Form Perception

National Science Foundation (SBE-0354378); Office of Naval Research (N00014-01-1-0624)

Cortical Dynamics of Visual Motion Perception: Short-Range and Long Range Apparent Motion

This article describes further evidence for a new neural network theory of biological motion perception that is called a Motion Boundary Contour System. This theory clarifies why parallel streams Vl-> V2 and Vl-> MT exist for static form and motion form processing among the areas Vl, V2, and MT of visual cortex. The Motion Boundary Contour System consists of several parallel copies, such that each copy is activated by a different range of receptive field sizes. Each copy is further subdivided into two hierarchically organized subsystems: a Motion Oriented Contrast Filter, or MOC Filter, for preprocessing moving images; and a Cooperative-Competitive Feedback Loop, or CC Loop, for generating emergent boundary segmentations of the filtered signals. The present article uses the MOC Filter to explain a variety of classical and recent data about short-range and long-range apparent motion percepts that have not yet been explained by alternative models. These data include split motion; reverse-contrast gamma motion; delta motion; visual inertia; group motion in response to a reverse-contrast Ternus display at short interstimulus intervals; speed-up of motion velocity as interfiash distance increases or flash duration decreases; dependence of the transition from element motion to group motion on stimulus duration and size; various classical dependencies between flash duration, spatial separation, interstimulus interval, and motion threshold known as Korte's Laws; and dependence of motion strength on stimulus orientation and spatial frequency. These results supplement earlier explanations by the model of apparent motion data that other models have not explained; a recent proposed solution of the global aperture problem, including explanations of motion capture and induced motion; an explanation of how parallel cortical systems for static form perception and motion form perception may develop, including a demonstration that these parallel systems are variations on a common cortical design; an explanation of why the geometries of static form and motion form differ, in particular why opposite orientations differ by 90°, whereas opposite directions differ by 180°, and why a cortical stream Vl -> V2 -> MT is needed; and a summary of how the main properties of other motion perception models can be assimilated into different parts of the Motion Boundary Contour System design.

Cortical Dynamics of Visual Motion Perception: Short-Range and Long-Range Apparent Motion

This article describes further evidence for a new neural network theory of biological motion perception. The theory clarifies why parallel streams Vl --> V2, Vl --> MT, and Vl --> V2 --> MT exist for static form and motion form processing among the areas Vl, V2, and MT of visual cortex. The theory suggests that the static form system (Static BCS) generates emergent boundary segmentations whose outputs are insensitive to direction-ofcontrast and insensitive to direction-of-motion, whereas the motion form system (Motion BCS) generates emergent boundary segmentations whose outputs are insensitive to directionof-contrast but sensitive to direction-of-motion. The theory is used to explain classical and recent data about short-range and long-range apparent motion percepts that have not yet been explained by alternative models. These data include beta motion; split motion; gamma motion and reverse-contrast gamma motion; delta motion; visual inertia; the transition from group motion to element motion in response to a Ternus display as the interstimulus interval (ISI) decreases; group motion in response to a reverse-contrast Ternus display even at short ISIs; speed-up of motion velocity as interflash distance increases or flash duration decreases; dependence of the transition from element motion to group motion on stimulus duration and size; various classical dependencies between flash duration, spatial separation, ISI, and motion threshold known as Korte's Laws; dependence of motion strength on stimulus orientation and spatial frequency; short-range and long-range form-color interactions; and binocular interactions of flashes to different eyes.

Specialized Mappings Architecture with Applications to Vision-based Estimation of Articulated Body Pose

A fundamental task of vision systems is to infer the state of the world given some form of visual observations. From a computational perspective, this often involves facing an ill-posed problem; e.g., information is lost via projection of the 3D world into a 2D image. Solution of an ill-posed problem requires additional information, usually provided as a model of the underlying process. It is important that the model be both computationally feasible as well as theoretically well-founded. In this thesis, a probabilistic, nonlinear supervised computational learning model is proposed: the Specialized Mappings Architecture (SMA). The SMA framework is demonstrated in a computer vision system that can estimate the articulated pose parameters of a human body or human hands, given images obtained via one or more uncalibrated cameras. The SMA consists of several specialized forward mapping functions that are estimated automatically from training data, and a possibly known feedback function. Each specialized function maps certain domains of the input space (e.g., image features) onto the output space (e.g., articulated body parameters). A probabilistic model for the architecture is first formalized. Solutions to key algorithmic problems are then derived: simultaneous learning of the specialized domains along with the mapping functions, as well as performing inference given inputs and a feedback function. The SMA employs a variant of the Expectation-Maximization algorithm and approximate inference. The approach allows the use of alternative conditional independence assumptions for learning and inference, which are derived from a forward model and a feedback model. Experimental validation of the proposed approach is conducted in the task of estimating articulated body pose from image silhouettes. Accuracy and stability of the SMA framework is tested using artificial data sets, as well as synthetic and real video sequences of human bodies and hands.

