TY - CONF T1 - Face tracking in low resolution videos under illumination variations T2 - 2011 18th IEEE International Conference on Image Processing (ICIP) Y1 - 2011 A1 - Zou, W.W.W. A1 - Chellapa, Rama A1 - Yuen, P.C. KW - Adaptation models KW - Computational modeling KW - Face KW - face recognition KW - face tracking KW - GLF-based tracker KW - gradient methods KW - gradient-logarithmic field feature KW - illumination variations KW - lighting KW - low resolution videos KW - low-resolution KW - particle filter KW - particle filter framework KW - particle filtering (numerical methods) KW - Robustness KW - tracking KW - video signal processing KW - Videos KW - Visual face tracking AB - In practical face tracking applications, the face region is often small and affected by illumination variations. We address this problem by using a new feature, namely the Gradient-Logarithmic Field (GLF) feature, in the particle filter framework. The GLF feature is robust under illumination variations and the GLF-based tracker does not assume any model for the face being tracked and is effective in low-resolution video. Experimental results show that the proposed GFL-based tracker works well under significant illumination changes and outperforms some of the state-of-the-art algorithms. JA - 2011 18th IEEE International Conference on Image Processing (ICIP) PB - IEEE SN - 978-1-4577-1304-0 M3 - 10.1109/ICIP.2011.6116672 ER - TY - JOUR T1 - Online Empirical Evaluation of Tracking Algorithms JF - IEEE Transactions on Pattern Analysis and Machine Intelligence Y1 - 2010 A1 - Wu,Hao A1 - Sankaranarayanan,A. C A1 - Chellapa, Rama KW - Back KW - Biomedical imaging KW - Computer vision KW - Filtering KW - formal model validation techniques KW - formal verification KW - ground truth KW - Kanade Lucas Tomasi feature tracker KW - Karhunen-Loeve transforms KW - lighting KW - Markov processes KW - mean shift tracker KW - model validation. KW - online empirical evaluation KW - particle filtering (numerical methods) KW - Particle filters KW - Particle tracking KW - performance evaluation KW - receiver operating characteristic curves KW - Robustness KW - SNR KW - Statistics KW - Surveillance KW - time reversed Markov chain KW - tracking KW - tracking algorithms KW - visual tracking AB - Evaluation of tracking algorithms in the absence of ground truth is a challenging problem. There exist a variety of approaches for this problem, ranging from formal model validation techniques to heuristics that look for mismatches between track properties and the observed data. However, few of these methods scale up to the task of visual tracking, where the models are usually nonlinear and complex and typically lie in a high-dimensional space. Further, scenarios that cause track failures and/or poor tracking performance are also quite diverse for the visual tracking problem. In this paper, we propose an online performance evaluation strategy for tracking systems based on particle filters using a time-reversed Markov chain. The key intuition of our proposed methodology relies on the time-reversible nature of physical motion exhibited by most objects, which in turn should be possessed by a good tracker. In the presence of tracking failures due to occlusion, low SNR, or modeling errors, this reversible nature of the tracker is violated. We use this property for detection of track failures. To evaluate the performance of the tracker at time instant t, we use the posterior of the tracking algorithm to initialize a time-reversed Markov chain. We compute the posterior density of track parameters at the starting time t = 0 by filtering back in time to the initial time instant. The distance between the posterior density of the time-reversed chain (at t = 0) and the prior density used to initialize the tracking algorithm forms the decision statistic for evaluation. It is observed that when the data are generated by the underlying models, the decision statistic takes a low value. We provide a thorough experimental analysis of the evaluation methodology. Specifically, we demonstrate the effectiveness of our approach for tackling common challenges such as occlusion, pose, and illumination changes and provide the Receiver Operating Characteristic (ROC) curves. Finally, we also s how the applicability of the core ideas of the paper to other tracking algorithms such as the Kanade-Lucas-Tomasi (KLT) feature tracker and the mean-shift tracker. VL - 32 SN - 0162-8828 CP - 8 M3 - 10.1109/TPAMI.2009.135 ER - TY - CONF T1 - Tracking via object reflectance using a hyperspectral video camera T2 - 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Y1 - 2010 A1 - Nguyen,Hien Van A1 - Banerjee, A. A1 - Chellapa, Rama KW - Computer vision KW - electronic design KW - hyperspectral datacubes KW - hyperspectral image analysis KW - Hyperspectral imaging KW - Hyperspectral sensors KW - hyperspectral video camera KW - Image motion analysis KW - Image sensors KW - lighting KW - Motion estimation KW - motion prediction KW - Object detection KW - object reflectance tracking KW - random projection KW - Reflectivity KW - robust methods KW - Robustness KW - sensor design KW - spectral detection KW - Surveillance KW - tracking KW - Video surveillance AB - Recent advances in electronics and sensor design have enabled the development of a hyperspectral video camera that can capture hyperspectral datacubes at near video rates. The sensor offers the potential for novel and robust methods for surveillance by combining methods from computer vision and hyperspectral image analysis. Here, we focus on the problem of tracking objects through challenging conditions, such as rapid illumination and pose changes, occlusions, and in the presence of confusers. A new framework that incorporates radiative transfer theory to estimate object reflectance and the mean shift algorithm to simultaneously track the object based on its reflectance spectra is proposed. The combination of spectral detection and motion prediction enables the tracker to be robust against abrupt motions, and facilitate fast convergence