Real-time vision systems
- Lawrence Livermore National Lab., CA (United States)
Many industrial and defence applications require an ability to make instantaneous decisions based on sensor input of a time varying process. Such systems are referred to as `real-time systems` because they process and act on data as it occurs in time. When a vision sensor is used in a real-time system, the processing demands can be quite substantial, with typical data rates of 10-20 million samples per second. A real-time Machine Vision Laboratory (MVL) was established in FY94 to extend our years of experience in developing computer vision algorithms to include the development and implementation of real-time vision systems. The laboratory is equipped with a variety of hardware components, including Datacube image acquisition and processing boards, a Sun workstation, and several different types of CCD cameras, including monochrome and color area cameras and analog and digital line-scan cameras. The equipment is reconfigurable for prototyping different applications. This facility has been used to support several programs at LLNL, including O Division`s Peacemaker and Deadeye Projects as well as the CRADA with the U.S. Textile Industry, CAFE (Computer Aided Fabric Inspection). To date, we have successfully demonstrated several real-time applications: bullet tracking, stereo tracking and ranging, and web inspection. This work has been documented in the ongoing development of a real-time software library.
- Research Organization:
- Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
- OSTI ID:
- 145961
- Report Number(s):
- CONF-9411140-Absts.; ON: DE95017252; TRN: 95:007225-0011
- Resource Relation:
- Conference: Imaging sciences workshop, Livermore, CA (United States), 15-16 Nov 1994; Other Information: PBD: 15 Nov 1994; Related Information: Is Part Of Imaging sciences workshop; Candy, J.V.; PB: 101 p.
- Country of Publication:
- United States
- Language:
- English
Similar Records
Quality Control by Artificial Vision
R and DE Robotic Sensor Intern Team: Advanced Sensor Suite Prototype