Papers by Keyword: Moving Body

Abstract: This paper presented a detecting algorithm based on improved Gaussian mixture model, which improved the speed of establishing and updating the model. Whilst, according to the detection requirements in different time periods, using the method of combining temporal differencing and background differencing to detect moving body improved the instantaneity and veracity of moving body detection.

Abstract: Thinning algorithm is widely used in image processing and pattern recognition.In this paper we proposed an optimized thinning algorithm based on Zhan-Suen thinning and applied it to video sequences of moving human body to extract real-time body skeleton. We firstly used background subtraction method to detect moving body, then made use of adaptive threshold segmentation to gain the binary moving body image, finally we used the optimized algorithm to the binary image and got its skeleton. The skeleton not only maintains the movement geometry and body image’s topological properties, also reduces image redundancy and computation cost, and helps us clearly recognize the moving body posture.

Abstract: We present an easy approach to obtain the dynamic flow field with a moving body inside. Instead of popular interface boundaries, the interior boundaries were applied as moving parts, which made separated computation volumes a default-continuum meanwhile. With the combination use of UDF and dynamic mesh model, the numerical technique was tested and validated by simulating flow through moving screen, a kind of porous material. The pressure and velocity contours obtained clearly showed the changing behaviors of the flow while passing through a moving porous material, and clarified the influence posed by the movement of its frame. The method is used for the simulation of the flow with a moving body inside.