of the mean shift tracker. In addition, the system achieves good computational efficiency by using random projection to reduce spectral dimension. The tracker has been evaluated on real hyperspectral video data. JA - 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) PB - IEEE SN - 978-1-4244-7029-7 M3 - 10.1109/CVPRW.2010.5543780 ER - TY - JOUR T1 - Multicamera Tracking of Articulated Human Motion Using Shape and Motion Cues JF - Image Processing, IEEE Transactions on Y1 - 2009 A1 - Sundaresan, A. A1 - Chellapa, Rama KW - 2D shape cues KW - 3D shape cues KW - algorithms KW - Anatomic;Models KW - articulated human motion KW - automatic algorithm KW - Biological;Movement;Posture;Skeleton;Video Recording; KW - Computer-Assisted;Models KW - Eigenvalues and eigenfunctions KW - human pose estimation KW - HUMANS KW - Image motion analysis KW - IMAGE PROCESSING KW - image registration KW - Image segmentation KW - Image sequences KW - kinematic singularity KW - Laplacian eigenmaps KW - multicamera tracking algorithm KW - pixel displacement KW - pose estimation KW - single-frame registration technique KW - temporal registration method KW - tracking AB - We present a completely automatic algorithm for initializing and tracking the articulated motion of humans using image sequences obtained from multiple cameras. A detailed articulated human body model composed of sixteen rigid segments that allows both translation and rotation at joints is used. Voxel data of the subject obtained from the images is segmented into the different articulated chains using Laplacian eigenmaps. The segmented chains are registered in a subset of the frames using a single-frame registration technique and subsequently used to initialize the pose in the sequence. A temporal registration method is proposed to identify the partially segmented or unregistered articulated chains in the remaining frames in the sequence. The proposed tracker uses motion cues such as pixel displacement as well as 2-D and 3-D shape cues such as silhouettes, motion residue, and skeleton curves. The tracking algorithm consists of a predictor that uses motion cues and a corrector that uses shape cues. The use of complementary cues in the tracking alleviates the twin problems of drift and convergence to local minima. The use of multiple cameras also allows us to deal with the problems due to self-occlusion and kinematic singularity. We present tracking results on sequences with different kinds of motion to illustrate the effectiveness of our approach. The pose of the subject is correctly tracked for the duration of the sequence as can be verified by inspection. VL - 18 SN - 1057-7149 CP - 9 M3 - 10.1109/TIP.2009.2022290 ER - TY - CONF T1 - An improved mean shift tracking method based on nonparametric clustering and adaptive bandwidth T2 - Machine Learning and Cybernetics, 2008 International Conference on Y1 - 2008 A1 - Zhuolin Jiang A1 - Li,Shao-Fa A1 - Jia,Xi-Ping A1 - Zhu,Hong-Li KW - adaptive bandwidth KW - appearance model KW - bandwidth matrix KW - Bhattacharyya coefficient KW - color information KW - color space partitioning KW - image colour analysis KW - iterative procedure KW - kernel bandwidth parameter KW - kernel density estimate KW - log-likelihood function KW - mean shift tracking method KW - modified weight function KW - nonparametric clustering KW - Object detection KW - object representation KW - object tracking KW - pattern clustering KW - similarity measure KW - spatial layout KW - target candidate KW - target model KW - tracking AB - An improved mean shift method for object tracking based on nonparametric clustering and adaptive bandwidth is presented in this paper. Based on partitioning the color space of a tracked object by using a modified nonparametric clustering, an appearance model of the tracked object is built. It captures both the color information and spatial layout of the tracked object. The similarity measure between the target model and the target candidate is derived from the Bhattacharyya coefficient. The kernel bandwidth parameters are automatically selected by maximizing the lower bound of a log-likelihood function, which is derived from a kernel density estimate using the bandwidth matrix and the modified weight function. The experimental results show that the method can converge in an average of 2.6 iterations per frame. JA - Machine Learning and Cybernetics, 2008 International Conference on VL - 5 M3 - 10.1109/ICMLC.2008.4620880 ER - TY - CONF T1 - In Situ Evaluation of Tracking Algorithms Using Time Reversed Chains T2 - Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on Y1 - 2007 A1 - Wu,Hao A1 - Sankaranarayanan,A. C A1 - Chellapa, Rama KW - (numerical KW - algorithm;Markov KW - chain;tracking KW - decision KW - density;time KW - detection;particle KW - Evaluation KW - evaluation;object KW - filter;performance KW - Filtering KW - Markov KW - methods);tracking;visual KW - processes;decision KW - reversed KW - servoing; KW - situ KW - statistics;in KW - strategy;posterior KW - systems;visual KW - theory;object KW - tracking KW - tracking;particle AB - Automatic evaluation of visual tracking algorithms in the absence of ground truth is a very challenging and important problem. In the context of online appearance modeling, there is an additional ambiguity involving the correctness of the appearance model. In this paper, we propose a novel performance evaluation strategy for tracking systems based on particle filter using a time reversed Markov chain. Starting from the latest observation, the time reversed chain is propagated back till the starting time t = 0 of the tracking algorithm. The posterior density of the time reversed chain is also computed. The distance between the posterior density of the time reversed chain (at t = 0) and the prior density used to initialize the tracking algorithm forms the decision statistic for evaluation. It is postulated that when the data is generated true to the underlying models, the decision statistic takes a low value. We empirically demonstrate the performance of the algorithm against various common failure modes in the generic visual tracking problem. Finally, we derive a small frame approximation that allows for very efficient computation of the decision statistic. JA - Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on M3 - 10.1109/CVPR.2007.382992 ER - TY - CONF T1 - Object Tracking at Multiple Levels of Spatial Resolutions T2 - Image Analysis and Processing, 2007. ICIAP 2007. 