Statistical models of non-rigid deformable shape have wide application in many fi elds,
including computer vision, computer graphics, and biometry. We show that shape deformations
are well represented through nonlinear manifolds that are also matrix Lie groups.
These pattern-theoretic representations lead to several advantages over other alternatives,
including a principled measure of shape dissimilarity and a natural way to compose deformations.
Moreover, they enable building models using statistics on manifolds. Consequently,
such models are superior to those based on Euclidean representations. We
demonstrate this by modeling 2D and 3D human body shape. Shape deformations are
only one example of manifold-valued data. More generally, in many computer-vision and
machine-learning problems, nonlinear manifold representations arise naturally and provide
a powerful alternative to Euclidean representations. Statistics is traditionally concerned
with data in a Euclidean space, relying on the linear structure and the distances associated
with such a space; this renders it inappropriate for nonlinear spaces. Statistics can,
however, be generalized to nonlinear manifolds. Moreover, by respecting the underlying
geometry, the statistical models result in not only more e ffective analysis but also consistent
synthesis. We go beyond previous work on statistics on manifolds by showing how,
even on these curved spaces, problems related to modeling a class from scarce data can be
dealt with by leveraging information from related classes residing in di fferent regions of the
space. We show the usefulness of our approach with 3D shape deformations. To summarize
our main contributions: 1) We de fine a new 2D articulated model -- more expressive than
traditional ones -- of deformable human shape that factors body-shape, pose, and camera
variations. Its high realism is obtained from training data generated from a detailed 3D
model. 2) We defi ne a new manifold-based representation of 3D shape deformations that
yields statistical deformable-template models that are better than the current state-of-the-
art. 3) We generalize a transfer learning idea from Euclidean spaces to Riemannian
manifolds. This work demonstrates the value of modeling manifold-valued data and their
statistics explicitly on the manifold. Specifi cally, the methods here provide new tools for
shape analysis.
Kalman filtering is a common method to decode neural signals from the motor cortex. In clinical research investigating the use of intracortical brain computer interfaces (iBCIs), the technique enabled people with tetraplegia to control assistive devices such as a computer or robotic arm directly from their neural activity. For reaching movements, the Kalman filter typically estimates the instantaneous endpoint velocity of the control device. Here, we analyzed attempted arm/hand movements by people with tetraplegia to control a cursor on a computer screen to reach several circular targets. A standard velocity Kalman filter is enhanced to additionally decode for the cursor’s position. We then mix decoded velocity and position to generate cursor movement commands. We analyzed data, offline, from two participants across six sessions. Root mean squared error between the actual and estimated
cursor trajectory improved by 12.2 ±10.5% (pairwise t-test, p<0.05) as compared to a standard velocity Kalman filter. The findings suggest that simultaneously decoding for intended velocity and position and using them both to generate movement commands can improve the performance of iBCIs.
In the spirit of recent work on contextual recognition and estimation, we present a method for estimating the pose of human hands, employing information about the shape of the object in the hand. Despite the fact that most applications of human hand tracking involve grasping and manipulation of objects, the majority of methods in the literature assume a free hand, isolated from the surrounding environment. Occlusion of the hand from grasped objects does in fact often pose a severe challenge to the estimation of hand pose. In the presented method, object occlusion is not only compensated for, it contributes to the pose estimation in a contextual fashion; this without an explicit model of object shape. Our hand tracking method is non-parametric, performing a nearest neighbor search in a large database (.. entries) of hand poses with and without grasped objects. The system that operates in real time, is robust to self occlusions, object occlusions and segmentation errors, and provides full hand pose reconstruction from monocular video. Temporal consistency in hand pose is taken into account, without explicitly tracking the hand in the high-dim pose space. Experiments show the non-parametric method to outperform other state of the art regression methods, while operating at a significantly lower computational cost than comparable model-based hand tracking methods.
Benchmarking methods for 3d hand tracking is still an open problem due to the difficulty of acquiring ground truth data.
We introduce a new dataset and benchmarking protocol that is insensitive to the accumulative error of other protocols.
To this end, we create testing frame pairs of increasing difficulty and measure the pose estimation error separately for each of them.
This approach gives new insights and allows to accurately study the performance of each feature or method without employing a full tracking pipeline.
