Spatiotemporal Gesture Segmentation

Spotting patterns of interest in an input signal is a very useful task in many different fields including medicine, bioinformatics, economics, speech recognition and computer vision. Example instances of this problem include spotting an object of interest in an image (e.g., a tumor), a pattern of interest in a time-varying signal (e.g., audio analysis), or an object of interest moving in a specific way (e.g., a human's body gesture). Traditional spotting methods, which are based on Dynamic Time Warping or hidden Markov models, use some variant of dynamic programming to register the pattern and the input while accounting for temporal variation between them. At the same time, those methods often suffer from several shortcomings: they may give meaningless solutions when input observations are unreliable or ambiguous, they require a high complexity search across the whole input signal, and they may give incorrect solutions if some patterns appear as smaller parts within other patterns. In this thesis, we develop a framework that addresses these three problems, and evaluate the framework's performance in spotting and recognizing hand gestures in video. The first contribution is a spatiotemporal matching algorithm that extends the dynamic programming formulation to accommodate multiple candidate hand detections in every video frame. The algorithm finds the best alignment between the gesture model and the input, and simultaneously locates the best candidate hand detection in every frame. This allows for a gesture to be recognized even when the hand location is highly ambiguous. The second contribution is a pruning method that uses model-specific classifiers to reject dynamic programming hypotheses with a poor match between the input and model. Pruning improves the efficiency of the spatiotemporal matching algorithm, and in some cases may improve the recognition accuracy. The pruning classifiers are learned from training data, and cross-validation is used to reduce the chance of overpruning. The third contribution is a subgesture reasoning process that models the fact that some gesture models can falsely match parts of other, longer gestures. By integrating subgesture reasoning the spotting algorithm can avoid the premature detection of a subgesture when the longer gesture is actually being performed. Subgesture relations between pairs of gestures are automatically learned from training data. The performance of the approach is evaluated on two challenging video datasets: hand-signed digits gestured by users wearing short sleeved shirts, in front of a cluttered background, and American Sign Language (ASL) utterances gestured by ASL native signers. The experiments demonstrate that the proposed method is more accurate and efficient than competing approaches. The proposed approach can be generally applied to alignment or search problems with multiple input observations, that use dynamic programming to find a solution.

Skin Color-Based Video Segmentation under Time-Varying Illumination

A novel approach for real-time skin segmentation in video sequences is described. The approach enables reliable skin segmentation despite wide variation in illumination during tracking. An explicit second order Markov model is used to predict evolution of the skin-color (HSV) histogram over time. Histograms are dynamically updated based on feedback from the current segmentation and predictions of the Markov model. The evolution of the skin-color distribution at each frame is parameterized by translation, scaling and rotation in color space. Consequent changes in geometric parameterization of the distribution are propagated by warping and resampling the histogram. The parameters of the discrete-time dynamic Markov model are estimated using Maximum Likelihood Estimation, and also evolve over time. The accuracy of the new dynamic skin color segmentation algorithm is compared to that obtained via a static color model. Segmentation accuracy is evaluated using labeled ground-truth video sequences taken from staged experiments and popular movies. An overall increase in segmentation accuracy of up to 24% is observed in 17 out of 21 test sequences. In all but one case the skin-color classification rates for our system were higher, with background classification rates comparable to those of the static segmentation.

Multiplicative Kernels: Object Detection, Segmentation and Pose Estimation

Object detection is challenging when the object class exhibits large within-class variations. In this work, we show that foreground-background classification (detection) and within-class classification of the foreground class (pose estimation) can be jointly learned in a multiplicative form of two kernel functions. One kernel measures similarity for foreground-background classification. The other kernel accounts for latent factors that control within-class variation and implicitly enables feature sharing among foreground training samples. Detector training can be accomplished via standard SVM learning. The resulting detectors are tuned to specific variations in the foreground class. They also serve to evaluate hypotheses of the foreground state. When the foreground parameters are provided in training, the detectors can also produce parameter estimate. When the foreground object masks are provided in training, the detectors can also produce object segmentation. The advantages of our method over past methods are demonstrated on data sets of human hands and vehicles.