14th International Conference on Y1 - 2007 A1 - Tran,S.D. A1 - Davis, Larry S. KW - coarse-to-fine KW - detection;tracking; KW - filtering;spatial KW - framework;object KW - levels;tracking KW - multiple KW - resolution;multiresolution KW - resolutions KW - searching;data KW - space;computer KW - state KW - tracking KW - tracking;sequential KW - vision;object AB - Tracking is usually performed at a single level of data resolution. This paper describes a multi-resolution tracking framework developed with efficiency and robustness in mind. Efficiency is achieved by processing low resolution data whenever possible. Robustness results from multiple level coarse-to-fine searching in the tracking state space. We combine sequential filtering both in time and resolution levels into a probabilistic framework. A color blob tracker is implemented and the tracking results are evaluated in a number of experiments. JA - Image Analysis and Processing, 2007. ICIAP 2007. 14th International Conference on M3 - 10.1109/ICIAP.2007.4362772 ER - TY - CONF T1 - Robust Object Tracking with Regional Affine Invariant Features T2 - Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on Y1 - 2007 A1 - Tran,Son A1 - Davis, Larry S. KW - affine KW - algorithm;feature KW - analysis;image KW - analysis;pixel KW - consistency;regional KW - detection;motion KW - detection;tracking; KW - extraction;image KW - feature KW - features;robust KW - invariant KW - matching;image KW - MOTION KW - object KW - resolution;object KW - tracking AB - We present a tracking algorithm based on motion analysis of regional affine invariant image features. The tracked object is represented with a probabilistic occupancy map. Using this map as support, regional features are detected and probabilistically matched across frames. The motion of pixels is then established based on the feature motion. The object occupancy map is in turn updated according to the pixel motion consistency. We describe experiments to measure the sensitivities of our approach to inaccuracy in initialization, and compare it with other approaches. JA - Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on M3 - 10.1109/ICCV.2007.4408948 ER - TY - CHAP T1 - Computer Vision, Statistics in T2 - Encyclopedia of Statistical SciencesEncyclopedia of Statistical Sciences Y1 - 2006 A1 - Chellapa, Rama A1 - Chowdhury,Amit K. Roy KW - Computer vision KW - sampling KW - Statistics KW - structure from motion KW - tracking AB - Computer Vision (CV) broadly refers to the discipline where extraction of useful 2D and/or 3D information from one or more images is of interest. Useful information could consist of features such as edges, lines, curves and textures, or information about depth, motion, object descriptions, etc. CV problems are usually ill-posed inverse problems. Since the image data is usually obtained from sensors such as video cameras, infrared, radar, etc., the information extraction processes often have to deal with data that is corrupted by noise from the sensors and the environment. Statistics can help in obtaining robust and accurate solutions to these inverse problems by modeling the noise processes. We present here a broad overview of the applications of statistics to different computer vision problems and explain in detail two particular applications, tracking and motion analysis, where statistical approaches have been used very successfully. JA - Encyclopedia of Statistical SciencesEncyclopedia of Statistical Sciences PB - John Wiley & Sons, Inc. SN - 9780471667193 UR - http://onlinelibrary.wiley.com/doi/10.1002/0471667196.ess3129/abstract ER - TY - JOUR T1 - How Multirobot Systems Research will Accelerate our Understanding of Social Animal Behavior JF - Proceedings of the IEEE Y1 - 2006 A1 - Balch, T. A1 - Dellaert, F. A1 - Feldman, A. A1 - Guillory, A. A1 - Isbell, C.L. A1 - Zia Khan A1 - Pratt, S.C. A1 - Stein, A.N. A1 - Wilde, H. KW - Acceleration KW - Animal behavior KW - ant movement tracking KW - Artificial intelligence KW - biology computing KW - Computer vision KW - control engineering computing KW - Insects KW - Intelligent robots KW - Labeling KW - monkey movement tracking KW - multi-robot systems KW - multirobot systems KW - robotics algorithms KW - Robotics and automation KW - social animal behavior KW - social animals KW - social insect behavior KW - Speech recognition KW - tracking AB - Our understanding of social insect behavior has significantly influenced artificial intelligence (AI) and multirobot systems' research (e.g., ant algorithms and swarm robotics). In this work, however, we focus on the opposite question: "How can multirobot systems research contribute to the understanding of social animal behavior?" As we show, we are able to contribute at several levels. First, using algorithms that originated in the robotics community, we can track animals under observation to provide essential quantitative data for animal behavior research. Second, by developing and applying algorithms originating in speech recognition and computer vision, we can automatically label the behavior of animals under observation. In some cases the automatic labeling is more accurate and consistent than manual behavior identification. Our ultimate goal, however, is to automatically create, from observation, executable models of behavior. An executable model is a control program for an agent that can run in simulation (or on a robot). The representation for these executable models is drawn from research in multirobot systems programming. In this paper we present the algorithms we have developed for tracking, recognizing, and learning models of social animal behavior, details of