Visual Odometry Using Commodity Optical Flow

13 years 5 months ago

Download www.cs.cmu.edu

A wide variety of techniques for visual navigation using robot-mounted cameras have been described over the past several decades, yet adoption of optical flow navigation techniques has been slow. This demo illustrates what visual navigation has to offer: robust hazard detection (including precipices and obstacles), high-accuracy open-loop odometry, and stable closed-loop motion control implemented via an optical flow based visual odometry system. This work is based on 1) open source vision code, 2) common computing hardware, and 3) inexpensive, consumer-quality cameras, and as such should be accessible to many robot builders. Demo Overview Optical flow field and camera ego-motion estimation have been the subject of much research for over 30 years, but this research has seen limited use. For many years this could be attributed to the high computational cost of the known techniques, but modern PCs and embedded systems have been sufficiently powerful to enable real-time optical flow anal...

Jason Campbell, Rahul Sukthankar, Illah R. Nourbak

Real-time Traffic