Shape Recipes: Scene Representations that Refer to the Image

The goal of low-level vision is to estimate an underlying scene, given an observed image. Real-world scenes (e.g., albedos or shapes) can be very complex, conventionally requiring high dimensional representations which are hard to estimate and store. We propose a low-dimensional representation, called a scene recipe, that relies on the image itself to describe the complex scene configurations. Shape recipes are an example: these are the regression coefficients that predict the bandpassed shape from bandpassed image data. We describe the benefits of this representation, and show two uses illustrating their properties: (1) we improve stereo shape estimates by learning shape recipes at low resolution and applying them at full resolution; (2) Shape recipes implicitly contain information about lighting and materials and we use them for material segmentation.

Properties and Applications of Shape Recipes

In low-level vision, the representation of scene properties such as shape, albedo, etc., are very high dimensional as they have to describe complicated structures. The approach proposed here is to let the image itself bear as much of the representational burden as possible. In many situations, scene and image are closely related and it is possible to find a functional relationship between them. The scene information can be represented in reference to the image where the functional specifies how to translate the image into the associated scene. We illustrate the use of this representation for encoding shape information. We show how this representation has appealing properties such as locality and slow variation across space and scale. These properties provide a way of improving shape estimates coming from other sources of information like stereo.

Recognizing Indoor Scenes

We propose a scheme for indoor place identification based on the recognition of global scene views. Scene views are encoded using a holistic representation that provides low-resolution spatial and spectral information. The holistic nature of the representation dispenses with the need to rely on specific objects or local landmarks and also renders it robust against variations in object configurations. We demonstrate the scheme on the problem of recognizing scenes in video sequences captured while walking through an office environment. We develop a method for distinguishing between 'diagnostic' and 'generic' views and also evaluate changes in system performances as a function of the amount of training data available and the complexity of the representation.

Procedures as a Representation for Data in a Computer Program for Understanding Natural Language

This paper describes a system for the computer understanding of English. The system answers questions, executes commands, and accepts information in normal English dialog. It uses semantic information and context to understand discourse and to disambiguate sentences. It combines a complete syntactic analysis of each sentence with a "heuristic understander" which uses different kinds of information about a sentence, other parts of the discourse, and general information about the world in deciding what the sentence means. It is based on the belief that a computer cannot deal reasonably with language unless it can "understand" the subject it is discussing. The program is given a detailed model of the knowledge needed by a simple robot having only a hand and an eye. We can give it instructions to manipulate toy objects, interrogate it about the scene, and give it information it will use in deduction. In addition to knowing the properties of toy objects, the program has a simple model of its own mentality. It can remember and discuss its plans and actions as well as carry them out. It enters into a dialog with a person, responding to English sentences with actions and English replies, and asking for clarification when its heuristic programs cannot understand a sentence through use of context and physical knowledge.

A Self-Organizing Multiple-View Representation of 3D Objects

We explore representation of 3D objects in which several distinct 2D views are stored for each object. We demonstrate the ability of a two-layer network of thresholded summation units to support such representations. Using unsupervised Hebbian relaxation, we trained the network to recognise ten objects from different viewpoints. The training process led to the emergence of compact representations of the specific input views. When tested on novel views of the same objects, the network exhibited a substantial generalisation capability. In simulated psychophysical experiments, the network's behavior was qualitatively similar to that of human subjects.

Analytical Representation of Contours

The interpretation and recognition of noisy contours, such as silhouettes, have proven to be difficult. One obstacle to the solution of these problems has been the lack of a robust representation for contours. The contour is represented by a set of pairwise tangent circular arcs. The advantage of such an approach is that mathematical properties such as orientation and curvature are explicityly represented. We introduce a smoothing criterion for the contour tht optimizes the tradeoff between the complexity of the contour and proximity of the data points. The complexity measure is the number of extrema of curvature present in the contour. The smoothing criterion leads us to a true scale-space for contours. We describe the computation of the contour representation as well as the computation of relevant properties of the contour. We consider the potential application of the representation, the smoothing paradigm, and the scale-space to contour interpretation and recognition.

Direct Estimation of Motion and Extended Scene Structure from a Moving Stereo Rig

We describe a new method for motion estimation and 3D reconstruction from stereo image sequences obtained by a stereo rig moving through a rigid world. We show that given two stereo pairs one can compute the motion of the stereo rig directly from the image derivatives (spatial and temporal). Correspondences are not required. One can then use the images from both pairs combined to compute a dense depth map. The motion estimates between stereo pairs enable us to combine depth maps from all the pairs in the sequence to form an extended scene reconstruction and we show results from a real image sequence. The motion computation is a linear least squares computation using all the pixels in the image. Areas with little or no contrast are implicitly weighted less so one does not have to explicitly apply a confidence measure.

Learning with Deictic Representation

Most reinforcement learning methods operate on propositional representations of the world state. Such representations are often intractably large and generalize poorly. Using a deictic representation is believed to be a viable alternative: they promise generalization while allowing the use of existing reinforcement-learning methods. Yet, there are few experiments on learning with deictic representations reported in the literature. In this paper we explore the effectiveness of two forms of deictic representation and a naive propositional representation in a simple blocks-world domain. We find, empirically, that the deictic representations actually worsen performance. We conclude with a discussion of possible causes of these results and strategies for more effective learning in domains with objects.

