Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/75358
Title: Available parking spaces detection with deep learning
Authors: Li, Xiaochen
Keywords: DRNTU::Engineering::Electrical and electronic engineering
Issue Date: 2018
Abstract: Image semantic segmentation has made great process with deep learning in recent years. There are various applications that need efficient and accurate segmentation systems. Image semantic segmentation has been widely used in modern medicine, robotics, and especially in the autonomous vehicle systems. An autonomous vehicle is a smart car that can sensing its surrounding environment and driving without human input, it is able to analysis the sensory data so that it can distinguish different objects such as cars and pedestrians on the road. With the great development and improvement of the Artificial Intelligence, we believe that automated driving will happen in the near future, and autonomous parking is a crucial step towards future autonomous driving. This report will give a study of the deep learning algorithms for image semantic segmentation of available parking spaces and CARLA Simulator. It will include a review of the basic principle, structure and design of the deep learning approach for image semantic segmentation, known as the Fully Convolutional Neural Networks model. Then it will show the training of the network and the results of the detection. The conclusion and the future works will be given in the end of the report.
URI: http://hdl.handle.net/10356/75358
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
FYP_Report_Lixiaochen.pdf
  Restricted Access
5.79 MBAdobe PDFView/Open

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.