• Home
  • Search
  • A Probability-Based Object Tracking Method
  • https://doi.org/10.1007/978-3-642-42057-3_75Copy DOI Icon

A Probability-Based Object Tracking Method

  • Jan 1, 2013
  • Xu Song +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Abstract Here we take advantage of the signal recovery power of Compressive Sensing (CS) to significantly reduce the computational complexity brought by the high-dimension image data, then an effective and efficient low-dimensional subspace representation of the object is computing by applying Principal Component Analysis (PCA) to a collection of object observations which are low-dimensional vectors derived from CS. An incremental PCA algorithm is used to update this subspace model for characterizing the object appearance changes. Meanwhile, two distances derived from Probabilistic Principal Component Analysis (PPCA): distance from feature space (DFFS) and distance in feature space (DIFS), are used to describe visual similarity between the learned subspace representation model and candidate targets. Comparing with the traditional used reconstruction error, the sum of two distances: DFFS + DIFS, is more accurate and more robust to noises and partial occlusions. Numerous experiment demonstrate that subspace representation model can handle the situation that target objects experience pose changes, scale changes, significant illumination variation, partial occlusions and so on.Keywordsobject trackingPPCAsubspace representation modelparticle filterdynamic modelobservation modelCompressive Sensing (CS)

Similar Papers
  • Research Article
  • Citations34

Robust object tracking using semi-supervised appearance dictionary learning

  • Apr 30, 2015
  • Pattern Recognition Letters
  • Lei Zhang +4
  • Research Article

Application of Bayesian Inference Model Variational Bayesian Principal Component Analysis (VBPCA) for Handling Missing Data in Principal Component Analysis

  • Jun 30, 2016
  • Jurnal Aplikasi Statistika & Komputasi Statistik
  • Ricky Yordani
  • Book Chapter

PCA-Based Appearance Template Learning for Contour Tracking

  • Jan 01, 2013
  • Bo Ma +3
  • Conference Article
  • Citations24

Comparison on PPCA, KPPCA and MPPCA Based Missing Data Imputing for Traffic Flow

  • Jun 11, 2013
  • Yuebiao Li +4
  • Conference Article
  • Citations106

Fast and robust CAMShift tracking

  • Jun 01, 2010
  • David Exner +4
  • Conference Article
  • Citations5

Using the EnKF with Kernel Methods for Estimation of Non-Gaussian Variables

  • Sep 08, 2008
  • Proceedings
  • J.G Vabø +3
  • Conference Article
  • Citations5

Aerodynamic Model Reconstruction via Probabilistic Principal Component Analysis

  • Jan 07, 2008
  • 46th AIAA Aerospace Sciences Meeting and Exhibit
  • Kyunghoon Lee +2
  • PDF
  • Research Article
  • Citations11

A fast MEANSHIFT algorithm-based target tracking system.

  • Jun 13, 2012
  • Sensors
  • Jian Sun
  • PDF
  • Research Article
  • Citations4

A Probabilistic Fusion Methodology for Face Recognition

  • Oct 23, 2005
  • EURASIP Journal on Advances in Signal Processing
  • K Srinivasa Rao +1
  • Conference Article
  • Citations2

OLAT Gaussians for Generic Relightable Appearance Acquisition

  • Dec 03, 2024
  • Zhiyi Kuang +5
  • PDF
  • Research Article
  • Citations10

Multitask Multisource Deep Correlation Filter for Remote Sensing Data Fusion

  • Jan 01, 2020
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Xu Cheng +3
  • Conference Article
  • Citations45

Anomaly Detection Using an Ensemble of Feature Models

  • Dec 01, 2010
  • Keith Noto +2
  • Conference Article

Kernelized convex hull for visual tracking

  • Dec 01, 2017
  • Jun Wang +3
  • Research Article

Interest-driven Deep Multi-modal Clustering

  • Mar 14, 2026
  • Guoliang Zou +5
  • Research Article
  • Citations36

An Identity-Preserved Model for Face Sketch-Photo Synthesis

  • Jan 01, 2020
  • IEEE Signal Processing Letters
  • Ye Lin +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.