Articulated Pose Estimation in a Learned Smooth Space of Feasible Solutions

A learning based framework is proposed for estimating human body pose from a single image. Given a differentiable function that maps from pose space to image feature space, the goal is to invert the process: estimate the pose given only image features. The inversion is an ill-posed problem as the inverse mapping is a one to many process. Hence multiple solutions exist, and it is desirable to restrict the solution space to a smaller subset of feasible solutions. For example, not all human body poses are feasible due to anthropometric constraints. Since the space of feasible solutions may not admit a closed form description, the proposed framework seeks to exploit machine learning techniques to learn an approximation that is smoothly parameterized over such a space. One such technique is Gaussian Process Latent Variable Modelling. Scaled conjugate gradient is then used find the best matching pose in the space of feasible solutions when given an input image. The formulation allows easy incorporation of various constraints, e.g. temporal consistency and anthropometric constraints. The performance of the proposed approach is evaluated in the task of upper-body pose estimation from silhouettes and compared with the Specialized Mapping Architecture. The estimation accuracy of the Specialized Mapping Architecture is at least one standard deviation worse than the proposed approach in the experiments with synthetic data. In experiments with real video of humans performing gestures, the proposed approach produces qualitatively better estimation results.

Tracking Human Body Pose on a Learned Smooth Space

Particle filtering is a popular method used in systems for tracking human body pose in video. One key difficulty in using particle filtering is caused by the curse of dimensionality: generally a very large number of particles is required to adequately approximate the underlying pose distribution in a high-dimensional state space. Although the number of degrees of freedom in the human body is quite large, in reality, the subset of allowable configurations in state space is generally restricted by human biomechanics, and the trajectories in this allowable subspace tend to be smooth. Therefore, a framework is proposed to learn a low-dimensional representation of the high-dimensional human poses state space. This mapping can be learned using a Gaussian Process Latent Variable Model (GPLVM) framework. One important advantage of the GPLVM framework is that both the mapping to, and mapping from the embedded space are smooth; this facilitates sampling in the low-dimensional space, and samples generated in the low-dimensional embedded space are easily mapped back into the original highdimensional space. Moreover, human body poses that are similar in the original space tend to be mapped close to each other in the embedded space; this property can be exploited when sampling in the embedded space. The proposed framework is tested in tracking 2D human body pose using a Scaled Prismatic Model. Experiments on real life video sequences demonstrate the strength of the approach. In comparison with the Multiple Hypothesis Tracking and the standard Condensation algorithm, the proposed algorithm is able to maintain tracking reliably throughout the long test sequences. It also handles singularity and self occlusion robustly.

A Dopamine-Acetylcholine Cascade: Simulating Learned and Lesion-Induced Behavior ff Striatal Cholinergic Interneurons

The "teaching signal" that modulates reinforcement learning at cortico-striatal synapses may be a sequence composed of an adaptively scaled DA burst, a brief ACh burst, and a scaled ACh pause. Such an interpretation is consistent with recent data on cholinergic interneurons of the striatum are tonically active neurons (TANs) that respond with characteristic pauses to novel events and to appetitive and aversive conditioned stimuli. Fluctuations in acetylcholine release by TANs modulate performance- and learning- related dynamics in the striatum. Whereas tonic activity emerges from intrinsic properties of these neurons, glutamatergic inputs from thalamic centromedian-parafascicular nuclei, and dopaminergic inputs from midbrain are required for the generation of pause responses. No prior computational models encompass both intrinsic and synaptically-gated dynamics. We present a mathematical model that robustly accounts for behavior-related electrophysiological properties of TANs in terms of their intrinsic physiological properties and known afferents. In the model balanced intrinsic hyperpolarizing and depolarizing currents engender tonic firing, and glutamatergic inputs from thalamus (and cortex) both directly excite and indirectly inhibit TANs. If the latter inhibition, probably mediated by GABAergic NOS interneurons, exceeds a threshold, its effect is amplified by a KIR current to generate a prolongued pause. In the model, the intrinsic mechanisms and external inputs are both modulated by learning-dependent dopamine (DA) signals and our simulations revealed that many learning-dependent behaviors of TANs are explicable without recourse to learning-dependent changes in synapses onto TANs.

