Robust feature extraction algorithm suitable for real-time embedded applications

Smart cameras integrate processing close to the image sensor, so they can deliver high-level information to a host computer or high-level decision process. One of the most common processing is the visual features extraction since many vision-based use-cases are based on such algorithm. Unfortunately...

Full description

Saved in:
Bibliographic Details
Published in:Journal of real-time image processing 2018-03, Vol.14 (3), p.647-665
Main Authors: Aguilar-González, Abiel, Arias-Estrada, Miguel, Berry, François
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Calibration
Cameras
Computer Graphics
Computer Science
Computer Vision and Pattern Recognition
Computers
Embedded systems
Feature extraction
Field programmable gate arrays
Hardware Architecture
Image Processing and Computer Vision
Localization
Multimedia Information Systems
Pattern Recognition
Pixels
Real time
Robotics
Robustness
Signal,Image and Speech Processing
Special Issue Paper
Surveillance
Systems design
Vision systems
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Smart cameras integrate processing close to the image sensor, so they can deliver high-level information to a host computer or high-level decision process. One of the most common processing is the visual features extraction since many vision-based use-cases are based on such algorithm. Unfortunately, in most of cases, features detection algorithms are not robust or do not reach real-time processing. Based on these limitations, a feature detection algorithm that is robust enough to deliver robust features under any type of indoor/outdoor scenarios is proposed. This was achieved by applying a non-textured corner filter combined to a subpixel refinement. Furthermore, an FPGA architecture is proposed. This architecture allows compact system design, real-time processing for Full HD images (it can process up to 44 frames/91.238.400 pixels per second for Full HD images), and high efficiency for smart camera implementations (similar hardware resources than previous formulations without subpixel refinement and without non-textured corner filter). For accuracy/robustness, experimental results for several real-world scenes are encouraging and show the feasibility of our algorithmic approach.
ISSN:1861-8200
1861-8219
DOI:10.1007/s11554-017-0701-8