Tense, Aspect and the Cognitive Representation of Time

This paper explores the relationships between a computation theory of temporal representation (as developed by James Allen) and a formal linguistic theory of tense (as developed by Norbert Hornstein) and aspect. It aims to provide explicit answers to four fundamental questions: (1) what is the computational justification for the primitive of a linguistic theory; (2) what is the computational explanation of the formal grammatical constraints; (3) what are the processing constraints imposed on the learnability and markedness of these theoretical constructs; and (4) what are the constraints that a linguistic theory imposes on representations. We show that one can effectively exploit the interface between the language faculty and the cognitive faculties by using linguistic constraints to determine restrictions on the cognitive representation and vice versa. Three main results are obtained: (1) We derive an explanation of an observed grammatical constraint on tense?? Linear Order Constraint??m the information monotonicity property of the constraint propagation algorithm of Allen's temporal system: (2) We formulate a principle of markedness for the basic tense structures based on the computational efficiency of the temporal representations; and (3) We show Allen's interval-based temporal system is not arbitrary, but it can be used to explain independently motivated linguistic constraints on tense and aspect interpretations. We also claim that the methodology of research developed in this study??oss-level" investigation of independently motivated formal grammatical theory and computational models??a powerful paradigm with which to attack representational problems in basic cognitive domains, e.g., space, time, causality, etc.

Context-Based Vision System for Place and Object Recognition

While navigating in an environment, a vision system has to be able to recognize where it is and what the main objects in the scene are. In this paper we present a context-based vision system for place and object recognition. The goal is to identify familiar locations (e.g., office 610, conference room 941, Main Street), to categorize new environments (office, corridor, street) and to use that information to provide contextual priors for object recognition (e.g., table, chair, car, computer). We present a low-dimensional global image representation that provides relevant information for place recognition and categorization, and how such contextual information introduces strong priors that simplify object recognition. We have trained the system to recognize over 60 locations (indoors and outdoors) and to suggest the presence and locations of more than 20 different object types. The algorithm has been integrated into a mobile system that provides real-time feedback to the user.

Toward a Theory of Representation Design

This research is concerned with designing representations for analytical reasoning problems (of the sort found on the GRE and LSAT). These problems test the ability to draw logical conclusions. A computer program was developed that takes as input a straightforward predicate calculus translation of a problem, requests additional information if necessary, decides what to represent and how, designs representations capturing the constraints of the problem, and creates and executes a LISP program that uses those representations to produce a solution. Even though these problems are typically difficult for theorem provers to solve, the LISP program that uses the designed representations is very efficient.

On Interpreting Stereo Disparity

The problems under consideration center around the interpretation of binocular stereo disparity. In particular, the goal is to establish a set of mappings from stereo disparity to corresponding three-dimensional scene geometry. An analysis has been developed that shows how disparity information can be interpreted in terms of three-dimensional scene properties, such as surface depth, discontinuities, and orientation. These theoretical developments have been embodied in a set of computer algorithms for the recovery of scene geometry from input stereo disparity. The results of applying these algorithms to several disparity maps are presented. Comparisons are made to the interpretation of stereo disparity by biological systems.

The Role of Knowledge in Visual Shape Representation

This report shows how knowledge about the visual world can be built into a shape representation in the form of a descriptive vocabulary making explicit the important geometrical relationships comprising objects' shapes. Two computational tools are offered: (1) Shapestokens are placed on a Scale-Space Blackboard, (2) Dimensionality-reduction captures deformation classes in configurations of tokens. Knowledge lies in the token types and deformation classes tailored to the constraints and regularities ofparticular shape worlds. A hierarchical shape vocabulary has been implemented supporting several later visual tasks in the two-dimensional shape domain of the dorsal fins of fishes.

TYPICAL: A Knowledge Representation System for Automated Discovery and Inference

TYPICAL is a package for describing and making automatic inferences about a broad class of SCHEME predicate functions. These functions, called types following popular usage, delineate classes of primitive SCHEME objects, composite data structures, and abstract descriptions. TYPICAL types are generated by an extensible combinator language from either existing types or primitive terminals. These generated types are located in a lattice of predicate subsumption which captures necessary entailment between types; if satisfaction of one type necessarily entail satisfaction of another, the first type is below the second in the lattice. The inferences make by TYPICAL computes the position of the new definition within the lattice and establishes it there. This information is then accessible to both later inferences and other programs (reasoning systems, code analyzers, etc) which may need the information for their own purposes. TYPICAL was developed as a representation language for the discovery program Cyrano; particular examples are given of TYPICAL's application in the Cyrano program.

Image Chunking: Defining Spatial Building Blocks for Scene Analysis

Rapid judgments about the properties and spatial relations of objects are the crux of visually guided interaction with the world. Vision begins, however, with essentially pointwise representations of the scene, such as arrays of pixels or small edge fragments. For adequate time-performance in recognition, manipulation, navigation, and reasoning, the processes that extract meaningful entities from the pointwise representations must exploit parallelism. This report develops a framework for the fast extraction of scene entities, based on a simple, local model of parallel computation.sAn image chunk is a subset of an image that can act as a unit in the course of spatial analysis. A parallel preprocessing stage constructs a variety of simple chunks uniformly over the visual array. On the basis of these chunks, subsequent serial processes locate relevant scene components and assemble detailed descriptions of them rapidly. This thesis defines image chunks that facilitate the most potentially time-consuming operations of spatial analysis---boundary tracing, area coloring, and the selection of locations at which to apply detailed analysis. Fast parallel processes for computing these chunks from images, and chunk-based formulations of indexing, tracing, and coloring, are presented. These processes have been simulated and evaluated on the lisp machine and the connection machine.