A Local Circuit Model of Learned Straitial and Dopamine Cell Responses under Probabilistic Schedules of Reward

Before choosing, it helps to know both the expected value signaled by a predictive cue and the associated uncertainty that the reward will be forthcoming. Recently, Fiorillo et al. (2003) found the dopamine (DA) neurons of the SNc exhibit sustained responses related to the uncertainty that a cure will be followed by reward, in addition to phasic responses related to reward prediction errors (RPEs). This suggests that cue-dependent anticipations of the timing, magnitude, and uncertainty of rewards are learned and reflected in components of the DA signals broadcast by SNc neurons. What is the minimal local circuit model that can explain such multifaceted reward-related learning? A new computational model shows how learned uncertainty responses emerge robustly on single trial along with phasic RPE responses, such that both types of DA responses exhibit the empirically observed dependence on conditional probability, expected value of reward, and time since onset of the reward-predicting cue. The model includes three major pathways for computing: immediate expected values of cures, timed predictions of reward magnitudes (and RPEs), and the uncertainty associated with these predictions. The first two model pathways refine those previously modeled by Brown et al. (1999). A third, newly modeled, pathway is formed by medium spiny projection neurons (MSPNs) of the matrix compartment of the striatum, whose axons co-release GABA and a neuropeptide, substance P, both at synapses with GABAergic neurons in the SNr and with the dendrites (in SNr) of DA neurons whose somas are in ventral SNc. Co-release enables efficient computation of sustained DA uncertainty responses that are a non-monotonic function of the conditonal probability that a reward will follow the cue. The new model's incorporation of a striatal microcircuit allowed it to reveals that variability in striatal cholinergic transmission can explain observed difference, between monkeys, in the amplitutude of the non-monotonic uncertainty function. Involvement of matriceal MSPNs and striatal cholinergic transmission implpies a relation between uncertainty in the cue-reward contigency and action-selection functions of the basal ganglia. The model synthesizes anatomical, electrophysiological and behavioral data regarding the midbrain DA system in a novel way, by relating the ability to compute uncertainty, in parallel with other aspects of reward contingencies, to the unique distribution of SP inputs in ventral SN.

Comparative Performance Measures of Fuzzy ARTMAP, Learned Vector Quantization, and Back Propagation for Handwritten Character Recognition

This article compares the performance of Fuzzy ARTMAP with that of Learned Vector Quantization and Back Propagation on a handwritten character recognition task. Training with Fuzzy ARTMAP to a fixed criterion used many fewer epochs. Voting with Fuzzy ARTMAP yielded the highest recognition rates.

Cryptographic Tamper Evidence

We propose a new notion of cryptographic tamper evidence. A tamper-evident signature scheme provides an additional procedure Div which detects tampering: given two signatures, Div can determine whether one of them was generated by the forger. Surprisingly, this is possible even after the adversary has inconspicuously learned (exposed) some-or even all-the secrets in the system. In this case, it might be impossible to tell which signature is generated by the legitimate signer and which by the forger. But at least the fact of the tampering will be made evident. We define several variants of tamper-evidence, differing in their power to detect tampering. In all of these, we assume an equally powerful adversary: she adaptively controls all the inputs to the legitimate signer (i.e., all messages to be signed and their timing), and observes all his outputs; she can also adaptively expose all the secrets at arbitrary times. We provide tamper-evident schemes for all the variants and prove their optimality. Achieving the strongest tamper evidence turns out to be provably expensive. However, we define a somewhat weaker, but still practical, variant: α-synchronous tamper-evidence (α-te) and provide α-te schemes with logarithmic cost. Our α-te schemes use a combinatorial construction of α-separating sets, which might be of independent interest. We stress that our mechanisms are purely cryptographic: the tamper-detection algorithm Div is stateless and takes no inputs except the two signatures (in particular, it keeps no logs), we use no infrastructure (or other ways to conceal additional secrets), and we use no hardware properties (except those implied by the standard cryptographic assumptions, such as random number generators). Our constructions are based on arbitrary ordinary signature schemes and do not require random oracles.

