Object Classification using 3D Convolutional Neural Networks

Examensarbete för masterexamen

Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.12380/249371
Download file(s):
File Description SizeFormat 
249371.pdfFulltext2.11 MBAdobe PDFView/Open
Type: Examensarbete för masterexamen
Master Thesis
Title: Object Classification using 3D Convolutional Neural Networks
Authors: Bender, Axel
Þorsteinsson Marel, Elías
Abstract: In the development of autonomous driving and active safety systems, knowledge about the vehicle’s surroundings is critical. When it comes to making decisions in real driving scenarios, the location and relative movement of surrounding vehicles, pedestrians and even static objects gives invaluable information to the system responsible for decision making. To know whether an object is a car or pedestrian, the system has to distinguish between the different features to predict object type. LiDAR sensors are among the most commonly used sensors in the development of modern AD systems as they produce dense images of their surroundings that are relatively resistant to changing light and weather conditions. Many classification methods use feature extraction or transformations to evaluate the 3D information using methods commonly used in 2D image analysis. In this thesis we evaluate the performance of training convolutional neural networks directly on 3D data, bypassing any information loss through data extraction or transformation and allowing the intensity hit of points to be used. The effectiveness of the method is evaluated on a dataset created from the KITTI Vision Benchmarking Suite. Our results show a total accuracy score of 96.35% and with a mean accuracy of 95.67% on a dataset trained on 7 classes.
Keywords: Building Futures;Energi;Informations- och kommunikationsteknik;Transport;Hållbar utveckling;Data- och systemvetenskap;Datorteknik;Infrastrukturteknik;Robotteknik och automation;Building Futures;Energy;Information & Communication Technology;Transport;Sustainable Development;Computer and systems science;Computer Engineering;Infrastructure Engineering;Robotics
Issue Date: 2016
Publisher: Chalmers tekniska högskola / Institutionen för energi och miljö
Chalmers University of Technology / Department of Energy and Environment
Series/Report no.: Rapportserie för Avdelningen för fysisk resursteori : 2016:11
URI: https://hdl.handle.net/20.500.12380/249371
Collection:Examensarbeten för masterexamen // Master Theses



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.