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.

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.

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.

Computer Recognition of Three-Dimensional Objects in a Visual Scene

Methods are presented (1) to partition or decompose a visual scene into the bodies forming it; (2) to position these bodies in three-dimensional space, by combining two scenes that make a stereoscopic pair; (3) to find the regions or zones of a visual scene that belong to its background; (4) to carry out the isolation of objects in (1) when the input has inaccuracies. Running computer programs implement the methods, and many examples illustrate their behavior. The input is a two-dimensional line-drawing of the scene, assumed to contain three-dimensional bodies possessing flat faces (polyhedra); some of them may be partially occluded. Suggestions are made for extending the work to curved objects. Some comparisons are made with human visual perception. The main conclusion is that it is possible to separate a picture or scene into the constituent objects exclusively on the basis of monocular geometric properties (on the basis of pure form); in fact, successful methods are shown.

Global Depth Perception from Familiar Scene Structure

In the absence of cues for absolute depth measurements as binocular disparity, motion, or defocus, the absolute distance between the observer and a scene cannot be measured. The interpretation of shading, edges and junctions may provide a 3D model of the scene but it will not inform about the actual "size" of the space. One possible source of information for absolute depth estimation is the image size of known objects. However, this is computationally complex due to the difficulty of the object recognition process. Here we propose a source of information for absolute depth estimation that does not rely on specific objects: we introduce a procedure for absolute depth estimation based on the recognition of the whole scene. The shape of the space of the scene and the structures present in the scene are strongly related to the scale of observation. We demonstrate that, by recognizing the properties of the structures present in the image, we can infer the scale of the scene, and therefore its absolute mean depth. We illustrate the interest in computing the mean depth of the scene with application to scene recognition and object detection.

Recovering Heading for Visually-Guided Navigation

We present a model for recovering the direction of heading of an observer who is moving relative to a scene that may contain self-moving objects. The model builds upon an algorithm proposed by Rieger and Lawton (1985), which is based on earlier work by Longuet-Higgens and Prazdny (1981). The algorithm uses velocity differences computed in regions of high depth variation to estimate the location of the focus of expansion, which indicates the observer's heading direction. We relate the behavior of the proposed model to psychophysical observations regarding the ability of human observers to judge their heading direction, and show how the model can cope with self-moving objects in the environment. We also discuss this model in the broader context of a navigational system that performs tasks requiring rapid sensing and response through the interaction of simple task-specific routines.

Localization and Positioning Using Combinations of Model Views

A method for localization and positioning in an indoor environment is presented. The method is based on representing the scene as a set of 2D views and predicting the appearances of novel views by linear combinations of the model views. The method is accurate under weak perspective projection. Analysis of this projection as well as experimental results demonstrate that in many cases it is sufficient to accurately describe the scene. When weak perspective approximation is invalid, an iterative solution to account for the perspective distortions can be employed. A simple algorithm for repositioning, the task of returning to a previously visited position defined by a single view, is derived from this method.

Algebraic Functions For Recognition

In the general case, a trilinear relationship between three perspective views is shown to exist. The trilinearity result is shown to be of much practical use in visual recognition by alignment --- yielding a direct method that cuts through the computations of camera transformation, scene structure and epipolar geometry. The proof of the central result may be of further interest as it demonstrates certain regularities across homographies of the plane and introduces new view invariants. Experiments on simulated and real image data were conducted, including a comparative analysis with epipolar intersection and the linear combination methods, with results indicating a greater degree of robustness in practice and a higher level of performance in re-projection tasks.

Range Segmentation Using Visibility Constraints

Visibility constraints can aid the segmentation of foreground objects observed with multiple range images. In our approach, points are defined as foreground if they can be determined to occlude some {em empty space} in the scene. We present an efficient algorithm to estimate foreground points in each range view using explicit epipolar search. In cases where the background pattern is stationary, we show how visibility constraints from other views can generate virtual background values at points with no valid depth in the primary view. We demonstrate the performance of both algorithms for detecting people in indoor office environments.