their implementation, and quantitative experimental results using them to study social insects VL - 94 SN - 0018-9219 CP - 7 ER - TY - CONF T1 - Model-based OpenMP implementation of a 3D facial pose tracking system T2 - 2006 International Conference on Parallel Processing Workshops, 2006. ICPP 2006 Workshops Y1 - 2006 A1 - Saha,S. A1 - Chung-Ching Shen A1 - Chia-Jui Hsu A1 - Aggarwal,G. A1 - Veeraraghavan,A. A1 - Sussman, Alan A1 - Bhattacharyya, Shuvra S. KW - 3D facial pose tracking system KW - application modeling KW - application program interfaces KW - application scheduling KW - coarse-grain dataflow graphs KW - Concurrent computing KW - data flow graphs KW - Educational institutions KW - face recognition KW - IMAGE PROCESSING KW - image processing applications KW - Inference algorithms KW - Message passing KW - OpenMP platform KW - parallel implementation KW - PARALLEL PROCESSING KW - parallel programming KW - Particle tracking KW - Processor scheduling KW - SHAPE KW - shared memory systems KW - shared-memory systems KW - Solid modeling KW - tracking AB - Most image processing applications are characterized by computation-intensive operations, and high memory and performance requirements. Parallelized implementation on shared-memory systems offer an attractive solution to this class of applications. However, we cannot thoroughly exploit the advantages of such architectures without proper modeling and analysis of the application. In this paper, we describe our implementation of a 3D facial pose tracking system using the OpenMP platform. Our implementation is based on a design methodology that uses coarse-grain dataflow graphs to model and schedule the application. We present our modeling approach, details of the implementation that we derived based on this modeling approach, and associated performance results. The parallelized implementation achieves significant speedup, and meets or exceeds the target frame rate under various configurations JA - 2006 International Conference on Parallel Processing Workshops, 2006. ICPP 2006 Workshops PB - IEEE SN - 0-7695-2637-3 M3 - 10.1109/ICPPW.2006.55 ER - TY - CONF T1 - Top-down, bottom-up multivalued default reasoning for identity maintenance T2 - Proceedings of the 4th ACM international workshop on Video surveillance and sensor networks Y1 - 2006 A1 - Shet,Vinay D. A1 - Harwood,David A1 - Davis, Larry S. KW - default logic KW - identity maintenance KW - nonmonotonic reasoning KW - tracking KW - visual surveillance AB - Persistent tracking systems require the capacity to track individuals by maintaining identity across visibility gaps caused by occlusion events. In traditional computer vision systems, the flow of information is typically bottom-up. The low level image processing modules take video input, perform early vision tasks such as background subtraction and object detection,and pass this information to the high level reasoning module. This paper describes the architecture of a system that uses top-down information flow to perform identity maintenance across occlusion events. This system uses the high level reasoning module to provide control feedback to the low level image processing module to perform forensic analysis of archival video and actively acquire information required to arrive at identity decisions. This functionality is in addition to traditional bottom-up reasoning about identity, employing contextual cues and appearance matching, within the multivalued default logic framework proposed in [18]. This framework, in addition to bestowing upon the system the property of nonmonotonicity, also allows for it to qualitatively encode its confidence in the identity decisions it takes. JA - Proceedings of the 4th ACM international workshop on Video surveillance and sensor networks T3 - VSSN '06 PB - ACM CY - New York, NY, USA SN - 1-59593-496-0 UR - http://doi.acm.org/10.1145/1178782.1178795 M3 - 10.1145/1178782.1178795 ER - TY - CONF T1 - Algorithmic and architectural design methodology for particle filters in hardware T2 - Computer Design: VLSI in Computers and Processors, 2005. ICCD 2005. Proceedings. 2005 IEEE International Conference on Y1 - 2005 A1 - Sankaranarayanan,A. C A1 - Chellapa, Rama A1 - Srivastava, A. KW - (numerical KW - algorithmic KW - architectural KW - architectures; KW - bearing KW - complexity; KW - computational KW - design KW - digital KW - evolution; KW - Filtering KW - filtering; KW - filters; KW - implementation; KW - methodology; KW - methods); KW - nonGaussian KW - nonlinear KW - only KW - Parallel KW - particle KW - pipeline KW - pipelined KW - problem; KW - processing; KW - state KW - tracking KW - VLSI KW - VLSI; AB - In this paper, we present algorithmic and architectural methodology for building particle filters in hardware. Particle filtering is a new paradigm for filtering in presence of nonGaussian nonlinear state evolution and observation models. This technique has found wide-spread application in tracking, navigation, detection problems especially in a sensing environment. So far most particle filtering implementations are not lucrative for real time problems due to excessive computational complexity involved. In this paper, we re-derive the particle filtering theory to make it more amenable to simplified VLSI implementations. Furthermore, we present and analyze pipelined architectural methodology for designing these computational blocks. Finally, we present an application using the bearing only tracking problem and evaluate the proposed architecture and algorithmic methodology. JA - Computer Design: VLSI in Computers and Processors, 2005. ICCD 2005. Proceedings. 