat:w3sxkiupo5avhlbrstugqkohqy

Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud [article]

Weijing Shi, Ragunathan Rajkumar
2020 arXiv   pre-print
In this paper, we propose a graph neural network to detect objects from a LiDAR point cloud. Towards this end, we encode the point cloud efficiently in a fixed radius near-neighbors graph.  ...  Our results demonstrate the potential of using the graph neural network as a new approach for 3D object detection. The code is available https://github.com/WeijingShi/Point-GNN.  ...  However, little research has looked into using a graph neural network for the 3D object detection in a point cloud.  ... 
arXiv:2003.01251v1 fatcat:jo2mgerobnbjlmecnqhoiujjvi

LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attention [article]

Junbo Yin, Jianbing Shen, Chenye Guan, Dingfu Zhou, Ruigang Yang
2020 arXiv   pre-print
Existing LiDAR-based 3D object detectors usually focus on the single-frame detection, while ignoring the spatiotemporal information in consecutive point cloud frames.  ...  In this paper, we propose an end-to-end online 3D video object detector that operates on point cloud sequences.  ...  Related Work LiDAR-based 3D Object Detection.  ... 
arXiv:2004.01389v1 fatcat:i46zosrmynabrl66egkeqnrr64

Dynamic Edge Weights in Graph Neural Networks for 3D Object Detection [article]

Sumesh Thakur, Jiju Peethambaran
2020 arXiv   pre-print
Traditionally, a majority of 3D object detection algorithms focus on processing 3D point clouds using voxel grids or bird's eye view (BEV).  ...  Recent works, however, demonstrate the utilization of the graph neural network (GNN) as a promising approach to 3D object detection.  ...  Graph Attention Networks for 3D Object Detection In this section, we discuss the proposed approach to detect 3D objects from LiDAR scans.  ... 
arXiv:2009.08253v1 fatcat:hhhofo6bgjetvih6s2ndnk42xe

Relation3DMOT: Exploiting Deep Affinity for 3D Multi-Object Tracking from View Aggregation [article]

Can Chen, Luca Zanotti Fragonara, Antonios Tsourdos
2020 arXiv   pre-print
However, many approaches detect objects in 2D RGB sequences for tracking, which is lack of reliability when localizing objects in 3D space.  ...  Autonomous systems need to localize and track surrounding objects in 3D space for safe motion planning. As a result, 3D multi-object tracking (MOT) plays a vital role in autonomous navigation.  ...  We summarize our contributions as: • We represent the detected objects as the nodes in a directed graph and propose a graph neural network to exploit discriminative features for the objects in the adjacent  ... 
arXiv:2011.12850v1 fatcat:ewh3c2arajegdgxobvlspcfskq

TearingNet: Point Cloud Autoencoder to Learn Topology-Friendly Representations [article]

Jiahao Pang, Duanshun Li, Dong Tian
2021 arXiv   pre-print
Particularly, the Tearing network module learns the point cloud topology explicitly.  ...  By breaking the edges of a primitive graph, it tears the graph into patches or with holes to emulate the topology of a target point cloud, leading to faithful reconstructions.  ...  The torn graph also enables us to resample the input 3D point cloud by resampling 2D points in manifold M while avoiding the "ghost" 3D points between different objects or within object holes.  ... 
arXiv:2006.10187v4 fatcat:jgsvduocmnbktejybm6x622ivq

Relation3DMOT: Exploiting Deep Affinity for 3D Multi-Object Tracking from View Aggregation

Can Chen, Luca Zanotti Zanotti Fragonara, Antonios Tsourdos
2021 Sensors  
However, many approaches detect objects in 2D RGB sequences for tracking, which lacks reliability when localizing objects in 3D space.  ...  Autonomous systems need to localize and track surrounding objects in 3D space for safe motion planning. As a result, 3D multi-object tracking (MOT) plays a vital role in autonomous navigation.  ...  • We represent the detected objects as the nodes in a directed acyclic graph and propose a graph neural network to exploit the discriminative features of the objects in the adjacent frames for 3D MOT  ... 
doi:10.3390/s21062113 pmid:33803021 pmcid:PMC8002739 fatcat:a3tmunoienfj3ldp63hj5wxxxy
« Previous Showing results 1 — 15 out of 15,698 results