The research explores the video processing techniques for visual monitoring, such as, video surveillance, meeting mining, and human activity understanding. The basic techniques of processing video from static cameras, object detection, tracking and recognition, trajectory analysis and object classification. The specific problems, for example, face analysis, license plate recognition, under vehicle scanner, parking system, helmet detector, gesture analysis and recognition, vehical logo/color recognition, leave largage, intrusion, pedestrian detection and etc. More advanced problems using multiple cameras and moving cameras, such as, the 3d localization, fall detection and etc. Privacy issues will also be examined, focusing on how automatic processing can protect privacy?
๑. My Research
On-line video processing for surveillance system is a very challenging problem. The computational complexity of video analysis algorithms and the massive amount of data to be analyzed must be considered under real-time constraints. Moreover it needs to satisfy different criteria of application domain, such as, scalability, re-configurability, and quality of service. Here we propose a flexible/efficient video analysis framework for surveillance system which is a component-based architecture. The video acquisition, re-configurable video analysis, and video storage are some of the basic components. The component execution and inter-components synchronization are designed for supporting the multi-cores and multi-processors architecture with multi-threading implementation
The goals of this research are to design and develop an integrated multimedia information retrieval and database management infrastructure that supports multimedia information. It’s emphasized three directions, 1) multimedia content representation by image processing and computer vision techniques in order to extract the salient features from visual media, 2) multimedia information retrieval to define a notion of similarity between multimedia objects, and 3) database management to support efficient storage of multimedia objects and retrieval based on the degree of match.
This research is invested on image matching methods, and their applications. It is divided into two parts: methodological and engineering. The first tackles decision methods used to match features between images. We found it on the “stable marriage” paradigm. Several algorithms are developed with constraints added, as global satisfaction or equity, for better adapting to […]
This research is done during my master’s degree, it emphasize on graph theory applying for real-time system, a system with multi-processors architecture for signal and digital image applications. The work is done for the SynDEx project at national institute of INRIA. The aim of project is to develop software that from algorithm/architectural graphs, the executive […]
The development of Land Use Potential Program is very useful for Thai’s farmers. In order to gain the maximum benefit from land, the farmers should produce crop with respect to land capability. Therefor, the land use potential program will provide a basic data for the formers decision. The data used in this determination based on […]