Likelihood map fusion for visual object tracking

Zhaozheng Yin, Fatih Porikli, Robert Collins

Research output: Chapter in Book/Report/Conference proceedingConference contribution

42 Citations (Scopus)

Abstract

Visual object tracking can be considered as a figure-ground classification task. In this paper, different features are used to generate a set of likelihood maps for each pixel indicating the probability of that pixel belonging to foreground object or scene background. For example, intensity, texture, motion, saliency and template matching can all be used to generate likelihood maps. We propose a generic likelihood map fusion framework to combine these heterogeneous features into a fused soft segmentation suitable for mean-shift tracking. All the component likelihood maps contribute to the segmentation based on their classification confidence scores (weights) learned from the previous frame. The evidence combination framework dynamically updates the weights such that, in the fused likelihood map, discriminative foreground/background information is preserved while ambiguous information is suppressed. The framework is applied here to track ground vehicles from thermal airborne video, and is also compared to other state-of-the-art algorithms.

Original languageEnglish (US)
Title of host publication2008 IEEE Workshop on Applications of Computer Vision, WACV
DOIs
StatePublished - Sep 8 2008
Event2008 IEEE Workshop on Applications of Computer Vision, WACV - Copper Mountain, CO, United States
Duration: Jan 7 2008Jan 9 2008

Publication series

Name2008 IEEE Workshop on Applications of Computer Vision, WACV

Other

Other2008 IEEE Workshop on Applications of Computer Vision, WACV
CountryUnited States
CityCopper Mountain, CO
Period1/7/081/9/08

Fingerprint

Fusion reactions
Pixels
Ground vehicles
Template matching
Textures

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Cite this

Yin, Z., Porikli, F., & Collins, R. (2008). Likelihood map fusion for visual object tracking. In 2008 IEEE Workshop on Applications of Computer Vision, WACV [4544036] (2008 IEEE Workshop on Applications of Computer Vision, WACV). https://doi.org/10.1109/WACV.2008.4544036
Yin, Zhaozheng ; Porikli, Fatih ; Collins, Robert. / Likelihood map fusion for visual object tracking. 2008 IEEE Workshop on Applications of Computer Vision, WACV. 2008. (2008 IEEE Workshop on Applications of Computer Vision, WACV).
@inproceedings{781608c5ed514a7db76714144efaca77,
title = "Likelihood map fusion for visual object tracking",
abstract = "Visual object tracking can be considered as a figure-ground classification task. In this paper, different features are used to generate a set of likelihood maps for each pixel indicating the probability of that pixel belonging to foreground object or scene background. For example, intensity, texture, motion, saliency and template matching can all be used to generate likelihood maps. We propose a generic likelihood map fusion framework to combine these heterogeneous features into a fused soft segmentation suitable for mean-shift tracking. All the component likelihood maps contribute to the segmentation based on their classification confidence scores (weights) learned from the previous frame. The evidence combination framework dynamically updates the weights such that, in the fused likelihood map, discriminative foreground/background information is preserved while ambiguous information is suppressed. The framework is applied here to track ground vehicles from thermal airborne video, and is also compared to other state-of-the-art algorithms.",
author = "Zhaozheng Yin and Fatih Porikli and Robert Collins",
year = "2008",
month = "9",
day = "8",
doi = "10.1109/WACV.2008.4544036",
language = "English (US)",
isbn = "1424419131",
series = "2008 IEEE Workshop on Applications of Computer Vision, WACV",
booktitle = "2008 IEEE Workshop on Applications of Computer Vision, WACV",

}

Yin, Z, Porikli, F & Collins, R 2008, Likelihood map fusion for visual object tracking. in 2008 IEEE Workshop on Applications of Computer Vision, WACV., 4544036, 2008 IEEE Workshop on Applications of Computer Vision, WACV, 2008 IEEE Workshop on Applications of Computer Vision, WACV, Copper Mountain, CO, United States, 1/7/08. https://doi.org/10.1109/WACV.2008.4544036

Likelihood map fusion for visual object tracking. / Yin, Zhaozheng; Porikli, Fatih; Collins, Robert.

2008 IEEE Workshop on Applications of Computer Vision, WACV. 2008. 4544036 (2008 IEEE Workshop on Applications of Computer Vision, WACV).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Likelihood map fusion for visual object tracking

AU - Yin, Zhaozheng

AU - Porikli, Fatih

AU - Collins, Robert

PY - 2008/9/8

Y1 - 2008/9/8

N2 - Visual object tracking can be considered as a figure-ground classification task. In this paper, different features are used to generate a set of likelihood maps for each pixel indicating the probability of that pixel belonging to foreground object or scene background. For example, intensity, texture, motion, saliency and template matching can all be used to generate likelihood maps. We propose a generic likelihood map fusion framework to combine these heterogeneous features into a fused soft segmentation suitable for mean-shift tracking. All the component likelihood maps contribute to the segmentation based on their classification confidence scores (weights) learned from the previous frame. The evidence combination framework dynamically updates the weights such that, in the fused likelihood map, discriminative foreground/background information is preserved while ambiguous information is suppressed. The framework is applied here to track ground vehicles from thermal airborne video, and is also compared to other state-of-the-art algorithms.

AB - Visual object tracking can be considered as a figure-ground classification task. In this paper, different features are used to generate a set of likelihood maps for each pixel indicating the probability of that pixel belonging to foreground object or scene background. For example, intensity, texture, motion, saliency and template matching can all be used to generate likelihood maps. We propose a generic likelihood map fusion framework to combine these heterogeneous features into a fused soft segmentation suitable for mean-shift tracking. All the component likelihood maps contribute to the segmentation based on their classification confidence scores (weights) learned from the previous frame. The evidence combination framework dynamically updates the weights such that, in the fused likelihood map, discriminative foreground/background information is preserved while ambiguous information is suppressed. The framework is applied here to track ground vehicles from thermal airborne video, and is also compared to other state-of-the-art algorithms.

UR - http://www.scopus.com/inward/record.url?scp=50849138898&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=50849138898&partnerID=8YFLogxK

U2 - 10.1109/WACV.2008.4544036

DO - 10.1109/WACV.2008.4544036

M3 - Conference contribution

AN - SCOPUS:50849138898

SN - 1424419131

SN - 9781424419135

T3 - 2008 IEEE Workshop on Applications of Computer Vision, WACV

BT - 2008 IEEE Workshop on Applications of Computer Vision, WACV

ER -

Yin Z, Porikli F, Collins R. Likelihood map fusion for visual object tracking. In 2008 IEEE Workshop on Applications of Computer Vision, WACV. 2008. 4544036. (2008 IEEE Workshop on Applications of Computer Vision, WACV). https://doi.org/10.1109/WACV.2008.4544036