Parallel Networks for Machine Vision

The amount of computation required to solve many early vision problems is prodigious, and so it has long been thought that systems that operate in a reasonable amount of time will only become feasible when parallel systems become available. Such systems now exist in digital form, but most are large and expensive. These machines constitute an invaluable test-bed for the development of new algorithms, but they can probably not be scaled down rapidly in both physical size and cost, despite continued advances in semiconductor technology and machine architecture. Simple analog networks can perform interesting computations, as has been known for a long time. We have reached the point where it is feasible to experiment with implementation of these ideas in VLSI form, particularly if we focus on networks composed of locally interconnected passive elements, linear amplifiers, and simple nonlinear components. While there have been excursions into the development of ideas in this area since the very beginnings of work on machine vision, much work remains to be done. Progress will depend on careful attention to matching of the capabilities of simple networks to the needs of early vision. Note that this is not at all intended to be anything like a review of the field, but merely a collection of some ideas that seem to be interesting.

Computational Vision: A Critical Review

We review the progress made in computational vision, as represented by Marr's approach, in the last fifteen years. First, we briefly outline computational theories developed for low, middle and high-level vision. We then discuss in more detail solutions proposed to three representative problems in vision, each dealing with a different level of visual processing. Finally, we discuss modifications to the currently established computational paradigm that appear to be dictated by the recent developments in vision.

A Comparison of Hardware Implementations for Low-Level Vision Algorithms

Early and intermediate vision algorithms, such as smoothing and discontinuity detection, are often implemented on general-purpose serial, and more recently, parallel computers. Special-purpose hardware implementations of low-level vision algorithms may be needed to achieve real-time processing. This memo reviews and analyzes some hardware implementations of low-level vision algorithms. Two types of hardware implementations are considered: the digital signal processing chips of Ruetz (and Broderson) and the analog VLSI circuits of Carver Mead. The advantages and disadvantages of these two approaches for producing a general, real-time vision system are considered.

Towards Autonomous Motion Vision

Earlier, we introduced a direct method called fixation for the recovery of shape and motion in the general case. The method uses neither feature correspondence nor optical flow. Instead, it directly employs the spatiotemporal gradients of image brightness. This work reports the experimental results of applying some of our fixation algorithms to a sequence of real images where the motion is a combination of translation and rotation. These results show that parameters such as the fization patch size have crucial effects on the estimation of some motion parameters. Some of the critical issues involved in the implementaion of our autonomous motion vision system are also discussed here. Among those are the criteria for automatic choice of an optimum size for the fixation patch, and an appropriate location for the fixation point which result in good estimates for important motion parameters. Finally, a calibration method is described for identifying the real location of the rotation axis in imaging systems.

How do Humans Determine Reflectance Properties under Unknown Illumination?

Under normal viewing conditions, humans find it easy to distinguish between objects made out of different materials such as plastic, metal, or paper. Untextured materials such as these have different surface reflectance properties, including lightness and gloss. With single isolated images and unknown illumination conditions, the task of estimating surface reflectance is highly underconstrained, because many combinations of reflection and illumination are consistent with a given image. In order to work out how humans estimate surface reflectance properties, we asked subjects to match the appearance of isolated spheres taken out of their original contexts. We found that subjects were able to perform the task accurately and reliably without contextual information to specify the illumination. The spheres were rendered under a variety of artificial illuminations, such as a single point light source, and a number of photographically-captured real-world illuminations from both indoor and outdoor scenes. Subjects performed more accurately for stimuli viewed under real-world patterns of illumination than under artificial illuminations, suggesting that subjects use stored assumptions about the regularities of real-world illuminations to solve the ill-posed problem.

A Binocular, Foveated Active Vision System

This report documents the design and implementation of a binocular, foveated active vision system as part of the Cog project at the MIT Artificial Intelligence Laboratory. The active vision system features a three degree of freedom mechanical platform that supports four color cameras, a motion control system, and a parallel network of digital signal processors for image processing. To demonstrate the capabilities of the system, we present results from four sample visual-motor tasks.