Following this protocol, we evaluate various directional distances in the context of silhouette-based 3d hand tracking, expressed as special cases of a generalized Chamfer distance form.
An appropriate parameter setup is proposed for each of them, and a comparative study reveals the best performing method in this context.
In this paper we propose an affordable solution to self-
localization, which utilizes visual odometry and road maps
as the only inputs. To this end, we present a probabilis-
tic model as well as an efficient approximate inference al-
gorithm, which is able to utilize distributed computation
to meet the real-time requirements of autonomous systems.
Because of the probabilistic nature of the model we are
able to cope with uncertainty due to noisy visual odometry
and inherent ambiguities in the map (
e.g
., in a Manhattan
world). By exploiting freely available, community devel-
oped maps and visual odometry measurements, we are able
to localize a vehicle up to 3m after only a few seconds of
driving on maps which contain more than 2,150km of driv-
able roads.
Despite the success of recent object class recognition systems, the long-standing problem of partial occlusion re- mains a major challenge, and a principled solution is yet to be found. In this paper we leave the beaten path of meth- ods that treat occlusion as just another source of noise – instead, we include the occluder itself into the modelling, by mining distinctive, reoccurring occlusion patterns from annotated training data. These patterns are then used as training data for dedicated detectors of varying sophistica- tion. In particular, we evaluate and compare models that range from standard object class detectors to hierarchical, part-based representations of occluder/occludee pairs. In an extensive evaluation we derive insights that can aid fur- ther developments in tackling the occlusion challenge.
Layered models allow scene segmentation and motion estimation to be formulated together and to inform one another. Traditional layered motion methods, however, employ fairly weak models of scene structure, relying on locally connected Ising/Potts models which have limited ability to capture long-range correlations in natural scenes. To address this, we formulate a fully-connected layered model that enables global reasoning about the complicated segmentations of real objects. Optimization with fully-connected graphical models is challenging, and our inference algorithm leverages recent work on efficient mean field updates for fully-connected conditional random fields. These methods can be implemented efficiently using high-dimensional Gaussian filtering. We combine these ideas with a layered flow model, and find that the long-range connections greatly improve segmentation into figure-ground layers when compared with locally connected MRF models. Experiments on several benchmark datasets show that the method can recover fine structures and large occlusion regions, with good flow accuracy and much lower computational cost than previous locally-connected layered models.
Faces and bodies are complex structures, perception of which can play important roles in person identification and inference of emotional state. Face representations have been explored using behavioural adaptation: in particular, studies have shown that face aftereffects show relatively broad tuning for viewpoint, consistent with origin in a high-level structural descriptor far removed from the retinal image. Our goals were to determine first, if body aftereffects also showed a degree of viewpoint invariance, and second if they also showed pose invariance, given that changes in pose create even more dramatic changes in the 2-D retinal image. We used a 3-D model of the human body to generate headless body images, whose parameters could be varied to generate different body forms, viewpoints, and poses. In the first experiment, subjects adapted to varying viewpoints of either slim or heavy bodies in a neutral stance, followed by test stimuli that were all front-facing. In the second experiment, we used the same front-facing bodies in neutral stance as test stimuli, but compared adaptation from bodies in the same neutral stance to adaptation with the same bodies in different poses. We found that body aftereffects were obtained over substantial viewpoint changes, with no significant decline in aftereffect magnitude with increasing viewpoint difference between adapting and test images. Aftereffects also showed transfer across one change in pose but not across another. We conclude that body representations may have more viewpoint invariance than faces, and demonstrate at least some transfer across pose, consistent with a high-level structural description.
Keywords: aftereffect, shape, face, representation
In this work, we address the problem of estimating 2d human pose from still images. Recent methods that rely on discriminatively trained deformable parts organized in a tree model have shown to be very successful in solving this task. Within such a pictorial structure framework, we address the problem of obtaining good part templates by proposing novel, non-linear joint regressors. In particular, we employ two-layered random forests as joint regressors. The first layer acts as a discriminative, independent body part classifier. The second layer takes the estimated class distributions of the first one into account and is thereby able to predict joint locations by modeling the interdependence and co-occurrence of the parts. This results in a pose estimation framework that takes dependencies between body parts already for joint localization into account and is thus able to circumvent typical ambiguities of tree structures, such as for legs and arms. In the experiments, we demonstrate that our body parts dependent joint regressors achieve a higher joint localization accuracy than tree-based state-of-the-art methods.
