Research On Moving Human Detection Based On Color Video Image

Visual analysis of human motion is one of the most important research topics in the domain of computer vision. It is also an active filed which has interested many researchers in recent years. Human motion analysis aims at attempting to detect, identify and track human bodies from image sequences, and more generally, to understand and describe their behaviors. Motion detection and tracking belong to the low-level vision problems, and behavior understanding and description belong to the high-level vision problems. Research in this domain involves wide application, including virtue reality, security surveillance, human-computer interface, etc. In this thesis, we focus on some problems about the motion human in still background, with stead camera. The research includes moving human detecting, background obtaining and updating, shadow detection and removing.Firstly, motion detection is the basic of video applications such as computer vision, object recognition and tracking, surveillance security etc. Background subtraction is an important approach of motion detection, but it is sensitive to illumination and shadow. A novel motion detection algorithm which employs background subtraction and symmetrical differencing based on RGB color difference model is presented in this thesis. The experimental results show that the detection algorithm can detect moving objects effectively and correctly.Secondly, background image usually changes as time goes by and the environment changes, which makes some parts of the background misclassified as moving foreground object. Therefore, it is necessary to model background to adapt the changes of background. In this thesis, the Single Gaussian Modeling as the initialization background model combined with an improved linear alternate background updating method is proposed. The experimental results are given.Thirdly, motion is usually along with the occurrence of shadow, which impacts the correctness and accuracy of motion detection. Furthermore, there are two same important visual characters between a shadow and its corresponding object: a shadow is obviously different from the background, so it is easily detected as foreground; shadow and its corresponding object have same movement. These two features make shadow detection and removal very challengeable. The algorithms in RGB and HSV color space are introduced in this paper. By comparing the algorithms in the two color spaces, one improved algorithm to detect the shadow in both two color spaces is proposed in this thesis. By using this algorithm, the accuracy and the time performance are greatly improved.