By Topic

High-level representations of temporary traffic states using Hasse graph and temporal change map under a grid-based site model

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)
Xiaoming Yao ; Coll. of Electr. Eng., Southwest Jiaotong Univ., Chengdu, China ; Qingquan Qian

High-level representation of temporary traffic states is very crucial for intelligent traffic management applications, but a challenging task due to the complexity of the traffic states. In this paper, we present theoretically a high-level representation of temporary regional traffic states using Hasse graph and temporal change map under a grid-based site model. We first model the region within the monitoring range of the camera as an uncovered house and express it with a set of 4-tuples. Then we formulate a partial ordered relation with grid coordinates of the extracted objects in a specific site from which a Hasse graph is yielded. On the timeline, difference between two consecutive Hasse graphs makes a variable temporal change map. All temporary traffic states can be categorized into two types: one is the motion of a single object, represented simply with the Hasse graph of its location and the temporal change map; the other is the set of grouped patterns of all the extracted object, or the Hasse graph of the neighboring objects. With this representation and the fuzzy concept of neighborhood, key traffic states like collision and secure distance can be distinguished and determined using appropriate motion prediction based on the previous measurement to manipulate the undesirable cases on time.

Published in:

Proceedings Autonomous Decentralized Systems, 2005. ISADS 2005.

Date of Conference:

4-8 April 2005