Progressive Framework of Learning 3D Object Classes and Orientations from Deep Point Cloud Representation

Background: While detecting the object directly from the 3D point cloud, the natural 3D patterns and invariance of 3D data are often obscure. Objective: In this work, we aimed at studying the 3D object detection from discrete, disordered and sparse 3D point clouds. Methods: The CNN is composed of the frustum sequence module, 3D instance segmentation module S-NET, 3D point cloud transformation module T-NET, and 3D boundary box estimation module E-NET. The search space of the object is determined by the frustum sequence module. The instance segmentation of the point cloud is performed by the 3D instance segmentation module. The 3D coordinates of the object are confirmed by the transformation module and the 3D bounding box estimation module. Results: Evaluated on KITTI benchmark dataset, our method outperforms the state of the art by remarkable margins while having real-time capability. Conclusion: We achieve real-time 3D object detection by proposing an improved convolutional neural network (CNN) based on image-driven point clouds.

Download Full-text

PointDCCNet: 3D Object Categorization Network using Point Cloud Decomposition

10.1109/cvprw53098.2021.00249 ◽

2021 ◽

Author(s):

Siddharth Katageri ◽

Sameer Kulmi ◽

Ramesh Ashok Tabib ◽

Uma Mudenagudi

Keyword(s):

Point Cloud ◽

Object Categorization ◽

3D Object

Download Full-text

Camera Relocalization using Deep Point Cloud Generation and Hand-crafted Feature Refinement

10.1109/icra48506.2021.9561289 ◽

2021 ◽

Author(s):

Wang Junyi ◽

Qi Yue

Keyword(s):

Point Cloud ◽

Deep Point

Download Full-text

DSP-Net: Dense-to-Sparse Proposal Generation Approach for 3D Object Detection on Point Cloud

10.1109/ijcnn52387.2021.9534412 ◽

2021 ◽

Author(s):

Xinrui Yan ◽

Yuhao Huang ◽

Shitao Chen ◽

Zhixiong Nan ◽

Jingmin Xin ◽

...

Keyword(s):

Object Detection ◽

Point Cloud ◽

3D Object ◽

3D Object Detection

Download Full-text

3D-GIoU: 3D Generalized Intersection over Union for Object Detection in Point Cloud

Sensors ◽

10.3390/s19194093 ◽

2019 ◽

Vol 19 (19) ◽

pp. 4093 ◽

Cited By ~ 7

Author(s):

Jun Xu ◽

Yanxin Ma ◽

Songhua He ◽

Jiahua Zhu

Keyword(s):

Object Detection ◽

Point Cloud ◽

Pedestrian Detection ◽

Three Dimensional ◽

Average Precision ◽

3D Object ◽

Automatic Driving ◽

3D Computer Vision ◽

High Level ◽

3D Object Detection

Three-dimensional (3D) object detection is an important research in 3D computer vision with significant applications in many fields, such as automatic driving, robotics, and human–computer interaction. However, the low precision is an urgent problem in the field of 3D object detection. To solve it, we present a framework for 3D object detection in point cloud. To be specific, a designed Backbone Network is used to make fusion of low-level features and high-level features, which makes full use of various information advantages. Moreover, the two-dimensional (2D) Generalized Intersection over Union is extended to 3D use as part of the loss function in our framework. Empirical experiments of Car, Cyclist, and Pedestrian detection have been conducted respectively on the KITTI benchmark. Experimental results with average precision (AP) have shown the effectiveness of the proposed network.

Download Full-text