Publications

Journal paper, doctoral thesis, international conference papers, research report, master thesis, journal submissions.

Journal Paper

  1. Van-Thinh VU, François BRÉMOND & Monique THONNAT. Human behaviour visualisation and simulation for automatic video understanding. Journal of WSCG, Volume 10, No.1-3, 2002, pp485-492 ISSN1213-6972 (http://wscg.zcu.cz/jwscg/index-jwscg.htm). Download. Demo.
    Abstract. The objective of this work is the visualisation and simulation for automatic video interpretation. We have conceived a test framework that generates 3D animations corresponding to behaviours recognised by an automatic interpretation system or corresponding to behaviours described by an expert. Conceiving this test framework is essential in order to be able to develop and validate the interpretation process. The objective of our test framework is (1) to visualise the computation of the interpretation, (2) to be flexible (configurable) enough for testing the different configurations of the interpretation and (3) to be realist enough to understand what is interpreted. To solve this problem we have defined six types of model to represent all the information that is necessary for the interpretation. First, we propose a model of the scene context (containing the 3D geometry) and a model for the virtual camera. Second, we propose an articulated and hierarchical model for representing the human body given its sub parts. We propose two other hierarchical models for modelling human actions and scenarios, and also a model of scene-scenarios that gathers all previous models. We have defined a description language for representing these models. The obtained results are promising: we have developed a test system for a given interpretation system and started evaluating it by generating test animations.

Doctoral Thesis

  1. Van-Thinh VU. Temporal Scenarios for Automatic Video Interpretation. Université de Nice – Sophia Antipolis, France, 14/10/2004. More details.

International Conference Papers: 2006, 2003, 2002, 1997, 1996.

2003
7.
 Van-Thinh VU, François BRÉMOND and Monique THONNAT. Automatic Video Interpretation: A Novel Algorithm for Temporal Scenario Recognition. The Eighteenth International Joint Conference on Artificial Intelligence (IJCAI'03), Acapulco, Mexico, 9-15 August 2003. © by IJCAII.
Abstract. This paper presents a new scenario recognition algorithm for Video Interpretation. We represent a scenario model by specifying the characters involved in the scenario, the sub-scenarios composing the scenario and the constraints combining the sub-scenarios. Various types of constraints can be used including spatio-temporal and  logical constraints. In this paper, we focus on the performance of the recognition algorithm. Our goal is to propose an efficient algorithm for processing temporal constraints and combining several actors defined within the scenario. By efficient we mean that the recognition process is linear in function of the number of sub-scenarios and in most of the cases in function of the number of characters. To validate this algorithm in term of correctness, robustness and processing time in function of scenario and scene properties (e.g. number of persons in the scene), we have tested the algorithm on several videos of a bank branch and of an office, in on-line and off-line mode and on simulated data. We conclude by comparing our algorithm with the state of the art and showing how the definition of scenario models can influence the results of the real-time scenario recognition.          Click here to get the article.
6.
 Van-Thinh VU, François BRÉMOND and Monique THONNAT. Automatic Video Interpretation: A Recognition Algorithm for Temporal Scenarios Based on Pre-compiled Scenario Models. The 3rd International Conference on Vision System (ICVS'03), Graz, Austria, 1-3 April 2003. LNCS 2626, pp.523-533, Springer-Verlag Berlin Heidelberg 2003.
Abstract. This paper presents a new scenario recognition algorithm for Video Interpretation. We represent a scenario model with the characters involved in the scenario, with its sub-scenarios and with the constraints combining the sub-scenarios. By pre-compiling the scenario models, the recognition algorithm processes temporal constraints by decomposing complex scenarios into intermediate sub-scenarios to reduce the algorithm complexity. We have tested the recognition algorithm on several videos of a bank agency to try to recognize a scenario of "Attack". We conclude by showing experimental results of the efficiency of this algorithm for real time temporal scenario recognition.          Click here to get the article.
2002
5.
 Van-Thinh VU, François BRÉMOND and Monique THONNAT. Temporal Constraints for Video Interpretation. The 15-th European Conference on Artificial Intelligence (ECAI'2002), W9:  Modelling and Solving Problems with Constraints, Lyon, France, 21-26 July 2002.
Abstract. This paper presents an original approach for temporal scenario recognition for video interpretation. We propose a declarative model to represent scenarios and we use a logic-based approach to recognize pre-defined scenario models.  To speed up the recognition process, we propose a new method to process the temporal operators of interval algebra and a method to extend the time interval of recognized scenarios. We have tested our representation formalism and the inference engine on two real video sequences.           Click here to get the article.
4.
 Van-Thinh VU, François BRÉMOND and Monique THONNAT. Video surveillance: human behaviour representation and on-line recognition. The Sixth International Conference onKnowledge-Based Intelligent Information  & Engineering Systems (KES'2002), Podere d'Ombriano, Crema, Italy, 16, 17 & 18 September 2002.
Abstract. This paper presents a recent work in human behaviour representation and on-line recognition for video interpretation. We propose a declarative model to represent human behaviours and we use the logic-based approach to recognise pre-defined behaviour models. We demonstrate our representation formalism and the inference engine on two video sequences. We also propose a limit for the number of behaviour actors based on experimental results. The processing time is still a challenge with complex behaviour models and cluttered scenes.       Click here to get the article.
1997
3.
 Khang BACH HUNG., Mai LUONG CHI, Van-Thinh VU, et al.. MapScan for Windows – Software Package for Automatic Map Data Entry. 1997 Asia-Pacific Symposium on Information and Telecommunication Technologies (APSITT'97), Hanoi, Vietnam, 13-14 March, 1997.
1996
2.
 Van-Thinh VU. A modification of unsupervised classification algorithms. International Conference on Information Technology on the 25th Anniversary of the Institute of Information Technology of Vietnam, Hanoi, Vietnam, 25-27/12/1996.
1.
 Khang BACH HUNG, Mai LUONG CHI, Van-Thinh VU, et al.. An examination of techniques for raster-to-vector process and its implementation - MAPSCAN software package. International Symposium "Advanced Manufacturing Processes, Systems and Technologies", Bradford, UK, 26-27/3/1996.

Research Report

  1. Francois BREMOND, Nicolas MAILLOT, Monique THONNAT & Van-Thinh VU. Ontologies For Video Events. Research report number 5189, INRIA, 04/2004. Download.

Master Thesis

  1. Van-Thinh VU. Visualisation de comportements humains pour l'interprétation automatique de séquences vidéos. INRIA Sophia-Antipolis, France, 08/2001. More details.

Journal Submissions

  1. Van-Thinh VU, François BRÉMOND & Monique THONNAT. Temporal Scenario Representation for Automatic Video Interpretation. Journal of Artificial Intelligence Research (JAIR).
  2. Van-Thinh VU, François BRÉMOND & Monique THONNAT. Audio-Video Event Recognition for Automated Scene Understanding. Journal of Computer Vision and Image Understanding (CVIU).