Abstract

A programmable vision chip with variable resolution and row-pixel-mixed parallel image processors is presented. The chip consists of a CMOS sensor array, with row-parallel 6-bit Algorithmic ADCs, row-parallel gray-scale image processors, pixel-parallel SIMD Processing Element (PE) array, and instruction controller. The resolution of the image in the chip is variable: high resolution for a focused area and low resolution for general view. It implements gray-scale and binary mathematical morphology algorithms in series to carry out low-level and mid-level image processing and sends out features of the image for various applications. It can perform image processing at over 1,000 frames/s (fps). A prototype chip with 64 × 64 pixels resolution and 6-bit gray-scale image is fabricated in 0.18 μm Standard CMOS process. The area size of chip is 1.5 mm × 3.5 mm. Each pixel size is 9.5 μm × 9.5 μm and each processing element size is 23 μm × 29 μm. The experiment results demonstrate that the chip can perform low-level and mid-level image processing and it can be applied in the real-time vision applications, such as high speed target tracking.

Highlights

  • A vision chip integrates a sensor array with parallel processors in one chip and performs real-time parallel low- and mid-level image processing without I/O bottlenecks

  • The experiment results demonstrate that the chip can perform low-level and mid-level image processing and it can be applied in the real-time vision applications, such as high speed target tracking

  • This paper presents a programmable vision chip with variable resolution and row-pixel-mixed parallel image processors, which can perform such complex algorithms

Read more

Summary

Introduction

A vision chip integrates a sensor array with parallel processors in one chip and performs real-time parallel low- and mid-level image processing without I/O bottlenecks. Some application-specific vision chips performing low- and mid-level image processing were developed [9,10,11,12], but these chips were designed for specified applications and with a specified architecture Another vision chip performing exact dilations was presented in [13], but this one focused on several specific algorithms, such as morphological dilation, multi-scale skeleton and Distance Transform [14].

Architecture
Operations
Binary Mathematical Morphology
Gray-Scale Mathematical Morphology
Detecting a Void Image
Extracting the Range and the Center of a Region
Extracting the Coordinates of Activated Pixels
CMOS Image Sensor
Row-Parallel 6-bit Algorithmic ADCs
Row-Parallel Processors
Search Chain in X Processors and Y Processors
XPUs in the X Processor
YPUs in the Y Processor
Chip Implementation and Experiments
Experiment in Gray-Scale Mathematical Morphology
Experiment in Binary Mathematical Morphology
Target Tracking
Discussion of Performance
Conclusions
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call