On pedestrian detection and tracking in infrared videos
Pattern Recognition LettersPublished 31 December 2011
Jiangtao Wang, Debao Chen, Haiyan Chen, Jingyu Yang
Citations71
SJR quartileQ1
SJR score1.00
SNIP1.43
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
After detecting the pedestrian based on the SVM classifier, a multi-cues fusing algorithm is provided to facilitate the task of pedestrian tracking using both edge feature and intensity feature under the particle filter framework.
Abstract
This article presents an approach for pedestrian detection and tracking from infrared imagery. The GMM background model is first deployed to separate the foreground candidates from background, then a shape describer is introduced to construct the feature vector for pedestrian candidates, and a SVM classifier is trained based on datasets generated from infrared images or manually. After detecting the pedestrian based on the SVM classifier, a multi-cues fusing algorithm is provided to facilitate the task of pedestrian tracking using both edge feature and intensity feature under the particle filter framework. Experimental results with various Infrared Video Database are reported to demonstrate the accuracy and robustness of our algorithm.
Keywords
Computer ScienceEngineering
IEE Proceedings F Radar and Signal ProcessingNovel approach to nonlinear/non-Gaussian Bayesian state estimation
7,588 Citations1993Neil Gordon, David Salmond +1 more
An algorithm, the bootstrap filter, is proposed for implementing recursive Bayesian filters, represented as a set of random samples, which are updated and propagated by the algorithm.
Adaptive background mixture models for real-time tracking
6,930 Citations2003Chris Stauffer, W. Eric L. Grimson
This paper discusses modeling each pixel as a mixture of Gaussians and using an on-line approximation to update the model, resulting in a stable, real-time outdoor tracker which reliably deals with lighting changes, repetitive motions from clutter, and long-term scene changes.
International Journal of Computer VisionCONDENSATION—Conditional Density Propagation for Visual Tracking
4,885 Citations1998Michael Isard, Andrew Blake
The Condensation algorithm uses “factored sampling”, previously applied to the interpretation of static images, in which the probability distribution of possible interpretations is represented by a randomly generated set.
IEEE Transactions on Pattern Analysis and Machine IntelligenceKernel-based object tracking
4,565 Citations2003Dorin Comaniciu, Visvanathan Ramesh +1 more
A new approach toward target representation and localization, the central component in visual tracking of nonrigid objects, is proposed, which employs a metric derived from the Bhattacharyya coefficient as similarity measure, and uses the mean shift procedure to perform the optimization.
International Journal of Computer VisionIncremental Learning for Robust Visual Tracking
3,101 Citations2007David A. Ross, Jongwoo Lim +2 more
A tracking method that incrementally learns a low-dimensional subspace representation, efficiently adapting online to changes in the appearance of the target, and includes a method for correctly updating the sample mean and a forgetting factor to ensure less modeling power is expended fitting older observations.
Real-time tracking of non-rigid objects using mean shift
2,913 Citations2002Dorin Comaniciu, Visvanathan Ramesh +1 more
The theoretical analysis of the approach shows that it relates to the Bayesian framework while providing a practical, fast and efficient solution for real time tracking of non-rigid objects seen from a moving camera.
IEEE Transactions on Pattern Analysis and Machine IntelligenceOnline selection of discriminative tracking features
1,217 Citations2005Robert T. Collins, Yanxi Liu +1 more
This paper presents an online feature selection mechanism for evaluating multiple features while tracking and adjusting the set of features used to improve tracking performance, and notes susceptibility of the variance ratio feature selection method to distraction by spatially correlated background clutter.
IEEE Transactions on Pattern Analysis and Machine IntelligenceMonocular Pedestrian Detection: Survey and Experiments
1,217 Citations2008Markus Enzweiler, Dariu M. Gavrila
An overview of the current state of the art of pedestrian detection from both methodological and experimental perspectives is provided and a clear advantage of HOG/linSVM at higher image resolutions and lower processing speeds is indicated.
Image and Vision ComputingAn adaptive color-based particle filter
1,153 Citations2003Katja Nummiaro, Esther Koller-Meier +1 more
The integration of color distributions into particle filtering, which has typically been used in combination with edge-based image features, is presented, as they are robust to partial occlusion, are rotation and scale invariant and computationally efficient.
IEEE Transactions on Pattern Analysis and Machine IntelligenceRobust online appearance models for visual tracking
924 Citations2003Allan D. Jepson, David J. Fleet +1 more
Proceedings of the IEEEData Fusion for Visual Tracking With Particles
466 Citations2004Patrick Pérez, J. Vermaak +1 more
Generic importance sampling mechanisms for data fusion are introduced and it is shown how each of the three cues can be modeled by an appropriate data likelihood function, and how the intermittent cues are best handled by generating proposal distributions from their likelihood functions.
Efficient Mean-Shift Tracking via a New Similarity Measure
312 Citations2005Changjiang Yang, Ramani Duraiswami +1 more
A new, simple-to-compute and more discriminative similarity measure in spatial-feature spaces allows the mean shift algorithm to track more general motion models in an integrated way and is tested on several image sequences and shown to achieve robust and reliable frame-rate tracking.
