A statistical modeling method for road recognition in traffic video analytics
Document Type
Conference Proceeding
Publication Date
9-23-2020
Abstract
A novel statistical modeling method is presented to solve the automated road recognition problem for the region of interest (RoI) detection in traffic video cognition. First, a temporal feature guided statistical modeling method is proposed for road modeling. Specifically, a foreground detection method is applied to extract the temporal features from the video and then to estimate a background image. Furthermore, the temporal features guide the statistical modeling method to select sample data. Additionally, a model pruning strategy is applied to estimate the road model. Second, a new road region detection method is presented to detect the road regions in the video. The method applies discrimination functions to classify each pixel in the estimated background image into a road class or a non-road class, respectively. The proposed method provides an intra-cognitive communication mode between the ROI selection and video analysis systems. Experimental results using real traffic videos from the New Jersey Department of Transportation (NJDOT) show that the proposed method is able to (i) detect the road region accurately and robustly and (ii) improve upon the state-of-the-art road recognition methods.
Identifier
85096352169 (Scopus)
ISBN
[9781728182131]
Publication Title
11th IEEE International Conference on Cognitive Infocommunications Coginfocom 2020 Proceedings
External Full Text Location
https://doi.org/10.1109/CogInfoCom50765.2020.9237905
First Page
97
Last Page
102
Grant
1647170
Fund Ref
National Science Foundation
Recommended Citation
Shi, Hang; Ghahremannezhadand, Hadi; and Liu, Chengjun, "A statistical modeling method for road recognition in traffic video analytics" (2020). Faculty Publications. 5001.
https://digitalcommons.njit.edu/fac_pubs/5001