Capturing the skeleton motion and detailed time-varying surface geometry of multiple, closely interacting peoples is a very challenging task, even in a multicamera setup, due to frequent occlusions and ambiguities in feature-to-person assignments. To address this task, we propose a framework that exploits multiview image segmentation. To this end, a probabilistic shape and appearance model is employed to segment the input images and to assign each pixel uniquely to one person. Given the articulated template models of each person and the labeled pixels, a combined optimization scheme, which splits the skeleton pose optimization problem into a local one and a lower dimensional global one, is applied one by one to each individual, followed with surface estimation to capture detailed nonrigid deformations. We show on various sequences that our approach can capture the 3D motion of humans accurately even if they move rapidly, if they wear wide apparel, and if they are engaged in challenging multiperson motions, including dancing, wrestling, and hugging.
We present a random forest-based framework for real time head pose estimation from depth images and extend it to localize a set of facial features in 3D. Our algorithm takes a voting approach, where each patch extracted from the depth image can directly cast a vote for the head pose or each of the facial features. Our system proves capable of handling large rotations, partial occlusions, and the noisy depth data acquired using commercial sensors. Moreover, the algorithm works on each frame independently and achieves real time performance without resorting to parallel computations on a GPU. We present extensive experiments on publicly available, challenging datasets and present a new annotated head pose database recorded using a Microsoft Kinect.
The field of Human Pose Estimation is developing fast and lately leaped forward
with the release of the Kinect system. That system reaches a very good perfor-
mance for pose estimation using 3D scene information, however pose estimation
from 2D color images is not solved reliably yet. There is a vast amount of pub-
lications trying to reach this aim, but no compilation of important methods and
solution strategies. The aim of this thesis is to fill this gap: it gives an introductory
overview over important techniques by analyzing four current (2012) publications
in detail. They are chosen such, that during their analysis many frequently used
techniques for Human Pose Estimation can be explained. The thesis includes two
introductory chapters with a definition of Human Pose Estimation and exploration
of the main difficulties, as well as a detailed explanation of frequently used methods.
A final chapter presents some ideas on how parts of the analyzed approaches can
be recombined and shows some open questions that can be tackled in future work.
The thesis is therefore a good entry point to the field of Human Pose Estimation
and enables the reader to get an impression of the current state-of-the-art.
This paper presents a new volumetric representation for categorizing objects in large-scale 3-D scenes reconstructed from image sequences. This work uses a probabilistic volumetric model (PVM) that combines the ideas of background modeling and volumetric multi-view reconstruction to handle the uncertainty inherent in the problem of reconstructing 3-D structures from 2-D images. The advantages of probabilistic modeling have been demonstrated by recent application of the PVM representation to video image registration, change detection and classification of changes based on PVM context. The applications just mentioned, operate on 2-D projections of the PVM. This paper presents the first work to characterize and use the local 3-D information in the scenes. Two approaches to local feature description are proposed and compared: 1) features derived from a PCA analysis of model neighborhoods; and 2) features derived from the coefficients of a 3-D Taylor series expansion within each neighborhood. The resulting description is used in a bag-of-features approach to classify buildings, houses, cars, planes, and parking lots learned from aerial imagery collected over Providence, RI. It is shown that both feature descriptions explain the data with similar accuracy and their effectiveness for dense-feature categorization is compared for the different classes. Finally, 3-D extensions of the Harris corner detector and a Hessian-based detector are used to detect salient features. Both types of salient features are evaluated through object categorization experiments, where only features with maximal response are retained. For most saliency criteria tested, features based on the determinant of the Hessian achieved higher classification accuracy than Harris-based features.
