Scalable real-time parking lot classification: an evaluation of image features and supervised learning algorithms

The time-consuming search for parking lots could be assisted by efficient routing systems. Still, the needed vacancy detection is either very hardware expensive, lacks detail or does not scale well for industrial application. This paper presents a video-based system for cost-effective detection of v...

Full description

Bibliographic Details
Main Authors: Tschentscher, Marc, Koch, Christian, König, Markus, Salmen, Jan, Schlipsing, Marc
Format: Conference or Workshop Item
Published: 2015
Online Access:https://eprints.nottingham.ac.uk/35406/
_version_ 1848795069506650112
author Tschentscher, Marc
Koch, Christian
König, Markus
Salmen, Jan
Schlipsing, Marc
author_facet Tschentscher, Marc
Koch, Christian
König, Markus
Salmen, Jan
Schlipsing, Marc
author_sort Tschentscher, Marc
building Nottingham Research Data Repository
collection Online Access
description The time-consuming search for parking lots could be assisted by efficient routing systems. Still, the needed vacancy detection is either very hardware expensive, lacks detail or does not scale well for industrial application. This paper presents a video-based system for cost-effective detection of vacant parking lots, and an extensive evaluation with respect to the system’s transferability to unseen environments. Therefore, different image features and learning algorithms were examined on three independent datasets for an unbiased validation. A feature / classifier combination which solved the given task against the background of a robustly scalable system, which does not require re-training on new parking areas, was found. In addition, the best feature provides high performance on gray value surveillance cameras. The final system reached an accuracy of 92.33% to 99.96%, depending on the parking rows’ distance, using DoG-features and a support vector machine.
first_indexed 2025-11-14T19:26:14Z
format Conference or Workshop Item
id nottingham-35406
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T19:26:14Z
publishDate 2015
recordtype eprints
repository_type Digital Repository
spelling nottingham-354062020-05-04T17:12:52Z https://eprints.nottingham.ac.uk/35406/ Scalable real-time parking lot classification: an evaluation of image features and supervised learning algorithms Tschentscher, Marc Koch, Christian König, Markus Salmen, Jan Schlipsing, Marc The time-consuming search for parking lots could be assisted by efficient routing systems. Still, the needed vacancy detection is either very hardware expensive, lacks detail or does not scale well for industrial application. This paper presents a video-based system for cost-effective detection of vacant parking lots, and an extensive evaluation with respect to the system’s transferability to unseen environments. Therefore, different image features and learning algorithms were examined on three independent datasets for an unbiased validation. A feature / classifier combination which solved the given task against the background of a robustly scalable system, which does not require re-training on new parking areas, was found. In addition, the best feature provides high performance on gray value surveillance cameras. The final system reached an accuracy of 92.33% to 99.96%, depending on the parking rows’ distance, using DoG-features and a support vector machine. 2015-07-17 Conference or Workshop Item PeerReviewed Tschentscher, Marc, Koch, Christian, König, Markus, Salmen, Jan and Schlipsing, Marc (2015) Scalable real-time parking lot classification: an evaluation of image features and supervised learning algorithms. In: 2015 International Joint Conference on Neural Networks (IJCNN), 12-17 July 2015, Killarney, Ireland. http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7280319 10.1109/IJCNN.2015.7280319 10.1109/IJCNN.2015.7280319 10.1109/IJCNN.2015.7280319
spellingShingle Tschentscher, Marc
Koch, Christian
König, Markus
Salmen, Jan
Schlipsing, Marc
Scalable real-time parking lot classification: an evaluation of image features and supervised learning algorithms
title Scalable real-time parking lot classification: an evaluation of image features and supervised learning algorithms
title_full Scalable real-time parking lot classification: an evaluation of image features and supervised learning algorithms
title_fullStr Scalable real-time parking lot classification: an evaluation of image features and supervised learning algorithms
title_full_unstemmed Scalable real-time parking lot classification: an evaluation of image features and supervised learning algorithms
title_short Scalable real-time parking lot classification: an evaluation of image features and supervised learning algorithms
title_sort scalable real-time parking lot classification: an evaluation of image features and supervised learning algorithms
url https://eprints.nottingham.ac.uk/35406/
https://eprints.nottingham.ac.uk/35406/
https://eprints.nottingham.ac.uk/35406/