2005 IEEE International Conference on M3 - 10.1109/ICCD.2005.20 ER - TY - CONF T1 - Efficient mean-shift tracking via a new similarity measure T2 - Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on Y1 - 2005 A1 - Yang,Changjiang A1 - Duraiswami, Ramani A1 - Davis, Larry S. KW - algorithm; KW - analysis; KW - Bhattacharyya KW - coefficient; KW - Color KW - colour KW - density KW - divergence; KW - estimates; KW - extraction; KW - fast KW - feature KW - frame-rate KW - Gauss KW - Gaussian KW - histograms; KW - image KW - Kernel KW - Kullback-Leibler KW - matching; KW - Mean-shift KW - measures; KW - nonparametric KW - processes; KW - sample-based KW - sequences; KW - similarity KW - spaces; KW - spatial-feature KW - tracking KW - tracking; KW - transform; AB - The mean shift algorithm has achieved considerable success in object tracking due to its simplicity and robustness. It finds local minima of a similarity measure between the color histograms or kernel density estimates of the model and target image. The most typically used similarity measures are the Bhattacharyya coefficient or the Kullback-Leibler divergence. In practice, these approaches face three difficulties. First, the spatial information of the target is lost when the color histogram is employed, which precludes the application of more elaborate motion models. Second, the classical similarity measures are not very discriminative. Third, the sample-based classical similarity measures require a calculation that is quadratic in the number of samples, making real-time performance difficult. To deal with these difficulties we propose a new, simple-to-compute and more discriminative similarity measure in spatial-feature spaces. The new similarity measure allows the mean shift algorithm to track more general motion models in an integrated way. To reduce the complexity of the computation to linear order we employ the recently proposed improved fast Gauss transform. This leads to a very efficient and robust nonparametric spatial-feature tracking algorithm. The algorithm is tested on several image sequences and shown to achieve robust and reliable frame-rate tracking. JA - Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on VL - 1 M3 - 10.1109/CVPR.2005.139 ER - TY - CONF T1 - Fast multiple object tracking via a hierarchical particle filter T2 - Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on Y1 - 2005 A1 - Yang,Changjiang A1 - Duraiswami, Ramani A1 - Davis, Larry S. KW - (numerical KW - algorithm; KW - analysis; KW - Color KW - colour KW - Computer KW - Convergence KW - detection; KW - edge KW - fast KW - filter; KW - Filtering KW - hierarchical KW - histogram; KW - image KW - images; KW - integral KW - likelihood; KW - methods); KW - methods; KW - multiple KW - numerical KW - object KW - observation KW - of KW - orientation KW - particle KW - processes; KW - quasirandom KW - random KW - sampling; KW - tracking KW - tracking; KW - vision; KW - visual AB - A very efficient and robust visual object tracking algorithm based on the particle filter is presented. The method characterizes the tracked objects using color and edge orientation histogram features. While the use of more features and samples can improve the robustness, the computational load required by the particle filter increases. To accelerate the algorithm while retaining robustness we adopt several enhancements in the algorithm. The first is the use of integral images for efficiently computing the color features and edge orientation histograms, which allows a large amount of particles and a better description of the targets. Next, the observation likelihood based on multiple features is computed in a coarse-to-fine manner, which allows the computation to quickly focus on the more promising regions. Quasi-random sampling of the particles allows the filter to achieve a higher convergence rate. The resulting tracking algorithm maintains multiple hypotheses and offers robustness against clutter or short period occlusions. Experimental results demonstrate the efficiency and effectiveness of the algorithm for single and multiple object tracking. JA - Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on VL - 1 M3 - 10.1109/ICCV.2005.95 ER - TY - CONF T1 - Pedestrian classification from moving platforms using cyclic motion pattern T2 - IEEE International Conference on Image Processing, 2005. ICIP 2005 Y1 - 2005 A1 - Yang Ran A1 - Qinfen Zheng A1 - Weiss, I. A1 - Davis, Larry S. A1 - Abd-Almageed, Wael A1 - Liang Zhao KW - compact shape representation KW - cyclic motion pattern KW - data mining KW - Detectors KW - digital phase locked loop KW - digital phase locked loops KW - feedback loop module KW - gait analysis KW - gait phase information KW - human body pixel oscillations KW - HUMANS KW - image classification KW - Image motion analysis KW - image representation KW - image sequence KW - Image sequences KW - Motion detection KW - Object detection KW - pedestrian classification KW - pedestrian detection system KW - Phase estimation KW - Phase locked loops KW - principle gait angle KW - SHAPE KW - tracking KW - Videos AB - This paper describes an efficient pedestrian detection system for videos acquired from moving platforms. Given a detected and tracked object as a sequence of images within a bounding box, we describe the periodic signature of its motion pattern using a twin-pendulum model. Then a principle gait angle is extracted in every frame providing gait phase information. By estimating the periodicity from the phase data using a digital phase locked loop (dPLL), we quantify the cyclic pattern of the object, which helps us to continuously classify it as a pedestrian. Past approaches have used shape detectors applied to a single image or classifiers based on human body pixel oscillations, but ours is the first to integrate a global cyclic motion model and periodicity analysis. Novel contributions of this paper include: i) development of a compact shape representation of cyclic motion as a signature for a pedestrian, ii) estimation of gait period via a feedback loop module, and iii) implementation of a fast online pedestrian classification system which operates on videos acquired from moving platforms. JA - IEEE International Conference on Image Processing, 2005. ICIP 2005 PB - IEEE VL - 2 SN - 0-7803-9134-9 M3 - 10.1109/ICIP.2005.1530190 ER - TY - CONF T1 - Tracking objects in video using motion and appearance models T2 - Image Processing, 2005. ICIP 2005. IEEE International Conference on Y1 - 2005 A1 - Sankaranarayanan,A. C A1 - Chellapa, Rama A1 - Qinfen Zheng KW - algorithm; KW - analysis; KW - appearance KW - background KW - estimation; KW - image KW - likelihood KW - maximum KW - model; KW - models; KW - MOTION KW - object KW - processing; KW - signal KW - target KW - tracking KW - tracking; KW - video KW - visual AB - This paper proposes a visual tracking algorithm that combines motion and appearance in a statistical framework. It is assumed that image observations are generated simultaneously from a background model and a target appearance model. This is different from conventional appearance-based tracking, that does not use motion information. The proposed algorithm attempts to maximize the likelihood ratio of the tracked region, derived from appearance and background models. Incorporation of motion in appearance based tracking provides robust tracking, even when the target violates the appearance model. We show that the proposed algorithm performs well in tracking targets efficiently over long time intervals. JA - Image Processing, 2005. ICIP 2005. IEEE International Conference on VL - 2 M3 - 10.1109/ICIP.2005.1530075 ER - TY - CONF T1 - Object tracking by adaptive feature extraction T2 - Image Processing, 2004. ICIP '04. 2004 International Conference on Y1 - 2004 A1 - Han,Bohyung A1 - Davis, Larry S. KW - adaptive KW - algorithm; KW - analysis; KW - colour KW - component KW - extraction; KW - feature KW - feature; KW - heterogeneous KW - image KW - image; KW - likelihood KW - Mean-shift KW - object KW - online KW - principal KW - tracking KW - tracking; AB - Tracking objects in the high-dimensional feature space is not only computationally expensive but also functionally inefficient. Selecting a low-dimensional discriminative feature set is a critical step to improve tracker performance. A good feature set for tracking can differ from frame to frame due to the changes in the background against the tracked object, and due to an on-line algorithm that adaptively determines a advantageous distinctive feature set. In this paper, multiple heterogeneous features are assembled, and likelihood images are constructed for various subspaces of the combined feature space. Then, the most discriminative feature is extracted by principal component analysis (PCA) based on those likelihood images. This idea is applied to the mean-shift tracking algorithm [D. Comaniciu et al., June 2000], and we demonstrate its effectiveness through various experiments. JA - Image Processing, 2004. ICIP '04. 2004 International Conference on VL - 3 M3 - 10.1109/ICIP.2004.1421349 ER - TY - CONF T1 - Robust two-camera tracking using homography T2 - Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on Y1 - 2004 A1 - Yue,Zhanfeng A1 - Zhou,S. K A1 - Chellapa, Rama KW - Carlo KW - filter; KW - filters; KW - frame KW - framework; KW - homography; KW - image KW - method; KW - methods; KW - Monte KW - nonlinear KW - occlusions; KW - optical KW - particle KW - processing; KW - robust KW - sequences; KW - sequential KW - signal KW - statistics; KW - tracking KW - tracking; KW - two KW - two-camera KW - video KW - view KW - visual AB - The paper introduces a two view tracking method which uses the homography relation between the two views to handle occlusions. An adaptive appearance-based model is incorporated in a particle filter to realize robust visual tracking. Occlusion is detected using robust statistics. When there is occlusion in one view, the homography from this view to other views is estimated from previous tracking results and used to infer the correct transformation for the occluded view. Experimental results show the robustness of the two view tracker. JA - Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on VL - 3 M3 - 10.1109/ICASSP.2004.1326466 ER - TY - CONF T1 - Simultaneous background and foreground modeling for tracking in surveillance video T2 - Image Processing, 2004. ICIP '04. 2004 International Conference on Y1 - 2004 A1 - Shao, J. A1 - Zhou,S. K A1 - Chellapa, Rama KW - algorithm; KW - analysis; KW - background-foreground KW - displacement KW - estimation; KW - image KW - information; KW - INTENSITY KW - modeling; KW - MOTION KW - processes; KW - processing; KW - resolution; KW - sequences; KW - signal KW - Stochastic KW - Surveillance KW - surveillance; KW - tracking KW - tracking; KW - video AB - We present a stochastic tracking algorithm for surveillance video where targets are dim and at low resolution. The algorithm builds motion models for both background and foreground by integrating motion and intensity information. Some other merits of the algorithm include adaptive selection of feature points for scene description and defining proper cost functions for displacement estimation. The experimental results show tracking robustness and precision in a challenging video sequences. JA - Image Processing, 2004. ICIP '04. 2004 International Conference on VL - 2 M3 - 10.1109/ICIP.2004.1419483 ER - TY - RPRT T1 - Video-Based Automatic Target Recognition Y1 - 2004 A1 - Zhou,S. K A1 - Chellapa, Rama A1 - Mei,Xue A1 - Wu,Hao A1 - Qinfen Zheng KW - *SEQUENCES(MATHEMATICS) KW - *TARGET RECOGNITION KW - *VEHICLES KW - *VIDEO RECORDING KW - algorithms KW - AUTOMATIC TRACKING. KW - COMPONENT REPORTS KW - MOVING TARGETS KW - SURFACE TRANSPORTATION AND EQUIPMENT KW - SYMPOSIA KW - TARGET CLASSIFICATION KW - TARGET DIRECTION, RANGE AND POSITION FINDING KW - tracking KW - VIDEO SIGNALS AB - We present an approach for vehicle classification in IR video sequences by integrating detection, tracking and recognition. The method has two steps. First, the moving target is automatically detected using a detection algorithm. Next, we perform simultaneous tracking and recognition using an appearance-model based particle filter. The tracking result is evaluated at each frame. Low confidence in tracking performance initiates a new cycle of detection, tracking and classification. We demonstrate the robustness of the proposed method using outdoor IR video sequences. PB - MARYLAND UNIV COLLEGE PARK CENTER FOR AUTOMATION RESEARCH UR - http://stinet.