Estimation and Prediction of Evolving Color Distributions for Skin Segmentation Under Varying Illumination

A novel approach for real-time skin segmentation in video sequences is described. The approach enables reliable skin segmentation despite wide variation in illumination during tracking. An explicit second order Markov model is used to predict evolution of the skin color (HSV) histogram over time. Histograms are dynamically updated based on feedback from the current segmentation and based on predictions of the Markov model. The evolution of the skin color distribution at each frame is parameterized by translation, scaling and rotation in color space. Consequent changes in geometric parameterization of the distribution are propagated by warping and re-sampling the histogram. The parameters of the discrete-time dynamic Markov model are estimated using Maximum Likelihood Estimation, and also evolve over time. Quantitative evaluation of the method was conducted on labeled ground-truth video sequences taken from popular movies.

An Integrated Approach for Segmentation and Estimation of Planar Structures

Standard structure from motion algorithms recover 3D structure of points. If a surface representation is desired, for example a piece-wise planar representation, then a two-step procedure typically follows: in the first step the plane-membership of points is first determined manually, and in a subsequent step planes are fitted to the sets of points thus determined, and their parameters are recovered. This paper presents an approach for automatically segmenting planar structures from a sequence of images, and simultaneously estimating their parameters. In the proposed approach the plane-membership of points is determined automatically, and the planar structure parameters are recovered directly in the algorithm rather than indirectly in a post-processing stage. Simulated and real experimental results show the efficacy of this approach.

Region Segmentation via Deformable Model-Guided Split and Merge

An improved method for deformable shape-based image segmentation is described. Image regions are merged together and/or split apart, based on their agreement with an a priori distribution on the global deformation parameters for a shape template. The quality of a candidate region merging is evaluated by a cost measure that includes: homogeneity of image properties within the combined region, degree of overlap with a deformed shape model, and a deformation likelihood term. Perceptually-motivated criteria are used to determine where/how to split regions, based on the local shape properties of the region group's bounding contour. A globally consistent interpretation is determined in part by the minimum description length principle. Experiments show that the model-based splitting strategy yields a significant improvement in segmention over a method that uses merging alone.

Foreground Object Segmentation from Binocular Stereo Video

Moving cameras are needed for a wide range of applications in robotics, vehicle systems, surveillance, etc. However, many foreground object segmentation methods reported in the literature are unsuitable for such settings; these methods assume that the camera is fixed and the background changes slowly, and are inadequate for segmenting objects in video if there is significant motion of the camera or background. To address this shortcoming, a new method for segmenting foreground objects is proposed that utilizes binocular video. The method is demonstrated in the application of tracking and segmenting people in video who are approximately facing the binocular camera rig. Given a stereo image pair, the system first tries to find faces. Starting at each face, the region containing the person is grown by merging regions from an over-segmented color image. The disparity map is used to guide this merging process. The system has been implemented on a consumer-grade PC, and tested on video sequences of people indoors obtained from a moving camera rig. As can be expected, the proposed method works well in situations where other foreground-background segmentation methods typically fail. We believe that this superior performance is partly due to the use of object detection to guide region merging in disparity/color foreground segmentation, and partly due to the use of disparity information available with a binocular rig, in contrast with most previous methods that assumed monocular sequences.

Isoperimetric Graph Partitioning for Data Clustering and Image Segmentation

Spectral methods of graph partitioning have been shown to provide a powerful approach to the image segmentation problem. In this paper, we adopt a different approach, based on estimating the isoperimetric constant of an image graph. Our algorithm produces the high quality segmentations and data clustering of spectral methods, but with improved speed and stability.

A Cortical and Cerebellar Parcellation System for Speech Studies

A neuroanatomical parcellation system is described which encompasses the entire cerebral cortex and the cerebellum. The cortical system modified version of the scheme described by Caviness et al. (1996) and is designed particularly for studies of speech processing. The cerebellum is parcellated into 6 cortical regions of interest (ROIs) and an ROI representing the deep cerebellar nuclei in each hemisphere. The boundaries of each ROI are based on individual anatomical markers that are clearly visible from standard structural MRI acquistions. The system permits averaginh of functional imaging data sets from multiple sujects while accounting for individual anatomical variability. Used in conjuction with region-of-interest analysis techniques such as that described by Nieto-Castanon et al. (2003), the parcellation system provides a more powerful means of analyzing functional data.

