| Due to the rapid development in VLSI technologies, it becomes possible to provide massive computing power which is essential to many real-time signal processing applications. Various functions, for example, machine vision algorithms for object detection or recognition and data compression algorithms for efficient wireless transmission or storage, will be provided by many applications, such as wearable computers and mobile equipments using batteries at home or in the office. These areas will become ubiquitous in some shape or form and generate huge market in the near future. Therefore, high performance and low power VLSI system design will be crucial to the future applications requiring high computational complexities.; Image and video coding techniques have become very attractive and widely used in many applications, such as high definition television (HDTV), video conferencing, and video telephony. Since visual information contains enormous amounts of data, many image and video coding standards, such as JPEG, JPEG-2000, H.26x, and MPEG family, have been developed to achieve high compression ratio. However, image and video coding algorithms have very high computational complexities and often demand strict real-time and low power requirements as well. Therefore, image and video signal processing algorithms are the focus of the thesis. Algorithm optimizations and efficient VLSI architectural designs for motion estimation and compensation in the transform domain, inverse discrete cosine transform, and hierarchical image coding, have been investigated and proposed to provide real-time, low power, and high computational capabilities. |
