Feature-Based Resource Allocation for Real-Time Stereo Disparity Estimation

Feature-Based Resource Allocation for Real-Time Stereo Disparity Estimation

The most accurate stereo disparity algorithms take dozens or hundreds of seconds to process a single frame. This timescale is impractical for many applications. However, high accuracy is often not needed throughout the scene. Here, we investigate a “foveation”approach (in which...

Full description

Bibliographic Details
Main Authors: Eric Hunsberger, Victor Reyes Osorio, Jeff Orchard, Bryan P. Tripp
Format: Article
Language:English
Published: IEEE 2017-01-01
Series:IEEE Access
Subjects:
Stereo vision
disparity
convolutional neural networks
Markov random fields
belief propagation
fovea
Online Access:https://ieeexplore.ieee.org/document/7938604/

Internet

https://ieeexplore.ieee.org/document/7938604/

Similar Items