Exploring Vision-Based Interfaces: How to Use Your Head in Dual Pointing Tasks

The utility of vision-based face tracking for dual pointing tasks is evaluated. We first describe a 3-D face tracking technique based on real-time parametric motion-stereo, which is non-invasive, robust, and self-initialized. The tracker provides a real-time estimate of a ?frontal face ray? whose intersection with the display surface plane is used as a second stream of input for scrolling or pointing, in paral-lel with hand input. We evaluated the performance of com-bined head/hand input on a box selection and coloring task: users selected boxes with one pointer and colors with a second pointer, or performed both tasks with a single pointer. We found that performance with head and one hand was intermediate between single hand performance and dual hand performance. Our results are consistent with previously reported dual hand conflict in symmetric pointing tasks, and suggest that a head-based input stream should be used for asymmetric control.

Seeing 'Ghost' Solutions in Stereo Vision

A unique matching is a stated objective of most computational theories of stereo vision. This report describes situations where humans perceive a small number of surfaces carried by non-unique matching of random dot patterns, although a unique solution exists and is observed unambiguously in the perception of isolated features. We find both cases where non-unique matchings compete and suppress each other and cases where they are all perceived as transparent surfaces. The circumstances under which each behavior occurs are discussed and a possible explanation is sketched. It appears that matching reduces many false targets to a few, but may still yield multiple solutions in some cases through a (possibly different) process of surface interpolation.

Vision by Man and Machine

The development of increasingly sophisticated and powerful computers in the last few decades has frequently stimulated comparisons between them and the human brain. Such comparisons will become more earnest as computers are applied more and more to tasks formerly associated with essentially human activities and capabilities. The expectation of a coming generation of "intelligent" computers and robots with sensory, motor and even "intellectual" skills comparable in quality to (and quantitatively surpassing) our own is becoming more widespread and is, I believe, leading to a new and potentially productive analytical science of "information processing". In no field has this new approach been so precisely formulated and so thoroughly exemplified as in the field of vision. As the dominant sensory modality of man, vision is one of the major keys to our mastery of the environment, to our understanding and control of the objects which surround us. If we wish to created robots capable of performing complex manipulative tasks in a changing environment, we must surely endow them with (among other things) adequate visual powers. How can we set about designing such flexible and adaptive robots? In designing them, can we make use of our rapidly growing knowledge of the human brain, and if so, how at the same time, can our experiences in designing artificial vision systems help us to understand how the brain analyzes visual information?

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.

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.

Mid-Level Vision and Recognition of Non-Rigid Objects

We address mid-level vision for the recognition of non-rigid objects. We align model and image using frame curves - which are object or "figure/ground" skeletons. Frame curves are computed, without discontinuities, using Curved Inertia Frames, a provably global scheme implemented on the Connection Machine, based on: non-cartisean networks; a definition of curved axis of inertia; and a ridge detector. I present evidence against frame alignment in human perception. This suggests: frame curves have a role in figure/ground segregation and in fuzzy boundaries; their outside/near/top/ incoming regions are more salient; and that perception begins by setting a reference frame (prior to early vision), and proceeds by processing convex structures.

Vision, Instruction, and Action

This thesis describes Sonja, a system which uses instructions in the course of visually-guided activity. The thesis explores an integration of research in vision, activity, and natural language pragmatics. Sonja's visual system demonstrates the use of several intermediate visual processes, particularly visual search and routines, previously proposed on psychophysical grounds. The computations Sonja performs are compatible with the constraints imposed by neuroscientifically plausible hardware. Although Sonja can operate autonomously, it can also make flexible use of instructions provided by a human advisor. The system grounds its understanding of these instructions in perception and action.

Progress in Vision and Robotics

The Vision Flashes are informal working papers intended primarily to stimulate internal interaction among participants in the A.I. Laboratory's Vision and Robotics group. Many of them report highly tentative conclusions or incomplete work. Others deal with highly detailed accounts of local equipment and programs that lack general interest. Still others are of great importance, but lack the polish and elaborate attention to proper referencing that characterizes the more formal literature. Nevertheless, the Vision Flashes collectively represent the only documentation of an important fraction of the work done in machine vision and robotics. The purpose of this report is to make the findings more readily available, but since they are not revised as presented here, readers should keep in mind the original purpose of the papers!