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA431617 ER - TY - JOUR T1 - Visual tracking and recognition using appearance-adaptive models in particle filters JF - IEEE Transactions on Image Processing Y1 - 2004 A1 - Zhou,Shaohua Kevin A1 - Chellapa, Rama A1 - Moghaddam, B. KW - adaptive filters KW - adaptive noise variance KW - algorithms KW - appearance-adaptive model KW - Artificial intelligence KW - Cluster Analysis KW - Computer Graphics KW - Computer simulation KW - Feedback KW - Filtering KW - first-order linear predictor KW - hidden feature removal KW - HUMANS KW - Image Enhancement KW - Image Interpretation, Computer-Assisted KW - image recognition KW - Information Storage and Retrieval KW - Kinematics KW - Laboratories KW - Male KW - Models, Biological KW - Models, Statistical KW - MOTION KW - Movement KW - Noise robustness KW - Numerical Analysis, Computer-Assisted KW - occlusion analysis KW - Particle filters KW - Particle tracking KW - Pattern Recognition, Automated KW - Predictive models KW - Reproducibility of results KW - robust statistics KW - Sensitivity and Specificity KW - Signal Processing, Computer-Assisted KW - State estimation KW - statistical analysis KW - Subtraction Technique KW - tracking KW - Training data KW - visual recognition KW - visual tracking AB - We present an approach that incorporates appearance-adaptive models in a particle filter to realize robust visual tracking and recognition algorithms. Tracking needs modeling interframe motion and appearance changes, whereas recognition needs modeling appearance changes between frames and gallery images. In conventional tracking algorithms, the appearance model is either fixed or rapidly changing, and the motion model is simply a random walk with fixed noise variance. Also, the number of particles is typically fixed. All these factors make the visual tracker unstable. To stabilize the tracker, we propose the following modifications: an observation model arising from an adaptive appearance model, an adaptive velocity motion model with adaptive noise variance, and an adaptive number of particles. The adaptive-velocity model is derived using a first-order linear predictor based on the appearance difference between the incoming observation and the previous particle configuration. Occlusion analysis is implemented using robust statistics. Experimental results on tracking visual objects in long outdoor and indoor video sequences demonstrate the effectiveness and robustness of our tracking algorithm. We then perform simultaneous tracking and recognition by embedding them in a particle filter. For recognition purposes, we model the appearance changes between frames and gallery images by constructing the intra- and extrapersonal spaces. Accurate recognition is achieved when confronted by pose and view variations. VL - 13 SN - 1057-7149 CP - 11 M3 - 10.1109/TIP.2004.836152 ER - TY - CONF T1 - A non-intrusive Kalman filter-based tracker for pursuit eye movement T2 - American Control Conference, 2002. Proceedings of the 2002 Y1 - 2002 A1 - Abd-Almageed, Wael A1 - Fadali,M. S A1 - Bebis,G. KW - Application software KW - characterization KW - Computer vision KW - Current measurement KW - deterministic component KW - Electric variables measurement KW - eye position estimation KW - eye tracking KW - gaze tracking KW - Human computer interaction KW - Kalman filter KW - Kalman filters KW - Lenses KW - Motion estimation KW - Optical reflection KW - pursuit eye movement KW - pursuit motion KW - random component KW - Skin KW - tracking AB - In this paper, we introduce a new non-intrusive approach to estimating the eye position during pursuit motion of the eye. We introduce a new characterization for the pursuit eye movement. Our characterization is based on the decomposition of the pursuit eye motion into a deterministic component and random component. We use a discrete Kalman filter to estimate the random component and calculate the deterministic component. We add the two components to obtain an estimate of the eye position. Simulation results are provided to illustrate the eye position estimation. JA - American Control Conference, 2002. Proceedings of the 2002 PB - IEEE VL - 2 SN - 0-7803-7298-0 UR - http://ieeexplore.ieee.org/ielx5/7965/22015/01023224.pdf?tp=&arnumber=1023224&isnumber=22015 M3 - 10.1109/ACC.2002.1023224 ER - TY - CONF T1 - Estimation of composite object and camera image motion T2 - The Proceedings of the Seventh IEEE International Conference on Computer Vision, 1999 Y1 - 1999 A1 - Yacoob,Yaser A1 - Davis, Larry S. KW - articulated bodies KW - camera image motion KW - camera image motions KW - CAMERAS KW - composite independent object KW - composite object estimation KW - Computer vision KW - Educational institutions KW - Image sequences KW - instantaneous flow measurements KW - Laboratories KW - Layout KW - Motion analysis KW - Motion estimation KW - motion trajectories KW - orthogonal flow bases KW - Principal component analysis KW - spatio-temporal flow models KW - tracking KW - Vehicles AB - An approach for estimating composite independent object and camera image motions is proposed. The approach employs spatio-temporal flow models learned through observing typical movements of the object, to decompose image motion into independent object and camera motions. The spatio-temporal flow models of the object motion are represented as a set of orthogonal flow bases that are learned using principal component analysis of instantaneous flow measurements from a stationary camera. These models are then employed in scenes with a moving camera to extract motion trajectories relative to those learned. The performance of the algorithm is demonstrated on several image sequences of rigid and articulated bodies in motion JA - The Proceedings of the Seventh IEEE International Conference on Computer Vision, 1999 PB - IEEE VL - 1 SN - 0-7695-0164-8 M3 - 10.1109/ICCV.1999.791217 ER - TY - CONF T1 - Tracking rigid motion using a compact-structure constraint T2 - Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on