Tracking failure detection by imitating human visual perception

In this paper, we present a tracking failure detection method by imitating human visual system. By adopting log-polar transformation, we could simulate properties of retina image, such as rotation and scaling invariance and foveal predominance. The rotation and scaling invariance helps to reduce fal...

Full description

Saved in:
Bibliographic Details
Main Authors: Hyung Jin Chang, Myoung Soo Park, Hawook Jeong, Jin Young Choi
Format: Conference Proceeding
Language:English
Subjects:
Adaptation models
Current measurement
Gaussian Mixture Model
Human visual system
Humans
Image color analysis
Log-Polar transform
Retina
Target tracking
Tracking failure detection
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we present a tracking failure detection method by imitating human visual system. By adopting log-polar transformation, we could simulate properties of retina image, such as rotation and scaling invariance and foveal predominance. The rotation and scaling invariance helps to reduce false alarms caused by pose changes and intensify translational changes. Foveal predominant property helps to detect the tracking failing moment by amplifying the resolution around focus (tracking box center) and blurring the peripheries. Each ganglion cell corresponds to a pixel of log-polar image, and its adaptation is modeled as Gaussian mixture model. Its validity is shown through various experiments.
ISSN:1522-4880
2381-8549
DOI:10.1109/ICIP.2011.6116374