Estimating Human Body Pose from a Single Image via the Specialized Mappings Architecture

A non-linear supervised learning architecture, the Specialized Mapping Architecture (SMA) and its application to articulated body pose reconstruction from single monocular images is described. The architecture is formed by a number of specialized mapping functions, each of them with the purpose of mapping certain portions (connected or not) of the input space, and a feedback matching process. A probabilistic model for the architecture is described along with a mechanism for learning its parameters. The learning problem is approached using a maximum likelihood estimation framework; we present Expectation Maximization (EM) algorithms for two different instances of the likelihood probability. Performance is characterized by estimating human body postures from low level visual features, showing promising results.

Laminar Cortical Dynamics of Visual Form and Motion Interactions During Coherent Object Motion Perception

How do visual form and motion processes cooperate to compute object motion when each process separately is insufficient? A 3D FORMOTION model specifies how 3D boundary representations, which separate figures from backgrounds within cortical area V2, capture motion signals at the appropriate depths in MT; how motion signals in MT disambiguate boundaries in V2 via MT-to-Vl-to-V2 feedback; how sparse feature tracking signals are amplified; and how a spatially anisotropic motion grouping process propagates across perceptual space via MT-MST feedback to integrate feature-tracking and ambiguous motion signals to determine a global object motion percept. Simulated data include: the degree of motion coherence of rotating shapes observed through apertures, the coherent vs. element motion percepts separated in depth during the chopsticks illusion, and the rigid vs. non-rigid appearance of rotating ellipses.

Laminar Cortical Dynamics of Visual Form and Motion Interactions During Coherent Object Motion Perception

How do visual form and motion processes cooperate to compute object motion when each process separately is insufficient? Consider, for example, a deer moving behind a bush. Here the partially occluded fragments of motion signals available to an observer must be coherently grouped into the motion of a single object. A 3D FORMOTION model comprises five important functional interactions involving the brain’s form and motion systems that address such situations. Because the model’s stages are analogous to areas of the primate visual system, we refer to the stages by corresponding anatomical names. In one of these functional interactions, 3D boundary representations, in which figures are separated from their backgrounds, are formed in cortical area V2. These depth-selective V2 boundaries select motion signals at the appropriate depths in MT via V2-to-MT signals. In another, motion signals in MT disambiguate locally incomplete or ambiguous boundary signals in V2 via MT-to-V1-to-V2 feedback. The third functional property concerns resolution of the aperture problem along straight moving contours by propagating the influence of unambiguous motion signals generated at contour terminators or corners. Here, sparse “feature tracking signals” from, e.g., line ends, are amplified to overwhelm numerically superior ambiguous motion signals along line segment interiors. In the fourth, a spatially anisotropic motion grouping process takes place across perceptual space via MT-MST feedback to integrate veridical feature-tracking and ambiguous motion signals to determine a global object motion percept. The fifth property uses the MT-MST feedback loop to convey an attentional priming signal from higher brain areas back to V1 and V2. The model's use of mechanisms such as divisive normalization, endstopping, cross-orientation inhibition, and longrange cooperation is described. Simulated data include: the degree of motion coherence of rotating shapes observed through apertures, the coherent vs. element motion percepts separated in depth during the chopsticks illusion, and the rigid vs. non-rigid appearance of rotating ellipses.

ImageRover: A Content-Based Image Browser for the World Wide Web

ImageRover is a search by image content navigation tool for the world wide web. To gather images expediently, the image collection subsystem utilizes a distributed fleet of WWW robots running on different computers. The image robots gather information about the images they find, computing the appropriate image decompositions and indices, and store this extracted information in vector form for searches based on image content. At search time, users can iteratively guide the search through the selection of relevant examples. Search performance is made efficient through the use of an approximate, optimized k-d tree algorithm. The system employs a novel relevance feedback algorithm that selects the distance metrics appropriate for a particular query.

Image Digestion and Relevance Feedback in the ImageRover WWW Search Engine

ImageRover is a search by image content navigation tool for the world wide web. The staggering size of the WWW dictates certain strategies and algorithms for image collection, digestion, indexing, and user interface. This paper describes two key components of the ImageRover strategy: image digestion and relevance feedback. Image digestion occurs during image collection; robots digest the images they find, computing image decompositions and indices, and storing this extracted information in vector form for searches based on image content. Relevance feedback occurs during index search; users can iteratively guide the search through the selection of relevant examples. ImageRover employs a novel relevance feedback algorithm to determine the weighted combination of image similarity metrics appropriate for a particular query. ImageRover is available and running on the web site.