This paper presents a novel framework for surface reconstruction from multi-view aerial imagery of large scale urban scenes, which combines probabilistic volumetric modeling with smooth signed distance surface estimation, to produce very detailed and accurate surfaces. Using a continuous probabilistic volumetric model which allows for explicit representation of ambiguities caused by moving objects, reflective surfaces, areas of constant appearance, and self-occlusions, the algorithm learns the geometry and appearance of a scene from a calibrated image sequence. An online implementation of Bayesian learning precess in GPUs significantly reduces the time required to process a large number of images. The probabilistic volumetric model of occupancy is subsequently used to estimate a smooth approximation of the signed distance function to the surface. This step, which reduces to the solution of a sparse linear system, is very efficient and scalable to large data sets. The proposed algorithm is shown to produce high quality surfaces in challenging aerial scenes where previous methods make large errors in surface localization. The general applicability of the algorithm beyond aerial imagery is confirmed against the Middlebury benchmark.
A variety of dynamic objects, such as faces, bodies, and cloth, are represented in computer graphics as a collection of moving spatial landmarks. Spatiotemporal data is inherent in a number of graphics applications including animation, simulation, and object and camera tracking. The principal modes of variation in the spatial geometry of objects are typically modeled using dimensionality reduction techniques, while concurrently, trajectory representations like splines and autoregressive models are widely used to exploit the temporal regularity of deformation. In this article, we present the bilinear spatiotemporal basis as a model that simultaneously exploits spatial and temporal regularity while maintaining the ability to generalize well to new sequences. This factorization allows the use of analytical, predefined functions to represent temporal variation (e.g., B-Splines or the Discrete Cosine Transform) resulting in efficient model representation and estimation. The model can be interpreted as representing the data as a linear combination of spatiotemporal sequences consisting of shape modes oscillating over time at key frequencies. We apply the bilinear model to natural spatiotemporal phenomena, including face, body, and cloth motion data, and compare it in terms of compaction, generalization ability, predictive precision, and efficiency to existing models. We demonstrate the application of the model to a number of graphics tasks including labeling, gap-filling, denoising, and motion touch-up.
Visual attention plays a major role in our lives. Our very perception (which very much decides our survival) depends on it - like perceiving a predator while walking through a forest, perceiving a fast car coming from the front on a busy road or even spotting our favorite color out of the many colors. In Medical Imaging, where medical experts have to take major clinical decisions based on the examination of images of various kinds (CT, MRI etc), visual attention plays a pivotal role. It makes the medical experts fixate on any abnormal behavior exhibited in the medical image and helps in speedy diagnosis. Many previous works (see the paper for details) have exhibited this important fact and the model proposed by Nodine and Kundel highlights the important role of visual attention in medical image diagnosis.
Visual attention involves two components - Bottom-Up and Top-Down.In the present work, we examine a number of established computational models of visual attention in the context of chest X-rays (infected with Pneumoconiosis) and retinal images (having hard exudates). The fundamental motivation is to try to understand the applicability of visual attention models in the context of different types of abnormalities.
Our assessment of four popular visual attention models, is extensive and shows that they are able to pick up abnormal features reasonably well. We compare the models towards detecting subtle abnormalities and high-contrast lesions. Although significant scope of improvements exists especially in picking up more subtle abnormalities and getting more selective towards picking up more abnormalities and less normal structures, the presented assessment shows that visual attention indeed shows a promise for inclusion in the main field of medical image analysis
We propose a physically-based approach to separate reflection using multiple polarized images with a background scene captured behind glass. The input consists of three polarized images, each captured from the same view point but with a different polarizer angle separated by 45 degrees. The output is the high-quality separation of the reflection and background layers from each of the input images. A main technical challenge for this problem is that the mixing coefficient for the reflection and background layers depends on the angle of incidence and the orientation of the plane of incidence, which are spatially-varying over the pixels of an image. Exploiting physical properties of polarization for a double-surfaced glass medium, we propose an algorithm which automatically finds the optimal separation of the reflection and background layers. Thorough experiments, we demonstrate that our approach can generate superior results to those of previous methods.
The segmentation of shapes from biomedical images has a wide range of uses such as image based modelling and bioimage analysis. In this paper, an active contour model is proposed for the segmentation of N-dimensional biomedical images. The proposed model uses a curvature smoothing flow and an image attraction force derived from the interactions between the geometries of the active contour model and the image objects. The active contour model is formulated using the level set method so as to handle topological changes automatically. The magnitude and orientation of the image attraction force is based on the relative geometric configurations between the active contour model and the image object boundaries. The vector force field is therefore dynamic, and the active contour model can propagate through narrow structures to segment complex shapes efficiently. The proposed model utilizes pixel interactions across the image domain, which gives a coherent representation of the image object shapes. This allows the active contour model to be robust to image noise and weak object edges. The proposed model is compared against widely used active contour models in the segmentation of anatomical shapes from biomedical images. It is shown that the proposed model has several advantages over existing techniques and can be used for the segmentation of biomedical images efficiently.