The Specialized Mappings Architecture

A probabilistic, nonlinear supervised learning model is proposed: the Specialized Mappings Architecture (SMA). The SMA employs a set of several forward mapping functions that are estimated automatically from training data. Each specialized function maps certain domains of the input space (e.g., image features) onto the output space (e.g., articulated body parameters). The SMA can model ambiguous, one-to-many mappings that may yield multiple valid output hypotheses. Once learned, the mapping functions generate a set of output hypotheses for a given input via a statistical inference procedure. The SMA inference procedure incorporates an inverse mapping or feedback function in evaluating the likelihood of each of the hypothesis. Possible feedback functions include computer graphics rendering routines that can generate images for given hypotheses. The SMA employs a variant of the Expectation-Maximization algorithm for simultaneous learning of the specialized domains along with the mapping functions, and approximate strategies for inference. The framework is demonstrated in a computer vision system that can estimate the articulated pose parameters of a human’s body or hands, given silhouettes from a single image. The accuracy and stability of the SMA are also tested using synthetic images of human bodies and hands, where ground truth is known.

Parameter Sensitive Detectors

Object detection can be challenging when the object class exhibits large variations. One commonly-used strategy is to first partition the space of possible object variations and then train separate classifiers for each portion. However, with continuous spaces the partitions tend to be arbitrary since there are no natural boundaries (for example, consider the continuous range of human body poses). In this paper, a new formulation is proposed, where the detectors themselves are associated with continuous parameters, and reside in a parameterized function space. There are two advantages of this strategy. First, a-priori partitioning of the parameter space is not needed; the detectors themselves are in a parameterized space. Second, the underlying parameters for object variations can be learned from training data in an unsupervised manner. In profile face detection experiments, at a fixed false alarm number of 90, our method attains a detection rate of 75% vs. 70% for the method of Viola-Jones. In hand shape detection, at a false positive rate of 0.1%, our method achieves a detection rate of 99.5% vs. 98% for partition based methods. In pedestrian detection, our method reduces the miss detection rate by a factor of three at a false positive rate of 1%, compared with the method of Dalal-Triggs.

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.

Inferring Body Pose without Tracking Body Parts

A novel approach for estimating articulated body posture and motion from monocular video sequences is proposed. Human pose is defined as the instantaneous two dimensional configuration (i.e., the projection onto the image plane) of a single articulated body in terms of the position of a predetermined set of joints. First, statistical segmentation of the human bodies from the background is performed and low-level visual features are found given the segmented body shape. The goal is to be able to map these, generally low level, visual features to body configurations. The system estimates different mappings, each one with a specific cluster in the visual feature space. Given a set of body motion sequences for training, unsupervised clustering is obtained via the Expectation Maximation algorithm. Then, for each of the clusters, a function is estimated to build the mapping between low-level features to 3D pose. Currently this mapping is modeled by a neural network. Given new visual features, a mapping from each cluster is performed to yield a set of possible poses. From this set, the system selects the most likely pose given the learned probability distribution and the visual feature similarity between hypothesis and input. Performance of the proposed approach is characterized using a new set of known body postures, showing promising results.