Estimating 3D Body Pose Using Uncalibrated Cameras

An approach for estimating 3D body pose from multiple, uncalibrated views is proposed. First, a mapping from image features to 2D body joint locations is computed using a statistical framework that yields a set of several body pose hypotheses. The concept of a "virtual camera" is introduced that makes this mapping invariant to translation, image-plane rotation, and scaling of the input. As a consequence, the calibration matrices (intrinsics) of the virtual cameras can be considered completely known, and their poses are known up to a single angular displacement parameter. Given pose hypotheses obtained in the multiple virtual camera views, the recovery of 3D body pose and camera relative orientations is formulated as a stochastic optimization problem. An Expectation-Maximization algorithm is derived that can obtain the locally most likely (self-consistent) combination of body pose hypotheses. Performance of the approach is evaluated with synthetic sequences as well as real video sequences of human motion.

Combining Textual and Visual Cues for Content-based Image Retrieval on the World Wide Web

Some WWW image engines allow the user to form a query in terms of text keywords. To build the image index, keywords are extracted heuristically from HTML documents containing each image, and/or from the image URL and file headers. Unfortunately, text-based image engines have merely retro-fitted standard SQL database query methods, and it is difficult to include images cues within such a framework. On the other hand, visual statistics (e.g., color histograms) are often insufficient for helping users find desired images in a vast WWW index. By truly unifying textual and visual statistics, one would expect to get better results than either used separately. In this paper, we propose an approach that allows the combination of visual statistics with textual statistics in the vector space representation commonly used in query by image content systems. Text statistics are captured in vector form using latent semantic indexing (LSI). The LSI index for an HTML document is then associated with each of the images contained therein. Visual statistics (e.g., color, orientedness) are also computed for each image. The LSI and visual statistic vectors are then combined into a single index vector that can be used for content-based search of the resulting image database. By using an integrated approach, we are able to take advantage of possible statistical couplings between the topic of the document (latent semantic content) and the contents of images (visual statistics). This allows improved performance in conducting content-based search. This approach has been implemented in a WWW image search engine prototype.

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.

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.

A Laminar Cortical Model for 3D Perception of Slanted and Curved Surfaces and of 2D Images: Developement, attention, and Bistability

A model of laminar visual cortical dynamics proposes how 3D boundary and surface representations of slated and curved 3D objects and 2D images arise. The 3D boundary representations emerge from interactions between non-classical horizontal receptive field interactions with intracorticcal and intercortical feedback circuits. Such non-classical interactions contextually disambiguate classical receptive field responses to ambiguous visual cues using cells that are sensitive to angles and disparity gradients with cortical areas V1 and V2. These cells are all variants of bipole grouping cells. Model simulations show how horizontal connections can develop selectively to angles, how slanted surfaces can activate 3D boundary representations that are sensitive to angles and disparity gradients, how 3D filling-in occurs across slanted surfaces, how a 2D Necker cube image can be represented in 3D, and how bistable Necker cuber percepts occur. The model also explains data about slant aftereffects and 3D neon color spreading. It shows how habituative transmitters that help to control developement also help to trigger bistable 3D percepts and slant aftereffects, and how attention can influence which of these percepts is perceived by propogating along some object boundaries.

Effects of Highlights on Gloss Perception

The perception of a glossy surface in a static monochromatic image can occur when a bright highlight is embedded in a compatible context of shading and a bounding contour. Some images naturally give rise to the impression that a surface has a uniform reflectance, characteristic of a shiny object, even though the highlight may only cover a small portion of the surface. Nonetheless, an observer may adopt an attitude of scrutiny in viewing a glossy surface, whereby the impression of gloss is partial and nonuniform at image regions outside of a higlight. Using a rating scale and small probe points to indicate image locations, differential perception of gloss within a single object is investigate in the present study. Observers' gloss ratings are not uniform across the surface, but decrease as a function of distance from highlight. When, by design, the distance from a highlight is uncoupled from the luminance value at corresponding probe points, the decrease in rated gloss correlates more with the distance than with the luminance change. Experiments also indicate that gloss ratings change as a function of estimated surface distance, rather than as a function of image distance. Surface continuity affects gloss ratings, suggesting that apprehension of 3D surface structure is crucial for gloss perception.