We present a method for the reconstruction of vascular geometries from medical images. Image denoising is performed using vessel enhancing diffusion, which can smooth out image noise and enhance vessel structures. The Canny edge detection technique which produces object edges with single pixel width is used for accurate detection of the lumen boundaries. The image gradients are then used to compute the geometric potential field which gives a global representation of the geometric configuration. The deformable model uses a regional constraint to suppress calcified regions for accurate segmentation of the vessel geometries. The proposed framework show high accuracy when applied to the segmentation of the carotid arteries from CT images.
Four decades after their invention, quasi- Newton methods are still state of the art in unconstrained numerical optimization. Although not usually interpreted thus, these are learning algorithms that fit a local quadratic approximation to the objective function. We show that many, including the most popular, quasi-Newton methods can be interpreted as approximations of Bayesian linear regression under varying prior assumptions. This new notion elucidates some shortcomings of classical algorithms, and lights the way to a novel nonparametric quasi-Newton method, which is able to make more efficient use of available information at computational cost similar to its predecessors.
We develop a method for discovering the parts of an articulated object from aligned meshes of the object in various three-dimensional poses. We adapt the distance dependent Chinese restaurant process (ddCRP) to allow nonparametric discovery of a potentially unbounded number of parts, while simultaneously guaranteeing a spatially connected segmentation. To allow analysis of datasets in which object instances have varying 3D shapes, we model part variability across poses via affine transformations. By placing a matrix normal-inverse-Wishart prior on these affine transformations, we develop a ddCRP Gibbs sampler which tractably marginalizes over transformation uncertainty. Analyzing a dataset of humans captured in dozens of poses, we infer parts which provide quantitatively better deformation predictions than conventional clustering methods.
In
Consumer Depth Cameras for Computer Vision: Research Topics and Applications,
Fossati, A., Gall, J., Grabner, H., Ren, X. and Konolige, K., Editors,
pages 99-118,
Springer-Verlag,
2012.
Three-dimensional (3D) shape models are powerful because they enable the inference of object shape from incomplete, noisy, or ambiguous 2D or 3D data. For example, realistic parameterized 3D human body models have been used to infer the shape and pose of people from images. To train such models, a corpus of 3D body scans is typically brought into registration by aligning a common 3D human-shaped template to each scan. This is an ill-posed problem that typically involves solving an optimization problem with regularization terms that penalize
implausible deformations of the template. When aligning a corpus, however, we can do better than generic regularization. If we have a model of how the template can deform then alignments can be regularized by this
model. Constructing a model of deformations, however, requires having a corpus that is already registered. We address this chicken-and-egg problem by approaching modeling and registration together. By minimizing
a single objective function, we reliably obtain high quality registration of noisy, incomplete, laser scans, while simultaneously learning a highly realistic articulated body model. The model greatly improves robustness
to noise and missing data. Since the model explains a corpus of body scans, it captures how body shape varies across people and poses.
Multi-metric learning techniques learn local metric tensors in different parts of a feature space. With such an approach, even simple classifiers can be competitive with the state-of-the-art because the distance measure locally adapts to the structure of the data. The learned distance measure is, however, non-metric, which has prevented multi-metric learning from generalizing to tasks such as dimensionality reduction and regression in a principled way. We prove that, with appropriate changes, multi-metric learning corresponds to learning the structure of a Riemannian manifold. We then show that this structure gives us a principled way to perform dimensionality reduction and regression according to the learned metrics. Algorithmically, we provide the first practical algorithm for computing geodesics according to the learned metrics, as well as algorithms for computing exponential and logarithmic maps on the Riemannian manifold. Together, these tools let many Euclidean algorithms take advantage of multi-metric learning. We illustrate the approach on regression and dimensionality reduction tasks that involve predicting measurements of the human body from shape data.
