Research On Algorithm Of Moving Object Detection And Tracking Methods In Intelligent Visual Surveillance System

Intelligent video surveillance (IVS) has been a more and more important role in society life with the improvement of security concepts. The core tasks of IVS are analyzing image sequences of video streaming automatically, realizing determination and tracking for dynamic scene, and achieving the target recognition as well as behavior comprehension in following steps. For movement contains lots of visual information, the detecting and trending of movement target are the most important part for IVS. Intensive studies on target determination and tacking are conducted according three respects. This paper has stated operating principles and technologies of IVS. And the application, superiority, key technology and developing trend are also elaborated in the article.Firstly, this paper researching on the nature of several commonly used moving objects detection methods, background are detected using the gaussian mixture model, and selected suitable morphological operations to denoise the detected foreground object.Aimed at the problem of the current moving cast shadow detection using texture information is excessively rough and requires manual intervention to selection the threshold, an adaptive elimination algorithm based on NCC (Normalized Cross-correlation) merging intensity and normalized color is proposed in this paper. Based on the foreground pixels which is obtained with the Gaussian mixture model, the brief steps to reach the goal are as follows:the candidate shadow region is selected through the feature of shadow on intensity and normalized color, then the shadow region is narrowed with the improved algorithm above and finally the real shadow is obtained by spatial analysis. The results show that the algorithm can effectively reduce the noise and then better distinguish the moving objects and shadows which possess of unconspicuous local texture.An improved tracking algorithm which combining the traditional Meanshift algorithm with the adaptive Kamlan filer was proposed to solve the poor tracking ability problem in occlusions. First, we transform the traditional RGB color space to HSV color space, then, a new fusion rules are put forward. Tracking by Meanshift algorithm when target without shelter or walking out the shelter and using Klaman filtering to estimating movement locus while target going into shelters and being sheltered completely. The result shows that new algorithm effectively solved the problem that tacking of target sheltered lost easily.The work principle and designing of IVS are analyzed, and the importance and superior in people’s life also stated. This paper focuses on analyzing application, technology superior and improvement trend.This research effectively improves the detecting of moving shadow and solves the problem of missing on moving object tracking. That has the application value and guiding significance to moving object detecting and tracking for IVS.