This paper presents a software-hardware co-operative protocol processor for a 10 gigabit Ethernet passive optical network (10G-EPON), designed with a software-hardware division technique that focuses on the throughput and timing-accuracy requirements. This protocol processor consists of frame-processing hardware to meet the timing requirements, an interface to absorb the speed difference between software and hardware, and software to implement additional protocols. This protocol processor enables network operators to install additional service protocols adaptively for their own services. The 10G-EPON system with this protocol processor properly worked in the experiment.

In this correspondence, a parallel algorithm, in order to extract parametric curves from a two-dimensional (2-D) image space, is proposed. It is based on the Hough transform (HT) and uses the content addressable memory (CAM) as the main processor. A set of simulated results for circular shape extraction are presented in order to demonstrate its merit. Hence, voting, thresholding, and three-dimensional (3-D) peak extraction are efficiently performed within the CAM. In addition, and in order to reduce the quantization errors, a weighted AT algorithm (WHT), which uses a weighted voting is proposed. Experimental results indicate that a real-time shape extraction for an image 256/spl times/256 can be achieved within a small amount of hardware. Therefore, CAM-based HT can be considered as a promising attraction for next generation pattern recognition platforms.

We describe real-time straight line extraction system and evaluate it. The main part of our system involves a highly parallel processing board on which a highly parallel Hough transform algorithm is mounted. We used the Hough transform, because it useful in line detection. In this board, a content addressable memory (CAM) LSI with dedicated functions for highly parallel image processing is used in this board. Both voting and peak extraction, which make up the Hough transform, are directly executed by the CAM. The CAM acts as a PE (processing element) array that performs highly parallel processing for the Hough transform and it also acts as a memory for two-dimensional Hough space. Sixteen thousand Hough points can be mapped at once and thousands more can be mapped by time-sharing in one CAM. Also variable Hough point resolution is available, because the CAM-based HT algorithm on this board is scalable. Thus line extraction by the Hough transform of 16-K point Hough space for a 256/spl times/256 picture can be carried out at video-rates by using a Hough board with a single CAM chip. Moreover a Hough transform with weighted voting for noisy images can also be achieved at video-rates.

This paper proposes a real-time content addressable memory (CAM)-based Hough transform algorithm for straight line detection and evaluates its performance. Both voting and peak extraction, which compose the Hough transform, are directly executed by CAM. The CAM acts as a processing element (PE) array that performs highly parallel processing for the Hough transform and also as a memory for two-dimensional Hough space. To achieve high-speed processing, voting is executed in every scanning line, not every pixel. The Hough space is mapped into the CAM in folded form to reduce the size of the CAM hardware. Moreover, CAM-based weighted voting achieves more accurate line detection in spite of the quantization error and noise in the image space. Simulations of CAM hardware size, processing time and the accuracy of line detection show that a real-time and high-resolution Hough transform for a 256/spl times/256 picture can be achieved using a single CAM chip with current VLSI technology. This CAM-based Hough transform algorithm promises to be an important step towards the realization of a real-time and compact image understanding system.