TY - JOUR T1 - Applications of a Simple Characterization of Human Gait in Surveillance JF - Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on Y1 - 2010 A1 - Yang Ran A1 - Qinfen Zheng A1 - Chellapa, Rama A1 - Strat, T.M. KW - algorithms KW - Artificial intelligence KW - Automated;Photography;Reproducibility of Results;Sensitivity and Specificity;Video Recording; KW - Biometry KW - Computer-Assisted;Pattern Recognition KW - double helical signatures KW - Gait KW - gait analysis KW - human gait KW - human motion kinematics KW - HUMANS KW - Image Enhancement KW - Image Interpretation KW - Image motion analysis KW - iterative local curve embedding algorithm KW - Object detection KW - simple spatiotemporal characterization KW - video sequence KW - Video surveillance AB - Applications of a simple spatiotemporal characterization of human gait in the surveillance domain are presented. The approach is based on decomposing a video sequence into x-t slices, which generate periodic patterns referred to as double helical signatures (DHSs). The features of DHS are given as follows: 1) they naturally encode the appearance and kinematics of human motion and reveal geometric symmetries and 2) they are effective and efficient for recovering gait parameters and detecting simple events. We present an iterative local curve embedding algorithm to extract the DHS from video sequences. Two applications are then considered. First, the DHS is used for simultaneous segmentation and labeling of body parts in cluttered scenes. Experimental results showed that the algorithm is robust to size, viewing angles, camera motion, and severe occlusion. Then, the DHS is used to classify load-carrying conditions. By examining various symmetries in DHS, activities such as carrying, holding, and walking with objects that are attached to legs are detected. Our approach possesses several advantages: a compact representation that can be computed in real time is used; furthermore, it does not depend on silhouettes or landmark tracking, which are sensitive to errors in background subtraction stage. VL - 40 SN - 1083-4419 CP - 4 M3 - 10.1109/TSMCB.2010.2044173 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 - CONF T1 - Bilateral symmetry of object silhouettes under perspective projection T2 - 19th International Conference on Pattern Recognition, 2008. ICPR 2008 Y1 - 2008 A1 - Bitsakos,K. A1 - Yi,H. A1 - Yi,L. A1 - Fermüller, Cornelia KW - Automation KW - bilateral symmetry KW - Computer vision KW - Frequency KW - Image analysis KW - Image coding KW - Image reconstruction KW - Internet KW - Internet images KW - Object detection KW - object silhouettes KW - perspective distortion KW - perspective projection KW - SHAPE KW - symmetric objects AB - Symmetry is an important property of objects and is exhibited in different forms e.g., bilateral, rotational, etc. This paper presents an algorithm for computing the bilateral symmetry of silhouettes of shallow objects under perspective distortion, exploiting the invariance of the cross ratio to projective transformations. The basic idea is to use the cross ratio to compute a number of midpoints of cross sections and then fit a straight line through them. The goodness-of-fit determines the likelihood of the line to be the axis of symmetry. We analytically estimate the midpointpsilas location as a function of the vanishing point for a given object silhouette. Hence finding the symmetry axis amounts to a 2D search in the space of vanishing points. We present experiments on two datasets as well as Internet images of symmetric objects that validate our approach. JA - 19th International Conference on Pattern Recognition, 2008. ICPR 2008 PB - IEEE SN - 978-1-4244-2174-9 M3 - 10.1109/ICPR.2008.4761501 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 - An adaptive mean shift tracking method using multiscale images T2 - Wavelet Analysis and Pattern Recognition, 2007. ICWAPR '07. International Conference on Y1 - 2007 A1 - Zhuolin Jiang A1 - Li,Shao-Fa A1 - Gao,Dong-Fa KW - adaptive mean shift tracking method KW - bandwidth matrix KW - Gaussian kernel KW - Gaussian processes KW - Image sequences KW - log-likelihood function KW - matrix algebra KW - maximum likelihood estimation KW - multiscale image KW - Object detection KW - object tracking AB - An adaptive mean shift tracking method for object tracking using multiscale images is presented in this paper. A bandwidth matrix and a Gaussian kernel are used to extend the definition of target model. The method can exactly estimate the position of the tracked object using multiscale images from Gaussian pyramid. The tracking method determines the parameters of kernel bandwidth by maximizing the lower bound of a log-likelihood function, which is derived from a kernel density estimate with the bandwidth matrix and the modified weight function. The experimental results show that it can averagely converge in 2.55 iterations per frame. JA - Wavelet Analysis and Pattern Recognition, 2007. ICWAPR '07. International Conference on VL - 3 M3 - 10.1109/ICWAPR.2007.4421589 ER - TY - CONF T1 - Identifying and segmenting human-motion for mobile robot navigation using alignment errors T2 - 12th International Conference on Advanced Robotics, 2005. ICAR '05. Proceedings Y1 - 2005 A1 - Abd-Almageed, Wael A1 - Burns,B. J A1 - Davis, Larry S. KW - Computer errors KW - Educational institutions KW - Frequency estimation KW - human-motion identification KW - human-motion segmentation KW - HUMANS KW - Image motion analysis KW - Image segmentation KW - mobile robot navigation KW - Mobile robots KW - Motion estimation KW - Navigation KW - Object detection KW - robot vision KW - SHAPE AB - This paper presents a new human-motion identification and segmentation algorithm, for mobile robot platforms. The algorithm is based on computing the alignment error between pairs of object images acquired from a moving platform. Pairs of images generating relatively small alignment errors are used to estimate the fundamental frequency of the object's motion. A decision criterion is then used to test the significance of the estimated frequency and to classify the object's motion. To verify the validity of the proposed approach, experimental results are shown on different classes of objects JA - 12th International Conference on Advanced Robotics, 2005. ICAR '05. Proceedings PB - IEEE SN - 0-7803-9178-0 M3 - 10.1109/ICAR.2005.1507441 ER - TY - JOUR T1 - Motion segmentation using occlusions JF - IEEE Transactions on Pattern Analysis and Machine Intelligence Y1 - 2005 A1 - Ogale, A. S A1 - Fermüller, Cornelia A1 - Aloimonos, J. KW - 3D motion estimation KW - algorithms KW - Artificial intelligence KW - CAMERAS KW - Computer vision KW - Filling KW - hidden feature removal KW - Image Enhancement KW - Image Interpretation, Computer-Assisted KW - image motion KW - Image motion analysis KW - Image segmentation KW - Layout KW - MOTION KW - Motion detection KW - Motion estimation KW - motion segmentation KW - Movement KW - Object detection KW - occlusion KW - occlusions KW - optical flow KW - ordinal depth KW - Pattern Recognition, Automated KW - Photography KW - Reproducibility of results KW - segmentation KW - Semiconductor device modeling KW - Sensitivity and Specificity KW - video analysis. KW - Video Recording AB - We examine the key role of occlusions in finding independently moving objects instantaneously in a video obtained by a moving camera with a restricted field of view. In this problem, the image motion is caused by the combined effect of camera motion (egomotion), structure (depth), and the independent motion of scene entities. For a camera with a restricted field of view undergoing a small motion between frames, there exists, in general, a set of 3D camera motions compatible with the observed flow field even if only a small amount of noise is present, leading to ambiguous 3D motion estimates. If separable sets of solutions exist, motion-based clustering can detect one category of moving objects. Even if a single inseparable set of solutions is found, we show that occlusion information can be used to find ordinal depth, which is critical in identifying a new class of moving objects. In order to find ordinal depth, occlusions must not only be known, but they must also be filled (grouped) with optical flow from neighboring regions. We present a novel algorithm for filling occlusions and deducing ordinal depth under general circumstances. Finally, we describe another category of moving objects which is detected using cardinal comparisons between structure from motion and structure estimates from another source (e.g., stereo). VL - 27 SN - 0162-8828 CP - 6 M3 - 10.1109/TPAMI.2005.123 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 - Multimodal 3-D tracking and event detection via the particle filter T2 - IEEE Workshop on Detection and Recognition of Events in Video, 2001. Proceedings Y1 - 2001 A1 - Zotkin,Dmitry N A1 - Duraiswami, Ramani A1 - Davis, Larry S. KW - algorithms KW - APPROACH KW - audio data collection KW - audio signal processing KW - Bayesian inference KW - Bayesian methods KW - belief networks KW - CAMERAS KW - capture KW - conversation KW - echo KW - Educational institutions KW - Event detection KW - event occurrence KW - filtering theory KW - flying echo locating bat behaviour KW - Image motion analysis KW - inference mechanisms KW - Laboratories KW - microphone arrays KW - moving object tracking KW - moving participants KW - moving prey KW - multimodal 3D tracking KW - multiple cameras KW - Object detection KW - particle filter KW - Particle filters KW - Particle tracking KW - Robustness KW - search KW - smart video conferencing setup KW - target tracking KW - Teleconferencing KW - tracking filters KW - turn-taking detection KW - video data collection KW - video signal processing AB - Determining the occurrence of an event is fundamental to developing systems that can observe and react to them. Often, this determination is based on collecting video and/or audio data and determining the state or location of a tracked object. We use Bayesian inference and the particle filter for tracking moving objects, using both video data obtained from multiple cameras and audio data obtained using arrays of microphones. The algorithms developed are applied to determining events arising in two fields of application. In the first, the behavior of a flying echo locating bat as it approaches a moving prey is studied, and the events of search, approach and capture are detected. In a second application we describe detection of turn-taking in a conversation between possibly moving participants recorded using a smart video conferencing setup JA - IEEE Workshop on Detection and Recognition of Events in Video, 2001. Proceedings PB - IEEE SN - 0-7695-1293-3 M3 - 10.1109/EVENT.2001.938862 ER - TY - CONF T1 - 3D object recognition via simulated particles diffusion T2 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1989. Proceedings CVPR '89 Y1 - 1989 A1 - Yacoob,Yaser A1 - Gold,Y. I KW - 3D object recognition KW - alignment strategy KW - Computational modeling KW - Computer science KW - data mining KW - Gold KW - Layout KW - Noise shaping KW - Object detection KW - Object recognition KW - parallel projection KW - pattern recognition KW - point features KW - radio access networks KW - scene acquisition KW - shape characterisation KW - Shape measurement KW - simulated particles diffusion KW - transformation detection AB - A novel approach for 3D object recognition is presented. This approach is model-based, and assumes either 3D or 21/2 D scene acquisition. Transformation detection is accomplished along with an object identification (six degrees of freedom, three rotational and three translational, are assumed). The diffusion-like simulation recently introduced as a means for characterization of shape is used in the extraction of point features. The point features represent regions on the object's surface that are extreme in curvature (i.e. concavities and convexities). Object matching is carried out by examining the correspondence between the object's set of point features and the model's set of point features, using an alignment strategy. Triangles are constructed between all possible triples of object's point features, and then are aligned to candidate corresponding triangles of the model's point features. 21/2 range images are transformed into a volumetric representation through a parallel projection onto the 3-D space. The resultant volume is suitable for processing by the diffusion-like simulation JA - IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1989. Proceedings CVPR '89 PB - IEEE SN - 0-8186-1952-x M3 - 10.1109/CVPR.1989.37886 ER -