Integrating vision and language: semantic description of traffic events from image sequences

Authors:
Takashi Hirano;Shogo Yoneyama;Yasuhiro Okada;Yukio Kosugi
Affiliations:
Mitsubishi Electric Corporation, Information Technology R&D Center;Mitsubishi Electric Corporation, Information Technology R&D Center;Mitsubishi Electric Corporation, Information Technology R&D Center;Tokyo Institute of Technology, Interdisciplinary Graduate School of Science and Engineering
Venue:
ISVC'07 Proceedings of the 3rd international conference on Advances in visual computing - Volume Part II
Year:
2007

Citing 6
Cited 0

Association of motion verbs with vehicle movements extracted from dense optical flow fields

ECCV '94 Proceedings of the third European conference on Computer Vision (Vol. II)
Integrating vision, motion and language through mind

Artificial Intelligence Review - Special issue on integration of natural language and vision processing: recent advances
Recognition of Visual Activities and Interactions by Stochastic Parsing

IEEE Transactions on Pattern Analysis and Machine Intelligence
Integrating Vision and Language: Towards Automatic Description of Human Movements

KI '95 Proceedings of the 19th Annual German Conference on Artificial Intelligence: Advances in Artificial Intelligence
Bayesian background modeling for foreground detection

Proceedings of the third ACM international workshop on Video surveillance & sensor networks
A Bayesian Approach to Background Modeling

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops - Volume 03

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose an event extraction method from traffic image sequences. This method extracts moving objects and their trajectories from image sequences recorded by a stationary camera. These trajectories are mapped to 3D virtual space and physical parameters such as velocity and direction are estimated. After that, traffic events are extracted from these trajectories and physical parameters based on case-frame analysis in the field of natural language processing. Our method facilitates to describe events easily and detect general traffic events and abnormal situations. The experimental results of actual intersection traffic image sequence have shown the effectiveness of the method.