Self-Supervised Cross-Connected CNNs for Binocular Disparity Estimation

Examensarbete för masterexamen

Please use this identifier to cite or link to this item:
Download file(s):
File Description SizeFormat 
255458.pdfFulltext1.56 MBAdobe PDFView/Open
Type: Examensarbete för masterexamen
Master Thesis
Title: Self-Supervised Cross-Connected CNNs for Binocular Disparity Estimation
Authors: Gröndahl, Trygve
Samuelsson, Anna
Abstract: When developing autonomous vehicles, sensors with high accuracy and speed are needed. One type of sensor that can gather a lot of information is the camera. From two stereo images a disparity between them can be calculated, and from that the depth. The drawback with today’s algorithms is the trade-off between high quality estimation and computational speed. By taking inspiration from recently published neural networks for other applications, we present a novel design for disparity estimation networks. We design a cross-connected convolutional neural network to calculate full HD disparity maps from stereo images at a high frequency. By transfer training the network, using self-supervised learning, the network can learn to handle new environments. The network shows significantly faster runtimes than other disparity estimation networks, with the loss of some accuracy. We show that the self-supervised loss functions perform poorly when the images are not aligned, which is important to solve for real life applications of the network. Furthermore, we present ideas on how to improve the network’s runtime further.
Keywords: Informations- och kommunikationsteknik;Datorseende och robotik (autonoma system);Bildanalys;Information & Communication Technology;Computer Vision and Robotics (Autonomous Systems);Image analysis
Issue Date: 2018
Publisher: Chalmers tekniska högskola / Institutionen för mekanik och maritima vetenskaper
Chalmers University of Technology / Department of Mechanics and Maritime Sciences
Series/Report no.: Master's thesis - Department of Mechanics and Maritime Sciences : 2018:26
Collection:Examensarbeten för masterexamen // Master Theses

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