Robust Parking Space Detection Considering Inter-Space Correlation

Author

Wu, Qi ; Huang, Chingchun ; Wang, Shih-Yu ; Chiu, Wei-Chen ; Chen, Tsuhan

Author_Institution

Carnegie Mellon Univ., Pittsburgh

fYear

2007

fDate

2-5 July 2007

Firstpage

659

Lastpage

662

Abstract

A major problem in metropolitan areas is searching for parking spaces. In this paper, we propose a novel method for parking space detection. Given input video captured by a camera, we can distinguish the empty spaces from the occupied spaces by using an 8-class support vector machine (SVM) classifier with probabilistic outputs. Considering the inter-space correlation, the outputs of the SVM classifier are fused together using a Markov random field (MRF) framework. The result is much improved detection performance, even when there are significant occlusion and shadowing effects in the scene. Experimental results are given to show the robustness of the proposed approach.

Keywords

Markov processes; image classification; image fusion; learning (artificial intelligence); object detection; probability; random processes; support vector machines; traffic engineering computing; video signal processing; 8-class support vector machine; Markov random field; SVM classifier; image fusion; inter-space correlation; machine learning; occlusion; parking space detection; probabilistic output; shadowing effect; video signal processing; Cameras; Feature extraction; Markov random fields; Robustness; Space exploration; Space technology; Space vehicles; Support vector machine classification; Support vector machines; Vehicle detection;

fLanguage

English

Publisher

ieee

Conference_Titel

Multimedia and Expo, 2007 IEEE International Conference on

Conference_Location

Beijing

Print_ISBN

1-4244-1016-9

Electronic_ISBN

1-4244-1017-7

Type

conf

DOI

10.1109/ICME.2007.4284736

Filename

4284736