The Techniques Of Intelligent Surveillance Based On Virtual Instrument

In the modem time of pursuing for the automatization in the field of visual surveillance, the desire for a smart surveillance system, which is the substitute of surveillance members and can monitoring the moving object in some surveillance scenes automatically and consecutively, is very strong. In most cases, this intelligent system has some self-determination functions such as motion detection, body recognition and object tracking etc. It's very possible to design this system which no one needed to watch by fully utilizing the powerful calculating capacity of modem computer and many subjects such as image processing and analyzing, computer vision etc. But regrettably the research on this kind of system is in the first step in our country currently. The most difficult problem is lack of a desiring of global algorithm. Common algorithm often can not reach the practical standards such as tight linking among modules, low algorithm complexity, low ratio of missing alarm and false alarm etc .This paper is put forward in such a backgroundThe algorithm complexity is more lowered by simplifying and improving the algorithm on the three modules of motion detection, body recognition and object locating on the basis of researching and analyzing many other person's algorithms and studying others' research fruits. The global algorithm synthetically considers the real-time property and robust performance, and can be used in surveillance system. As mean while the system uses virtual instrument as a platform, and makes use of its strong functions on machine vision, image process, automatic control and man-machine interfacing. The system is novel and will have a favorable application field.Firstly this paper introduces the research status and tendency in the world detailedly, and then introduces Virtual Instrument and the design scheme and software structure of intelligent visual surveillance system based on Virtual Instrumentln main body, the whole paper is divided by three modules of motion detection, body recognition and object locating based on its function, and the article elaborates them one by one Motion detection module is the "eye" and the most important part in the intelligent system. Its design is the key of the whole system and it also holds the most calculating task. This module is divided by three sub-modules of preprocessing, motion detection and post-processing. In the sub-module of motion detection, the article first analyzes performance of traditional algorithm and points out some disadvantages,and then taking two algorithms: the background deduction algorithm and update background algorithm by means of motion average. The post-processing sub-module uses morphological filter to remove isolated noise and to fill the holes inside objects, deals with the apart image and the shadow of body effectively by a sample way.Body recognition module is the "brain" and the middle part in the intelligent system. It is also the precondition to be tracking precisely. The paper takes a simplified method of body recognition. This method only aims to the binary image gotten from the detection module and distinguishes person from other objects simply by distilling some characters in the object area of image. Comparing to other design method, this method lower the calculating cost in recognition. At the same time, this method also improves the system's recognition ratio and has more feasibility relative to other single recognition algorithm.Finally the paper makes summarizing, as meanwhile prospects the development of system..