RTL3D: real‐time LIDAR‐based 3D object detection with sparse CNN

Lin, Yan; Li, Kai; Belyaev, Evgeny; Duan, Meiyu

doi:10.1049/iet-cvi.2019.0508

Cited by 8 publications

(9 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methods can be categorised into the following categories: (1) pointbased methods [1][2][3][4][5][6][7][8][9][10] that directly operate 3D points and output semantic information. (2) Voxel-based methods [11][12][13][14][15][16][17][18] that voxelise point clouds into 3D grids and then use 3D CNNs to process these 3D grids. (3) Point-Voxelbased methods [19][20][21][22] that combine point-based method and voxel-based method together to process point clouds.…”

Section: Introductionmentioning

confidence: 99%

Sparse point‐voxel aggregation network for efficient point cloud semantic segmentation

Fang

Xiong

Liu

2022

IET Computer Vision

View full text Add to dashboard Cite

Effective and efficient semantic segmentation of 3D point cloud data is important for many tasks. Many methods for point cloud semantic segmentation rely on computationally expensive sampling and grouping layers to process irregular points, while others convert irregular points into regular volumetric grids and process them with a 3D U-Netbased semantic segmentation network. However, most of these methods suffer from high computational costs and cannot be applied to the real-time processing of large-scale point clouds. To address these issues, we propose a computationally efficient point-voxel-based network architecture named Sparse Point-Voxel Aggregation Network (SPVAN) for point cloud semantic segmentation. It consists of an encoding layer that consists of sparse convolution and MLP layers and a new decoding layer called Point Feature Aggregation Layer (PFAL) that is only composed of feature interpolation and MLP layers. Compared with recent popular point-voxel-based methods with the U-Net-based network, our method does not need 3D convolution networks in the decoding layer and thus achieves a higher speed. Experimental results on the large-scale SemanticKITTI dataset show that our method gets a good balance between the efficiency and the performance. Moreover, our method achieves on-par or better performance than previous methods for semantic segmentation on the challenging S3DIS dataset.

show abstract

Section: Introductionmentioning

confidence: 99%

Sparse point‐voxel aggregation network for efficient point cloud semantic segmentation

Fang

Xiong

Liu

2022

IET Computer Vision

View full text Add to dashboard Cite

show abstract

“…Light detection and ranging (LiDAR) system is one of the technologies that use 3D detection techniques [6]. However, LiDAR systems had been replaced gradually by the rising of outstanding depth sensors such as Microsoft Kinect.…”

Section: Introductionmentioning

confidence: 99%

A Real-Time Distance Prediction via Deep Learning and Microsoft Kinect

Tham

Hussin

Ismail

2022

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

3D(Dimension) understanding has become the herald of computer vision and graphics research in the era of technology. It benefits many applications such as autonomous cars, robotics, and medical image processing. The pros and cons of 3D detection bring convenience to the human community instead of 2D detection. The 3D detection consists of RGB (Red, Green and Blue) colour images and depth images which are able to perform better than 2D in real. The current technology is relying on the high costing light detection and ranging (LiDAR). However, the use of Microsoft Kinect has replaced the LiDAR systems for 3D detection gradually. In this project, a Kinect camera is used to extract the depth of image information. From the depth images, the distance can be defined easily. As in the colour scale, the red colour is the nearest and the blue colour is the farthest. The depth image will turn black when reaching the limitation of the Kinect camera measuring range. The depth information collected will be trained with deep learning architecture to perform a real-time distance prediction.

show abstract

“…Point cloud is a generic and most widely used representation of 3D data that has drawn increasing popularity in a broad range of applications, for example, robotic mapping, autonomous vehicle, and navigation [1][2][3]. With the popularity of the range sensors, for example, Kinect, Lidar, radar, semantic understanding of point cloud is a foundational application for robotics and automotive [4][5][6]. Unlike 2D image, 3D point cloud is a set of unstructured and unordered points of non-unified numbers, which makes the existing 2D methods less effective in representation and learning.…”

Section: Introductionmentioning

confidence: 99%

Long short‐distance topology modelling of 3D point cloud segmentation with a graph convolution neural network

Zhang

Hong

et al. 2022

IET Computer Vision

View full text Add to dashboard Cite

3D point cloud segmentation is a non-trivial problem due to its irregular, sparse, and unordered data structure. Existing methods only consider structural relationships of a 3D point and its spatial neighbours. However, the inner-point interactions and long-distance context of a 3D point cloud have been less investigated. In this study, we propose an effective plug-and-play module called the Long Short-Distance Topologically Modelled (LSDTM) Graph Convolutional Neural Network (GCNN) to learn the underlying structure of 3D point clouds. Specifically, we introduce the concept of subgraph to model the contextual-point relationships within a short distance. Then the proposed topology can be reconstructed by recursive aggregation of subgraphs, and importantly, to propagate the contextual scope to a long range. The proposed LSDTM can parse the point cloud data with maximisation of preserving the geometric structure and contextual structure, and the topological graph can be trained end-to-end through a seamlessly integrated GCNN. We provide a case study of triple-layer ternary topology and experimental results on ShapeNetPart, Stanford 3D Indoor Semantics and ScanNet datasets, indicating a significant improvement on the task of 3D point cloud segmentation and validating the effectiveness of our research.

show abstract

RTL3D: real‐time LIDAR‐based 3D object detection with sparse CNN

Cited by 8 publications

References 45 publications

Sparse point‐voxel aggregation network for efficient point cloud semantic segmentation

Sparse point‐voxel aggregation network for efficient point cloud semantic segmentation

A Real-Time Distance Prediction via Deep Learning and Microsoft Kinect

Long short‐distance topology modelling of 3D point cloud segmentation with a graph convolution neural network

Contact Info

Product

Resources

About