Video Segmentation System Of Moving Object Using FPGA

• Main Authors: Dong-Sen Fang, 方東森
• Other Authors: Chyun-Shin Cheng
• Format: Others
• Language: zh-TW
• Published: 2002
• Online Access: http://ndltd.ncl.edu.tw/handle/19535055062906259310

碩士 === 國立臺北科技大學 === 自動化科技研究所 === 90 === The application of moving object segmentation is an essential technique on whether image identification or MPEG_4 compression techniques in the future. Moving object segmentation is also an important preprocessing stage in image capture procedures. MPEG_4 is currently the most focused compression technique. Therefore, to develop a way to retrieve video object within dynamic images in MPEG_4 is the key topic. The results of current researches over this topic tend to consume much processing time, and are also hard for hardware implementation. Therefore it’s quite difficult to apply moving object segmentation in real time. We first propose an easily implemented hardware moving object segmentation algorithm focused on this goal. We also propose an effective MADND (Mean Absolute Different Noise Deletion) algorithm for noise reduction, and a full orientated object scan algorithm to identify object region. In moving object detection, we propose a TFDA (Triple Frames Different And ) algorithm which is capable of detecting precise object region without complex operation. In hardware framework, we use a FPGA from Xilinx Vertex_E600 to design, simulate and integrate system algorithm . The result is a fast moving object segmentation hardware system . After design and test stages, we conclude the features of our system: 1.Simple and easily implemented algorithms. 2.Efficient in segmentation, can apply different segmentation approaches according to different conditions. 3.Provide fast segmentation ability to fit in real time MPEG_4 transmitting framework. 4.Can be used as an IP in image processing SOC.