Youmei Harada

Real-time segmentation architecture of gray-scale/color motion pictures and digital test-chip implementation

This paper proposes a digital algorithm for gray-scale/color image segmentation of real-time video signals and a cell-network-based implementation architecture in state-of-the-art CMOS technology. Through extrapolation of test-chip-data design in 0.35 /spl mu/m CMOS technology and simulation results we predict that about 50,000 /spl sim/ 100,000 pixels can be integrated on a chip in a 0.09 /spl mu/m CMOS technology, realizing very high-speed segmentation at about 300 /spl mu/sec per gray-scale/color image. Consequently real-time color-video segmentation will become possible in near future.

Low-Complexity, Highly-Parallel Color Motion-Picture Segmentation Architecture for Compact Digital CMOS Implementation

l.Introduction Image segmentation is the process by which the original natural image is partitioned into meaningful regions and is an important initial task for higher-level image processing such as object recognition or object tracking. Several image segmentation algorithms have been proposed [1,2]. However, due to their complexity, compact digital VLSI implementation is impossible. For previously proposed analog VLSI approaches [3,4] the scalability to future sub-100nm,low-voltage CMOS technologies is questionable. In this paper, we present a lowcomplexity digital algorithm, offering high-density VLSIimplementation, comparable for gray-scale and color motionpicture segmentation.

Low-power design for real-time image segmentation LSI and compact digital CMOS implementation

We present a low-power design for real-time digital image segmentation LSI. We design the CMOS test-chip in a 0.35 /spl mu/m 2-Poly 3-Metal CMOS technology, based on a boundary active only architecture. The design area for 41 /spl times/ 31 pixels is 51.1mm/sup 2/ and the integration density is 26.5pixel/mm/sup 2/. From the circuit simulations at 3.3V supply voltage and 10MHz clock frequency, we obtain a power dissipation of 21.8mW and an image segmentation time of 23/spl mu/sec.