3D Object Detection For Intelligent Vehicles

van der Sluis, J.R.

3D Object Detection For Intelligent Vehicles

Master thesis (2020)

Authors

J.R. van der Sluis Mechanical Engineering

Contributors

D. Gavrila Intelligent Vehicles - Mechanical, Maritime and Materials Engineering (mentor)

E.A.I. Pool Intelligent Vehicles - Mechanical, Maritime and Materials Engineering (mentor)

W. Pan Robot Dynamics - Mechanical, Maritime and Materials Engineering (graduation committee member)

J.C. van Gemert Pattern Recognition and Bioinformatics - (graduation committee member)

Faculty

Mechanical Engineering, Mechanical Engineering

Robotics Distance Point Cloud LiDAR Intensity Camera Intelligent Vehicles Experimental study Occlusion 3D object detection Vulnerable Road User KITTI dataset Pedestrian detection Temporal fusion 3D Person Localization Intersection over Union EuroCity Persons 2.5D dataset LiDAR Points

To reference this document use:

http://resolver.tudelft.nl/uuid:55819905-53fb-41bd-839f-6e840216035a

More Info

expand_more

Published Date

26-10-2020

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Mechanical Engineering

Abstract

This master thesis presents an experimental study on 3D person localization (i.e., pedestrians, cyclists)in traffic scenes, using monocular vision and Light Detection And Ranging (LiDAR) data. The performance of two top-ranking methods is analyzed on the 3D object detection KITTI dataset. In this evaluation, the effect of the Intersection over Union (IoU) threshold on the performance in terms of 3D bounding box location, size, and orientation is analysed.
Since the KITTI 3D object detection dataset contains relatively few 3D person instances, the analysis will is to the EuroCity Persons 2.5D (ECP2.5D) datasets (both day and night), which is one order of magnitude larger. Using both datasets, additional experiments are performed to evaluate the influence of distance, the number of LiDAR points, occlusion, and intensity on the performance. Domain transfer experiments between the KITTI and ECP2.5D datasets are performed, to examine how these datasets generalize with respect to each other. Furthermore, Part-A2 net is used to evaluate the detection score which is given to the ground truth pedestrians. The relationship between the detection score and the distance, the number of LiDAR points, and occlusion is analyzed. Some objects are not detected although their ground truth detection score is high. This creates the potential to detect these pedestrians. Lastly, this thesis presents a method that uses the detections from the previous frame to increase the performance in the subsequent frame by adding the previous detections to the 3D proposals coming from the Region Proposal Network (RPN).

Files

Master_Thesis_Joram_van_der_Sl... (pdf)

(pdf | 25.5 Mb)

Unknown license