By Topic

Fully-automatic recognition of various parking slot markings in Around View Monitor (AVM) image sequences

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Jae Kyu Suhr ; Research Institute of Automotive Electronics and Control, Hanyang University, Seoul, Korea ; Ho Gi Jung

This paper proposes a novel fully-automatic method for recognizing various parking slot markings in image sequences acquired by an Around View Monitor (AVM) system which is gaining popularity as a parking-aid product. The proposed method utilizes an approach which finds parking slots in AVM image sequences using a simple detector and combines sequentially acquired slots rather than using a sophisticated heavy detector in order to achieve the robustness against diverse practical situations. Parking slots are first detected in the current image using the hierarchical tree structure based approach presented in our previous paper [1]. Then, the current positions of previously detected parking slots are predicted using a transformation between consecutive images, and the parking slots detected in the current image and predicted from previous images are combined. The resulting parking slots are clustered according to their types and orientations, and the clusters which contain more than a predetermined number of slots are selected as final parking slots. The proposed method was evaluated using 10 AVM image sequences that include 134 parking slots, and demonstrated a detection rate of 95% with only three false detections.

Published in:

2012 15th International IEEE Conference on Intelligent Transportation Systems

Date of Conference:

16-19 Sept. 2012