Y1 - 1999 A1 - Yacoob,Yaser A1 - Davis, Larry S. KW - compact-structure constraint KW - image motion KW - Image sequences KW - Motion estimation KW - parameterized flow models KW - polynomial parameterized flow models KW - Polynomials KW - rigid motion tracking KW - rigid object KW - rigidly moving objects KW - structure-compactness constraint KW - tracking AB - An approach for tracking the motion of a rigid object using parameterized flow models and a compact-structure constraint is proposed. While polynomial parameterized flow models have been shown to be effective in tracking the rigid motion of planar objects, these models are inappropriate for tracking moving objects that change appearance revealing their 3D structure. We extend these models by adding a structure-compactness constraint that accounts for image motion that deviates from a planar structure. The constraint is based on the assumption that object structure variations are limited with respect to planar object projection onto the image plane and therefore can be expressed as a direct constraint on the image motion. The performance of the algorithm is demonstrated on several long image sequences of rigidly moving objects JA - Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on VL - 1 M3 - 10.1109/ICCV.1999.791218 ER - TY - CONF T1 - Computing 3-D head orientation from a monocular image sequence T2 - Automatic Face and Gesture Recognition, 1996., Proceedings of the Second International Conference on Y1 - 1996 A1 - Horprasert,T. A1 - Yacoob,Yaser A1 - Davis, Larry S. KW - 3D head orientation computation KW - anthropometric statistics KW - camera plane KW - coarse structure KW - eye KW - eye boundary KW - eye corners KW - face features KW - face recognition KW - Feature extraction KW - head pitch KW - head roll KW - head yaw KW - Image sequences KW - image-based parameterized tracking KW - monocular image sequence KW - projective cross-ratio invariance KW - sub-pixel parameterized shape estimation KW - tracking AB - An approach for estimating 3D head orientation in a monocular image sequence is proposed. The approach employs recently developed image-based parameterized tracking for face and face features to locate the area in which a sub-pixel parameterized shape estimation of the eye's boundary is performed. This involves tracking of five points (four at the eye corners and the fifth is the lip of the nose). The authors describe an approach that relies on the coarse structure of the face to compute orientation relative to the camera plane. Our approach employs projective invariance of the cross-ratios of the eye corners and anthropometric statistics to estimate the head yaw, roll and pitch. Analytical and experimental results are reported JA - Automatic Face and Gesture Recognition, 1996., Proceedings of the Second International Conference on M3 - 10.1109/AFGR.1996.557271 ER - TY - JOUR T1 - Recognizing human facial expressions from long image sequences using optical flow JF - IEEE Transactions on Pattern Analysis and Machine Intelligence Y1 - 1996 A1 - Yacoob,Yaser A1 - Davis, Larry S. KW - Computer vision KW - Eyebrows KW - face recognition KW - facial dynamics KW - Facial features KW - human facial expression recognition KW - HUMANS KW - Image motion analysis KW - image recognition KW - image representation KW - Image sequences KW - Motion analysis KW - Motion estimation KW - Optical computing KW - optical flow KW - symbolic representation KW - tracking AB - An approach to the analysis and representation of facial dynamics for recognition of facial expressions from image sequences is presented. The algorithms utilize optical flow computation to identify the direction of rigid and nonrigid motions that are caused by human facial expressions. A mid-level symbolic representation motivated by psychological considerations is developed. Recognition of six facial expressions, as well as eye blinking, is demonstrated on a large set of image sequences VL - 18 SN - 0162-8828 CP - 6 M3 - 10.1109/34.506414 ER - TY - CONF T1 - Perceptual computational advantages of tracking T2 - , 11th IAPR International Conference on Pattern Recognition, 1992. Vol.I. Conference A: Computer Vision and Applications, Proceedings Y1 - 1992 A1 - Fermüller, Cornelia A1 - Aloimonos, J. KW - active vision KW - Automation KW - Employment KW - fixation KW - image intensity function KW - Image motion analysis KW - IMAGE PROCESSING KW - Motion estimation KW - Nonlinear optics KW - Optical computing KW - Optical sensors KW - parameter estimation KW - pattern recognition KW - perceptual computational advantages KW - spatiotemporal derivatives KW - Spatiotemporal phenomena KW - tracking KW - unrestricted motion KW - visual flow measurements AB - The paradigm of active vision advocates studying visual problems in the form of modules that are directly related to a visual task for observers that are active. It is argued that in many cases when an object is moving in an unrestricted manner (translation and rotation) in the 3D world only the motion's translational components are of interest. For a monocular observer, using only the normal flow-the spatiotemporal derivatives of the image intensity function-the authors solve the problem of computing the direction of translation. Their strategy uses fixation and tracking. Fixation simplifies much of the computation by placing the object at the center of the visual field, and the main advantage of tracking is the accumulation of information over time. The authors show how tracking is accomplished using normal flow measurements and use it for two different tasks in the solution process. First, it serves as a tool to compensate for the lack of existence of an optical flow field and thus to estimate the translation parallel to the image plane; and second, it gathers information about the motion component perpendicular to the image plane JA - , 11th IAPR International Conference on Pattern Recognition, 1992. Vol.I. Conference A: Computer Vision and Applications, Proceedings PB - IEEE SN - 0-8186-2910-X M3 - 10.1109/ICPR.1992.201633 ER -