|
Tech Focus: Jumping on the Embedded Vision bandwagon
HIGHLIGHTS
Introduction to embedded vision and the OpenCV library
Seeing is believing, but vision isn't video
Gesture recognition--first step toward 3D UIs?
Editor's Note
Since its founding about eight months ago, the nascent Embedded Vision Alliance has been moving fast: membership has grown to 19 members and includes Analog Devices, BDTI, CEVA, Cognimem, eyeSight, Freescale, Intel, Mathworks. National Instruments and Xilinx.
Its aim is to take what has been learned about vision technology in a variety of industrial and military/aerospace applications and provide the means by which it can be incorporated into a new wave of user-friendly consumer electronics devices. In "My vision for embedded vision," BDTI's Jeff Bier, founder of the Embedded Vision Alliance, describes some of the challenges and opportunities ahead.
But where the initial membership so far is made up mostly of companies who have specialized in embedded vision hardware and software development, the next step for the alliance is to bring those capabilities – and the tools by which to do them - to a broader range of developers in various segments of the consumer electronics, mobile device, and automotive markets..
A major step in this direction is a set of tools described in "Introduction to embedded vision and the OpenCV library," by BDTI's Eric Gregori, my Editor's Top Pick this week. In addition to the Linux- and Windows-focused OpenCV toolsets described, EVA also plans to tailor the tools for Android and is looking to partner with Khronos Group on the development of an API similar to its OpenGL for graphics and OpenCL for parallel programming.
Such tools are coming none too soon for mobile and embedded consumer designs, according to TI's Dong-Ik Ko and Gaurav Agarwal, authors of "Gesture recognition--first step toward 3D UIs?", in which they describe the complex vision processing algorithms that will be needed.
Included in this Tech Focus newsletter are links to a number of recent Embedded.com design articles, white papers, webinars, news, and product stories on various vision technologies and how and where to use them. In addition, below are a few recent embedded vision professional journal and technical conference papers in downloadable PDF form:
OpenCV Based Real-Time Video Processing Using Android
A GPU accelerated face annotation system for smartphones
OpenCV in embedded systems: a performance insight
Self-organizing computer vision for object tracking in smart cameras
Design How-Tos
Introduction to embedded vision and the OpenCV library
BDTI's Eric Gregori explores the opportunities for embedded vision and how to use the open source OpenCV function library to speed creation of embedded vision software. He also reviews available demonstration and development tools.
Building mobile and embedded consumer devices that can "see"
Eldad Melamed of CEVA provides some general guidelines for developing signal processing algorithms that will allow the use of real-time face detection applications on any mobile device.
Gesture recognition--first step toward 3D UIs?
Gesture recognition is the first step to fully 3D interaction with computing devices. The authors outline the challenges and techniques to overcome them in embedded systems.
The challenges of multi-touch gesture interfaces
The key to understanding multi-touch touch panels is to realize that a touch is not the same thing as a mouse click.
Video Cameras and Machine Vision: A Technology Overview
Video technology is playing an increasing role in a number of real-time systems. While many early systems were tied in to standards developed for the broadcast industry, video is now moving out on its own. One of the areas where this is most evident is in machine vision, where systems today use frame sizes and frame rates totally distinct from common broadcast industry standards. This article gives an overview of standard and non-standard video cameras.
Implementation of A 2D Real-Time Correlator Based on a DSP
Image correlation plays an important roll in vision systems and it can be used for autonomous navigation, tracking systems, detection of environment changes, and automatic pattern recognition. The correlation between images must usually be calculated in a very short period of time to be integrated in real-world applications. In this project, the operation of a 2D correlator is tested by implementing a pattern recognition system based on the real-time location of a vehicle model moving along a square-shaped area.
Camera design for machine vision
The fundamental components of machine vision and a close look at camera requirements, including image sensor technology, architecture requirements, interface standards, resolutions, frame rates and signal processing.
Application dictates union between robotics and machine vision
Pairing robotics with machine vision marries industrial muscle to electronic intelligence, creating one of the most powerful automation solutions available to industry today.
Parallel processing architecture brings advanced vision applications to today's cars
Technologies now on the road enable automotive design engineers to implement robust and powerful recognition algorithms, while meeting the stringent automotive power consumption and operational constraints.
Vision Guided Robotics
Vision and robotics systems are able to be programmed within one application with LabVIEW and the ImagingLab Robotics Library for DENSO.
Common Vision Blox V10 enables new dimensions in image processing
Stemmer Imaging announces Version 10 of the Common Vision Blox (CVB) programming library. In addition to its hardware independence and connection flexibility, Version 10 includes support of Microsoft Windows VISTA plus a new, optimised installation routine.
Automotive vision system recognizes road signs: Part 1 - Basic functions
Pattern recognition and processors deal with computational and I/O challenges of handling video data stream.
Advanced interconnects drive intelligent vision applications: Part 1
Platform-centric methodology enables decoupling IP cores for parallel engineering with data flow design, early architecture exploration of data flows to characterize processor performance, and isolation of chip areas for rapid re-engineering of derivatives and updates.
2012 Embedded Market Survey webinar
UBM Electronics' 17th annual survey of embedded systems designers worldwide shows trends in software and hardware usage. The 2012 Embedded Market Survey also looks at languages, productivity, and the challenges design teams rank as most important. A webinar on Friday April 20 will examine the results from over 1,700 respondents from across the embedded industry, the dataset enables a deep analysis to track key changes in this important electronics industry segment. There will also be the opportunity to ask questions online. To register click here.
Products
GE 's new FPDP PMC/XMC module transfers data 30% faster
The SPR507B 4-Channel serial FPDP interface PMC/XMC module from GE Intelligent Platforms is designed for high speed remote data transfer at the industry's fastest rates.
Analog Devices' Blackfin processors feature 1GHz core performance, accelerated vision analytic, and low power consumption
Analog Devices, Inc. has launched a series of 1-GHz, dual-core, Blackfin processors optimized for embedded vision applications.
Touch screen vision sensors with Ethernet connectivity
Banner Engineering introduced the iVu Plus, adding Ethernet connectivity and more advanced inspection capabilities to the iVu's intuitive platform.
Mobileye licenses MIPS core for auto vision system
Collision-avoidance system developer Mobileye has licensed MIPS Technologies' MIPS32 1004K Coherent Processing System for incorporation into Mobileye's next EyeQ vision-based SoC for use in collision-avoidance systems.
NI adds vision capabilities to CompactRIO, Single-Board RIO
National Instruments has added machine vision capabilities to its NI CompactRIO and NI Single-Board RIO hardware devices that provide engineers with an integrated measurement and control platform for industrial and embedded systems, the company said.
|
