Fast segmentation of 3D point clouds for ground vehicles

By Michael Himmelsbach, Felix von Hundelshausen, Hans-Joachim Wünsche. 2010

444 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Automotive Engineering, Environmental Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Automotive Engineering

In Environmental Engineering

Citations in the corpus

3D fully convolutional network for vehicle detection in point cloud (2016, background): “Candidates can be proposed by delicate segmentation algorithms [2], [5], [11], [14], [21], [22], [28], [29], [31], sliding window [30], random sampling [13], or the recently popular Region Proposal Network (RPN) [26].”
Vehicle Detection from 3D Lidar Using Fully Convolutional Network (2016, methodology): “In some early works, rule-based segmentation is suggested for speciﬁc scene [10, 20, 5].”
LeGO-LOAM: Lightweight and Ground-Optimized Lidar Odometry and Mapping on Variable Terrain (2018, methodology): “A column-wise evaluation of the range image, which can be viewed as ground plane estimation [22], is conducted for ground point extraction before segmentation.”
Fast segmentation of 3D point clouds: A paradigm on LiDAR data for autonomous vehicle applications (2017, background): “[3] are treating the point cloud in cylindrical coordinates and taking advantage of the distribution of the points in order to fit line segments to the point cloud.”
A Slope-robust Cascaded Ground Segmentation in 3D Point Cloud for Autonomous Vehicles (2018, methodology): “In order to highlight the performance of the proposed algorithm, the comparison between the various segmentation results of the proposed method and the other two methods described in [5] and [6] are shown in Fig 8.”
Laser-based segment classification using a mixture of bag-of-words (2013, background): “Especially self-driving cars need to distinguish reliably between static and dynamic objects, such as pedestrians, vehicles, and bicyclists, to ensure safe operation in crowded and even uncooperative inner-city traffic.”
Performance of global descriptors for velodyne-based urban object recognition (2014, methodology): “For every scan (the set of points collected during the Velodyne LIDAR spins once), we assume that the ground segmentation and object cluster steps ( [1], [2], [3], [4], [5], [6]) have already been performed, and the outputs of the two steps are different objects.”