Motion Vision: design of compact motion sensing solutions for navigation of autonomous systems

Buy e-book PDF
(plus tax if applicable)
Buy print edition
image of Motion Vision: design of compact motion sensing solutions for navigation of autonomous systems
Author(s): J. Kolodko  and  L. Vlacic
Publication Year: 2005

Segmenting the environment surrounding an autonomous vehicle into coherently moving regions is a vital first step towards intelligent autonomous navigation. Without this temporal information, navigation becomes a simple obstacle avoidance scheme that is inappropriate in highly dynamic environments such as roadways and places where many people congregate. The book begins by looking at the problem of motion estimation from biological, algorithmic and digital perspectives. It goes on to describe an algorithm that fits with the motion processing model, and hardware and software constraints. This algorithm is based on the optical flow constraint equation and introduces range information to resolve the depth-velocity ambiguity, which is critical for autonomous navigation. Finally, implementation of the algorithm in digital hardware is described in detail, covering both the initial motion processing model and the chosen hardware platforms, and the global functional structure of the system.

Inspec keywords: sensors; hardware description languages; radionavigation; motion estimation; field programmable gate arrays

Other keywords: FPGA design; VHDL hardware description language; autonomous system; real-time motion estimation problem; motion estimation theory; motion vision; motion estimation algorithm; autonomous navigation; sensor design; motion sensing solution

Subjects: Computer vision and image processing techniques; Radionavigation and direction finding; Optical, image and video signal processing; Sensing devices and transducers; Logic design methods; Electronic engineering computing; Logic and switching circuits; Logic circuits

Related content

This is a required field
Please enter a valid email address