Neural ComputationDemocratic Integration: Self-Organized Integration of Adaptive Cues
173 Citations2001Jochen Triesch, Christoph von der Malsburg
A new architecture for adaptively integrating different cues in a self-organized manner called Democratic Integration is proposed, in which discordant cues are quickly suppressed and recalibrated, while cues having been consistent with the result in the recent past are given a higher weight in the future.
Machine Vision and ApplicationsTowards robust multi-cue integration for visual tracking
154 Citations2003Martin Spengler, Bernt Schiele
It is argued that the principles of sensor and model integration can increase the robustness of today's computer-vision systems substantially and, as an example, multi-cue tracking of faces is discussed.
Image and Vision ComputingSequential Monte Carlo tracking by fusing multiple cues in video sequences
150 Citations2006Paul Brasnett, Lyudmila Mihaylova +2 more
It is shown that tracking with multiple weighted cues provides more reliable performance than single cue tracking.
IEEE Transactions on Vehicular TechnologyA Shape-Independent Method for Pedestrian Detection With Far-Infrared Images
141 Citations2004Yongcong Fang, Kenta Yamada +3 more
A shape-independent pedestrian-detection system that needs only one pedestrian template-corresponding to a generic walking pose-and avoids brute-force searching for pedestrians throughout whole images, which typically involves brightness-similarity comparisons between candidate image patches and a multiplicity of pedestrian templates.
International Journal of Computer VisionRobust Visual Tracking by Integrating Multiple Cues Based on Co-Inference Learning
135 Citations2004Ying Wu, Thomas S. Huang
This paper formulates the problem of multiple cue integration and tracking in a probabilistic framework based on a factorized graphical model and proposes a sequential Monte Carlo algorithm to provide an efficient simulation and approximation of the co-inferencing of multiple cues.
Computer Vision and Image UnderstandingPedestrian detection and tracking in infrared imagery using shape and appearance
118 Citations2006Congxia Dai, Yunfei Zheng +1 more
A layered representation is first introduced and a generalized expectation-maximization (EM) algorithm is developed to separate infrared images into background (still) and foreground (moving) layers regardless of camera panning to facilitate pedestrian tracking.
Computer Vision and Image UnderstandingPedestrian detection by means of far-infrared stereo vision
113 Citations2007Massimo Bertozzi, Alberto Broggi +4 more
A stereo system for the detection of pedestrians using far-infrared cameras that exploits three different detection approaches: warm area detection, edge-based detection, and disparity computation.
Machine Vision and ApplicationsThermo-visual feature fusion for object tracking using multiple spatiogram trackers
94 Citations2007Ciarán Ó Conaire, Noel E. O’Connor +1 more
A mean-shift type algorithm is derived for the framework that allows efficient object tracking with very low computational overhead and especially targets the fusion of thermal infrared and visible spectrum features as the most useful features for automated surveillance applications.
The International Journal of Robotics ResearchA Fast Stereo-based System for Detecting and Tracking Pedestrians from a Moving Vehicle
76 Citations2009Max Bajracharya, Baback Moghaddam +3 more
A fully integrated system for detecting, localizing, and tracking pedestrians from a moving vehicle that can reliably detect upright pedestrians to a range of 40 m in lightly cluttered urban environments and on a diverse set of datasets with groundtruth in outdoor environments with varying degrees of pedestrian density and clutter.
Probabilistic Multiple Cue Integration for Particle Filter Based Tracking
71 Citations2003Chunhua Shen, Anton van den Hengel +2 more
This paper demonstrates how the combination of multiple cue integration and particle filtering results in a robust track- ing method and demonstrates how each cue's weight can be adapted on-line during the tracking procedure.
An adaptive fusion architecture for target tracking
68 Citations2003Gareth Loy, Luke Fletcher +2 more
A vision system is demonstrated that adaptively allocates computational resources over multiple cues to robustly track a target in 3D using a particle filter to maintain multiple hypotheses of the target location.
Lecture notes in computer scienceImage Cues Fusion for Object Tracking Based on Particle Filter
27 Citations2004Peihua Li, François Chaumette
A color likelihood to capture color distribution of the object based on Bhattacharry coefficient, and a structure likelihood representing high level knowledge regarding the object represent a straightforward image cues fusion for object tracking in the framework of particle filter.
Efficient Visual Tracking by Probabilistic Fusion of Multiple Cues
19 Citations2006Hanzi Wang, David Suter
A novel shape similarity measure which includes the spatial distribution of the number of and the gradient intensity of the edge points is proposed which is integrated with the recently proposed SMOG-based color similarity measure in the framework of particle filter (PF).
Robust observations for object tracking
13 Citations2005Bohyung Han, L.S. Davis
This paper proposes an adaptive observation enhancement technique based on likelihood images, which are derived from multiple visual features, which contribute to more robust observations through demonstrations.