Learning Object-Independent Modes of Variation with Feature Flow Fields

We present a unifying framework in which "object-independent" modes of variation are learned from continuous-time data such as video sequences. These modes of variation can be used as "generators" to produce a manifold of images of a new object from a single example of that object. We develop the framework in the context of a well-known example: analyzing the modes of spatial deformations of a scene under camera movement. Our method learns a close approximation to the standard affine deformations that are expected from the geometry of the situation, and does so in a completely unsupervised (i.e. ignorant of the geometry of the situation) fashion. We stress that it is learning a "parameterization", not just the parameter values, of the data. We then demonstrate how we have used the same framework to derive a novel data-driven model of joint color change in images due to common lighting variations. The model is superior to previous models of color change in describing non-linear color changes due to lighting.

Monitoring Activities from Multiple Video Streams: Establishing a Common Coordinate Frame

Passive monitoring of large sites typically requires coordination between multiple cameras, which in turn requires methods for automatically relating events between distributed cameras. This paper tackles the problem of self-calibration of multiple cameras which are very far apart, using feature correspondences to determine the camera geometry. The key problem is finding such correspondences. Since the camera geometry and photometric characteristics vary considerably between images, one cannot use brightness and/or proximity constraints. Instead we apply planar geometric constraints to moving objects in the scene in order to align the scene"s ground plane across multiple views. We do not assume synchronized cameras, and we show that enforcing geometric constraints enables us to align the tracking data in time. Once we have recovered the homography which aligns the planar structure in the scene, we can compute from the homography matrix the 3D position of the plane and the relative camera positions. This in turn enables us to recover a homography matrix which maps the images to an overhead view. We demonstrate this technique in two settings: a controlled lab setting where we test the effects of errors in internal camera calibration, and an uncontrolled, outdoor setting in which the full procedure is applied to external camera calibration and ground plane recovery. In spite of noise in the internal camera parameters and image data, the system successfully recovers both planar structure and relative camera positions in both settings.

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.

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.

Contextual Influences on Saliency

This article describes a model for including scene/context priors in attention guidance. In the proposed scheme, visual context information can be available early in the visual processing chain, in order to modulate the saliency of image regions and to provide an efficient short cut for object detection and recognition. The scene is represented by means of a low-dimensional global description obtained from low-level features. The global scene features are then used to predict the probability of presence of the target object in the scene, and its location and scale, before exploring the image. Scene information can then be used to modulate the saliency of image regions early during the visual processing in order to provide an efficient short cut for object detection and recognition.

Automatically Recovering Geometry and Texture from Large Sets of Calibrated Images

Three-dimensional models which contain both geometry and texture have numerous applications such as urban planning, physical simulation, and virtual environments. A major focus of computer vision (and recently graphics) research is the automatic recovery of three-dimensional models from two-dimensional images. After many years of research this goal is yet to be achieved. Most practical modeling systems require substantial human input and unlike automatic systems are not scalable. This thesis presents a novel method for automatically recovering dense surface patches using large sets (1000's) of calibrated images taken from arbitrary positions within the scene. Physical instruments, such as Global Positioning System (GPS), inertial sensors, and inclinometers, are used to estimate the position and orientation of each image. Essentially, the problem is to find corresponding points in each of the images. Once a correspondence has been established, calculating its three-dimensional position is simply a matter of geometry. Long baseline images improve the accuracy. Short baseline images and the large number of images greatly simplifies the correspondence problem. The initial stage of the algorithm is completely local and scales linearly with the number of images. Subsequent stages are global in nature, exploit geometric constraints, and scale quadratically with the complexity of the underlying scene. We describe techniques for: 1) detecting and localizing surface patches; 2) refining camera calibration estimates and rejecting false positive surfels; and 3) grouping surface patches into surfaces and growing the surface along a two-dimensional manifold. We also discuss a method for producing high quality, textured three-dimensional models from these surfaces. Some of the most important characteristics of this approach are that it: 1) uses and refines noisy calibration estimates; 2) compensates for large variations in illumination; 3) tolerates significant soft occlusion (e.g. tree branches); and 4) associates, at a fundamental level, an estimated normal (i.e. no frontal-planar assumption) and texture with each surface patch.