A direct adaptive tracking control architecture is proposed and evaluated for a class of continuous -time nonlinear dynamic systems for which an explicit linear parameterization of the uncertainty in the dynamics is either unknown or impossible. The architecture employs a network of gaussian radial basis functions to adaptively compensate for the plant nonlinearities. Under mild assumptions about the degree of smoothness exhibited by the nonlinear functions, the algorithm is proven to be globally stable, with tracking errors converging to a neighborhood of zero. A constructive procedure is detailed, which directly translates the assumed smoothness properties of the nonlinearities involved into a specification of the network required to represent the plant to a chosen degree of accuracy. A stable weight adjustment mechanism is then determined using Lyapunov theory. The network construction and performance of the resulting controller are illustrated through simulations with example syst...

We propose a unified approach to solve low, intermediate and high level computer vision problems for 3D object recognition from range images. All three levels of computation are cast in an optimization framework and can be implemented on neural network style architecture. In the low level computation, the tasks are to estimate curvature images from the input range data. Subsequent processing at the intermediate level is concerned with segmenting these curvature images into coherent curvature sign maps. In the high level, image features are matched against model features based on an object description called attributed relational graph (ARG). We show that the above computational tasks at each of the three different levels can all be formulated as optimizing a two-term energy function. The first term encodes unary constraints while the second term binary ones. These energy functions are minimized using parallel and distributed relaxation-based algorithms which are well suited for neural...

This article describes a project to design and build prototype analog early vision systems that are remarkably low-power, small, and fast. Three chips are described in detail. A continuous-time CMOS imager and processor chip uses a fully parallel 2-D resistive grid to find an object's position and orientation at 5000 frames/second, using only 30 milliwatts of power. A CMOS/CCD imager and processor chip does high-speed image smoothing and segmentation in a clocked, fully parallel 2-D array. And a chip that merges imperfect depth and slope data to produce an accurate depth map is under development in switched-capacitor CMOS technology. (see also Parallel networks for machine vision – Horn - 1988)

In 1986, Tanner and Mead [1] implemented an interesting constraint satisfaction circuit for global motion sensing in aVLSI. We report here a new and improved aVLSI implementation that provides smooth optical flow as well as global motion in a two dimensional visual field. The computation of optical flow is an ill-posed problem, which expresses itself as the aperture problem. However, the optical flow can be estimated by the use of regularization methods, in which additional constraints are introduced in terms of a global energy functional that must be minimized. We show how the algorithmic constraints of Horn and Schunck [2] on computing smooth optical flow can be mapped onto the physical constraints of an equivalent electronic network. 1 Motivation The perception of apparent motion is crucial for navigation. Knowledge of local motion of the environment relative to the observer simplifies the calculation of important tasks such as time-to-contact or focus-of-expansion. There are sever...

that of a biological vision. The two most critical features presently missing from the machine vision are lo}v latency processing and top-dow sen. sorv adaptation. This thesis proposes to overcome these two deficiencies by implementing global operations in computational sensors.

This thesis examines a complete design framework for a real-time, autonomous system with specialized VLSI hardware for computing 3-D camera motion. In the proposed architecture, the first step is to determine point correspondences between two images. Two processors, a CCD array edge detector and a mixed analog/digital binary block correlator, are proposed for this task. The report is divided into three parts. Part I covers the algorithmic analysis; part II describes the design and test of a 32\Theta32 CCD edge detector fabricated through MOSIS; and part III compares the design of the mixed analog/digital correlator to a fully digital implementation. Copyright c fl Massachusetts Institute of Technology, 1993 This report describes research done at the Artificial Intelligence Laboratory of the Massachusetts Institute of Technology in collaboration with the Analog VLSI for Machine Vision research project. Support for the Laboratory's research is provided in part by the ARPA contract N000...

Abstract — We describe a compound eye vision sensor for 3D ego motion computation. Inspired by eyes of insects, we show that the compound eye sampling geometry is optimal for 3D camera motion estimation. This optimality allows us to estimate the 3D camera motion in a scene-independent and robust manner by utilizing linear equations. The mathematical model of the new sensor can be implemented in analog networks resulting in a compact computational sensor for instantaneous 3D ego motion measurements in full six degrees of freedom. Key words: analog VLSI; 3D motion sensor; parallel imaging sensor; robot vision; insect vision; 3D ego motion I.

In the course of designing an integrated system for locating the focus of expansion (FOE) from a sequence of images taken while a camera is translating, a variety of direct motion vision algorithms based on image brightness gradients have been studied (McQuirk, 1991, 1996b). The location of the FOE is the intersection of the translation vector of the camera with the image plane, and hence gives the direction of camera motion. This paper describes two approaches that appeared promising for analog very large scale integrated (VLSI) circuit implementation. In particular, two algorithms based on these approaches are compared with respect to bias, robustness to noise, and suitability for realization in analog VLSI. From these results, one algorithm was chosen for implementation. This paper also briefly discuss the real-time analog CMOS/CCD VLSI architecture realized in the FOE chip.

A direct adaptive tracking control architecture is proposed and evaluated for a class of continuous-time nonlinear dynamic systems for which an explicit linear parameterization of the uncertainty in the dynamics is either unknown or impossible. The architecture employs a network of gaussian radial basis functions to adaptively compensate for the plant nonlinearities. Under mild assumptions about the degree of smoothness exhibited by the nonlinear functions, the algorithm is proven to be stable, with tracking errors converging to a neighborhood of zero. A constructive procedure is detailed, which directly translates the assumed smoothness properties of the nonlinearities involved into a specification of the network required to represent the plant to a chosen degree of accuracy. A stable weight adjustment mechanism is then determined using Lyapunov theory. The network construction and performance of the resulting controller are illustrated through simulations with an example system. 1 ...

Early nd intermediate vision algorithms, such as smoothing and discontinuity detection, re often implemented on general-purpose serial, and, more recently, parallel computers. The excessive time required by these general-purpose computers prevents real-time computation of these vision algorithms. Special-purpose hardware implementations of low-level vision algorithms may be needed to achieve real-time processing.