Accurate and Efficient Gesture Spotting via Pruning and Subgesture Reasoning

Gesture spotting is the challenging task of locating the start and end frames of the video stream that correspond to a gesture of interest, while at the same time rejecting non-gesture motion patterns. This paper proposes a new gesture spotting and recognition algorithm that is based on the continuous dynamic programming (CDP) algorithm, and runs in real-time. To make gesture spotting efficient a pruning method is proposed that allows the system to evaluate a relatively small number of hypotheses compared to CDP. Pruning is implemented by a set of model-dependent classifiers, that are learned from training examples. To make gesture spotting more accurate a subgesture reasoning process is proposed that models the fact that some gesture models can falsely match parts of other longer gestures. In our experiments, the proposed method with pruning and subgesture modeling is an order of magnitude faster and 18% more accurate compared to the original CDP algorithm.

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.

Object Detection at the Optimal Scale with Hidden State Shape Models

Hidden State Shape Models (HSSMs) [2], a variant of Hidden Markov Models (HMMs) [9], were proposed to detect shape classes of variable structure in cluttered images. In this paper, we formulate a probabilistic framework for HSSMs which provides two major improvements in comparison to the previous method [2]. First, while the method in [2] required the scale of the object to be passed as an input, the method proposed here estimates the scale of the object automatically. This is achieved by introducing a new term for the observation probability that is based on a object-clutter feature model. Second, a segmental HMM [6, 8] is applied to model the "duration probability" of each HMM state, which is learned from the shape statistics in a training set and helps obtain meaningful registration results. Using a segmental HMM provides a principled way to model dependencies between the scales of different parts of the object. In object localization experiments on a dataset of real hand images, the proposed method significantly outperforms the method of [2], reducing the incorrect localization rate from 40% to 15%. The improvement in accuracy becomes more significant if we consider that the method proposed here is scale-independent, whereas the method of [2] takes as input the scale of the object we want to localize.

A Model of Cerebellar Adaptation of Grip Forces During Lifting

We investigated adaptive neural control of precision grip forces during object lifting. A model is presented that adjusts reactive and anticipatory grip forces to a level just above that needed to stabilize lifted objects in the hand. The model obeys priciples of cerebellar structure and function by using slip sensations as error signals to adapt phasic motor commands to tonic force generators associated with output synergies controlling grip aperture. The learned phasic commands are weight and texture-dependent. Simulations of the new curcuit model reproduce key aspects of experimental observations of force application. Over learning trials, the onset of grip force buildup comes to lead the load force buildup, and the rate-of-rise of grip force, but not load force, scales inversely with the friction of the gripped object.

A Quantitative Evaluation of the AVITEWRITE Model of Handwriting Learning

Much sensory-motor behavior develops through imitation, as during the learning of handwriting by children. Such complex sequential acts are broken down into distinct motor control synergies, or muscle groups, whose activities overlap in time to generate continuous, curved movements that obey an intense relation between curvature and speed. The Adaptive Vector Integration to Endpoint (AVITEWRITE) model of Grossberg and Paine (2000) proposed how such complex movements may be learned through attentive imitation. The model suggest how frontal, parietal, and motor cortical mechanisms, such as difference vector encoding, under volitional control from the basal ganglia, interact with adaptively-timed, predictive cerebellar learning during movement imitation and predictive performance. Key psycophysical and neural data about learning to make curved movements were simulated, including a decrease in writing time as learning progresses; generation of unimodal, bell-shaped velocity profiles for each movement synergy; size scaling with isochrony, and speed scaling with preservation of the letter shape and the shapes of the velocity profiles; an inverse relation between curvature and tangential velocity; and a Two-Thirds Power Law relation between angular velocity and curvature. However, the model learned from letter trajectories of only one subject, and only qualitative kinematic comparisons were made with previously published human data. The present work describes a quantitative test of AVITEWRITE through direct comparison of a corpus of human handwriting data with the model's performance when it learns by tracing human trajectories. The results show that model performance was variable across subjects, with an average correlation between the model and human data of 89+/-10%. The present data from simulations using the AVITEWRITE model highlight some of its strengths while focusing attention on areas, such as novel shape learning in children, where all models of handwriting and learning of other complex sensory-motor skills would benefit from further research.