SEMINAR REPORT ON

GENERIC VISUAL PERCEPTION PROCESSOR

Session :2014-2015

Submitted By:

Deobrat Singh

B.Tech 3rd Year(CSE)

Department Of

Computer Science And Engineering

Madan Mohan Malaviya University of Technology

Gorakhpur-273010

INTRODUCTION

Generic Visual Perception Processor (GVPP) can automatically detect

objects and track their movement in real-time.

The processor sees its environment as a stream of histograms

regarding the location and velocity of objects.

This electronic "eye" on a chip can now handle most tasks that a

normal human eye can. That includes driving safely, selecting ripe

fruits, reading and recognizing things.

BACKGROUND OF INVENTION

Traditional processor failed when there was no predefined algorithm to

solve problem

Even in these extreme cases GVPP performs well. It can solve problem

with its neural learning function.

The GVPP was invented in 1992,by BEV founder Patric Pirim.

Pirim created a chip architecture that mimicked the work of neurons , with

the help of multiplexing and memory.

HOW IT WORKS

There is large number of input lines and an output line to a neuron and

each of them is capable of implementing a simple functions.

It takes weighted sum of inputs and produces an output that is fed into the

next layer.

The chip mimics the human eye’s in two processing steps, tonic and

phasic.

HARDWARE AND SOFTWARE ASPECTS

SOFTWARE ASPECTS

A host operating system running on external PC communicates with the

GVPP evaluation board via an OS kernel within the on chip

microprocessor.

“Programming the GVPP is as simple as setting a few registers and then

testing the results to gauge the application’s success” said Steve Rowe,

BEV’s director of R&D.

Programming GVPP application takes minimal time.

HARDWARE ASPECTS

The chip houses 23 neural blocks, both temporal and spatial, each consists

of 20 hardware input and output “synaptic” connections.

GVPP multiplexes this neural hardware with off chip scratchpad memory to

simulate as many as 100,000 synaptic connections per neuron.

The retine in the figure is the electronic eye of the system. The

eye referred to a high definition camera.

ADVANTAGES

GVPP has been demonstrated as capable of learning-in-place to solve a

variety of pattern recognition problems.

It is an inexpensive device that can autonomously "perceive" and then track

up to eight user-specified objects in a video stream

The engineer needs no knowledge of the internal workings of the GVPP,

the company said, only application-specific domain knowledge.

The chip could be useful across a wide variety of industries where visual

tracking is important

Simple applications can be quickly prototyped in a few days, with medium-

size applications taking a few weeks and even big applications only a

couple of months

DISADVANTAGES

Sadly, though modeled on the visual perception capabilities of the human

brain, the chip is not really a medical marvel, poised to cure the blind.

APPLICATION

Automotive Industry

Robotics

Agriculture and Fisheries

Military Applications

CONCLUSION

Imitating the human eye's neural networks and the brain, the generic

visual perception processor can handle about 20 billion instructions

per second, and can manage most tasks performed by the eye

This electronic "eye" on a chip can now handle most tasks that a

normal human eye can. That includes driving safely, selecting ripe

fruits, reading and recognizing things.

REFERENCES

Bart Kosko, Neural networks and fuzzy systems, Addison Wesley

http://www.techweb.com

http://www.patentstorm.us

International Journal of Engineering Research and General

Science Volume 2, Issue 6, October-November, 2014

THANK YOU