Neural Models of Motion Integration, Segmentation, and Probablistic Decision-Making

When brain mechanism carry out motion integration and segmentation processes that compute unambiguous global motion percepts from ambiguous local motion signals? Consider, for example, a deer running at variable speeds behind forest cover. The forest cover is an occluder that creates apertures through which fragments of the deer's motion signals are intermittently experienced. The brain coherently groups these fragments into a trackable percept of the deer in its trajectory. Form and motion processes are needed to accomplish this using feedforward and feedback interactions both within and across cortical processing streams. All the cortical areas V1, V2, MT, and MST are involved in these interactions. Figure-ground processes in the form stream through V2, such as the seperation of occluding boundaries of the forest cover from the boundaries of the deer, select the motion signals which determine global object motion percepts in the motion stream through MT. Sparse, but unambiguous, feauture tracking signals are amplified before they propogate across position and are intergrated with far more numerous ambiguous motion signals. Figure-ground and integration processes together determine the global percept. A neural model predicts the processing stages that embody these form and motion interactions. Model concepts and data are summarized about motion grouping across apertures in response to a wide variety of displays, and probabilistic decision making in parietal cortex in response to random dot displays.

Variable Rate Working Memories for Phonetic Categorization and Invariant Speech Perception

Speech can be understood at widely varying production rates. A working memory is described for short-term storage of temporal lists of input items. The working memory is a cooperative-competitive neural network that automatically adjusts its integration rate, or gain, to generate a short-term memory code for a list that is independent of item presentation rate. Such an invariant working memory model is used to simulate data of Repp (1980) concerning the changes of phonetic category boundaries as a function of their presentation rate. Thus the variability of categorical boundaries can be traced to the temporal in variance of the working memory code.

A Fast BCS/FCS Algorithm for Image Segmentation

A fast and efficient segmentation algorithm based on the Boundary Contour System/Feature Contour System (BCS/FCS) of Grossberg and Mingolla [3] is presented. This implementation is based on the FFT algorithm and the parallelism of the system.

A Neural Network Model of Speech Acquisition and Motor Equivalent Speech Production

This article describes a neural network model that addresses the acquisition of speaking skills by infants and subsequent motor equivalent production of speech sounds. The model learns two mappings during a babbling phase. A phonetic-to-orosensory mapping specifies a vocal tract target for each speech sound; these targets take the form of convex regions in orosensory coordinates defining the shape of the vocal tract. The babbling process wherein these convex region targets are formed explains how an infant can learn phoneme-specific and language-specific limits on acceptable variability of articulator movements. The model also learns an orosensory-to-articulatory mapping wherein cells coding desired movement directions in orosensory space learn articulator movements that achieve these orosensory movement directions. The resulting mapping provides a natural explanation for the formation of coordinative structures. This mapping also makes efficient use of redundancy in the articulator system, thereby providing the model with motor equivalent capabilities. Simulations verify the model's ability to compensate for constraints or perturbations applied to the articulators automatically and without new learning and to explain contextual variability seen in human speech production.

Preattentive Texture Segmentation and Grouping by the Boundary Contour System

An improved Boundary Contour System (BCS) neural network model of preattentive vision is applied to two images that produce strong "pop-out" of emergent groupings in humans. In humans these images generate groupings collinear with or perpendicular to image contrasts. Analogous groupings occur in computer simulations of the model. Long-range cooperative and short-range competitive processes of the BCS dynamically form the stable groupings of texture regions in response to the images.

A Recurrent Cooperative/Competitive Field for Segmentation of Magnetic Resonance Brain Imagery

The Grey-White Decision Network is introduced as an application of an on-center, off-surround recurrent cooperative/competitive network for segmentation of magnetic resonance imaging (MRI) brain images. The three layer dynamical system relaxes into a solution where each pixel is labeled as either grey matter, white matter, or "other" matter by considering raw input intensity, edge information, and neighbor interactions. This network is presented as an example of applying a recurrent cooperative/competitive field (RCCF) to a problem with multiple conflicting constraints. Simulations of the network and its phase plane analysis are presented.