Color Space for Embedded Vision, Part 2

Thumbnail image for Color Space for Embedded Vision, Part 2

I really did rush into the luminance options in Part 1. I’ll take this opportunity to try to gain amnesty for when I make the same mistake again.

But as for embedded vision, it will succeed when it delivers useful vision functions at a cost appropriate to the application.

Read the full article →

Semi-Conscious: The consumer vision market is more real than you are.

Thumbnail image for Semi-Conscious: The consumer vision market is more real than you are.

Seriously does anyone really think we will have a breakthrough in consumer vision products using general purpose processors alone?

Not breakthrough in the sense of “more people will have to buy our big hot chip.”

Read the full article →

Color Space for Embedded Vision

Thumbnail image for Color Space for Embedded Vision

The components of a color space let us specify the reproduction of an image pixel by pixel.

The quality of appearance each component describes–and how well it describes that quality–can determine the complexity, cost, and performance of our embedded vision system.

Which color space is best for embedded vision?

Read the full article →

Easy Eye: SiLabs 8051 + Camera

Thumbnail image for Easy Eye: SiLabs 8051 + Camera

Image capture and 60fps color object targeting with an 8-bit microprocessor and a CMOS camera.

The C8051F360 syncs to video from a digital camera, reads pixel values, makes decisions about objects in the scene, communicates by serial port, and drives displays or servos by GPIO.

Read the full article →

Semi-Conscious: Consumer Vision

Thumbnail image for Semi-Conscious: Consumer Vision

Sensor networks with cameras. $2 vision systems. Roombas that avoid dog poop.

Machine vision people ask me “what do you want, object recognition with a PIC?”

Yes. Why not?

Read the full article →

RAW Pixel Diet

Thumbnail image for RAW Pixel Diet

What type of input does a vision application need?

Can we use pixel data straight from the camera’s image sensor?

Or does the application need pixel data processed by an image sensor pipeline (ISP) with color transformations and denoising?

Read the full article →

Semi-Conscious: Hot FPGA Pixels = Surveillance?

Has not one seat in the circle of vision research been left vacant for a new approach?

Come winter we enjoy the heat of FPGAs stuffed with cranky algorithms grinding through pixels to make …. the same pixels come out the other end.

Read the full article →

Microchip – Let my robot see!

Thumbnail image for Microchip – Let my robot see!

Computer Vision, Laser Ranging, and Servo Control on a Single-Wire Network

A Microchip PIC directly sampling a video signal. 8 pins well used.

Read the full article →

Semi-Conscious: GPU – Now you’re just mashing it.

CPU/GPU/FPGA/ASIC.

General purpose processors that do everything slowly vs. specialized functions that do some things quickly.

Read the full article →

Computer Vision for Everyone

The purpose of this website is to extend computer vision to anyone who builds embedded systems.

Embedded vision architecture tutorial.

Read the full article →

Semi-Conscious: 30 years and no computer vision?

Awesome giant algorithms stuffed into awesome giant hardware!

Lusty venturists, myopic academics, and single-crop semiconductor farmers conspiring for the last of your gas money.

Read the full article →

Vision for Vision

Thumbnail image for Vision for Vision

What happens when computer vision is suddenly available as a platform for applications?

Stellaris computer vision…

Lattice MachXO2 CPLDs are perfect…

Read the full article →