Showing papers by "Takeo Kanade published in 1988"

Vision and navigation for the Carnegie-Mellon Navlab

Abstract: A distributed architecture articulated around the CODGER (communication database with geometric reasoning) knowledge database is described for a mobile robot system that includes both perception and navigation tools. Results are described for vision and navigation tests using a mobile testbed that integrates perception and navigation capabilities that are based on two types of vision algorithms: color vision for road following, and 3-D vision for obstacle detection and avoidance. The perception modules are integrated into a system that allows the vehicle to drive continuously in an actual outdoor environment. The resulting system is able to navigate continuously on roads while avoiding obstacles. >

Automatic generation of object recognition programs

Abstract: Issues and techniques are discussed to automatically compile object and sensor models into a visual recognition strategy for recognizing and locating an object in three-dimensional space from visual data. Automatic generation of recognition programs by compilation, in an attempt to automate this process, is described. An object model describes geometric and photometric properties of an object to be recognized. A sensor model specifies the sensor characteristics in predicting object appearances and variations of feature values. It is emphasized that the sensors, as well as objects, must be explicitly modeled to achieve the goal of automatic generation of reliable and efficient recognition programs. Actual creation of interpretation trees for two objects and their execution for recognition from a bin of parts are demonstrated. >

Experimental evaluation of nonlinear feedback and feedforward control schemes for manipulators

Abstract: The manipulator trajectory tracking control problem revolves around computing the torques to be applied to achieve accu rate tracking. This problem has been extensively studied in simulations, but real-time results have been lacking in the robotics literature. In this paper, we present the experimental results of the real-time performance of model-based control algorithms. We compare the computed-torque control scheme with the feedforward dynamics compensation scheme. The feedforward scheme compensates for the manipulator dy namics in the feedforward path, whereas the computed-torque scheme uses the dynamics in the feedback loop for lineariza tion and decoupling. The parameters in the dynamics model for the computed-torque and feedforward schemes were esti mated by using an identification algorithm. Our experiments underscore the importance of including the off-diagonal terms of the manipulator inertia matrix in the torque compu tation. This observation is further supported by our analysis of the dynamics...

Geometric camera calibration using systems of linear equations

Abstract: Geometric camera calibration is the process of determining a mapping between points in world coordinates and the corresponding image locations of the points. In previous methods, calibration typically involved the iterative solution to a system of nonlinear equations. A method is presented for performing camera calibration that provides a complete, accurate solution, using only linear systems of equations. By using two calibration planes, a line-of-sight vector is defined for each pixel in the image. The effective focal point of a camera can be obtained by solving the system that defines the intersection point of the line-of-sight vectors. Once the focal point has been determined, a complete camera model can be obtained with a straightforward least-squares procedure. This method of geometric camera calibration has the advantages of being accurate, efficient, and practical for a wide variety of applications. >

The CMU reconfigurable modular manipulator system

Abstract: Modular manipulator designs have long been been considered for use as research tools, and as the basis for easily modified industrial manipulators. In these manipulators the links and joints are discrete and modular components that can be assembled into a desired manipulator configuration. As hardware advances have made actual modular manipulators practical, various capabilities of such manipulators have gained interest. Particularly desirable is the ability to rapidly reconfigure such a manipulator, in order to custom tailor it to specific tasks. This reconfiguration greatly enhances the capability of a given amount of manipulator hardware. This paper discusses the development of a prototype modular manipulator and the implementation of a configuration independent manipulator kinematics algorithm used for path planning in the prototype.

Image Segmentation and Reflection Analysis Through Color

Abstract: In this paper, we present an approach to color image understanding that can be used to segment and analyze surfaces with color variations due to highlights and shading. We begin with a theory that relates the reflected light from dielectric materials, such as plastic, to fundamental physical reflection processes, and describes the color of the reflected light as a linear combination of the color of the light due to surface reflection (highlights) and body reflection (object color). This theory is used in an algorithm that separates a color image into two parts: an image of just the highlights, and the original image with the highlights removed. In the past, we have applied this method to hand-segmented images. The current paper shows how to perform automatic segmentation method by applying this theory in stages to identify the object and highlight colors. The result is a combination of segmentation and reflection analysis that is better than traditional heuristic segmentation methods (such as histogram thresholding), and provides important physical information about the surface geometry and material properties at the same time. We also show the importance of modeling the camera properties for this kind of quantitative analysis of color. This line of research cRn lead to physics-based image segmentation methods that are both more reliable and more useful than traditional segmentation methods.

Incremental estimation of dense depth maps from image sequences

Abstract: The authors introduce a novel pixel-based (iconic) algorithm that estimates depth and depth uncertainty at each pixel and incrementally refines these estimates over time. They describe the algorithm for translations parallel to the image plane and contrast its formulation and performance to that of a feature-based Kalman filtering algorithm. They compare the performance of the two approaches by analyzing their theoretical convergence rates, by conducting quantitative experiments with images of a flat poster, and by conducting qualitative experiments with images of a realistic outdoor scene model. The results show that the method is an effective way to extract depth from lateral camera translations and suggest that it will play an important role in low-level vision. >

Applying Sensor Models To Automatic Generation Of Object Recognition Programs

Abstract: One of the most important and systematic methods to build modelbased vision systems is that to generate object recognition programs automatically from given geometric models. Automatic generation of object recognition programs requires several key components to be developed: object models to describe the geometric and photometric properties of an object to be recognized, sensor models to predict object appearances from the object model under a given sensor, strategy generation using the pred,icted appearances to produce an recognition strategy, and program generation converting the recognition strategy into an executable code. This paper concentrates on sensor modeling and its relationship with strategy generation, because we regard it as the bottle neck to automatic generation of object recognition programs. We consider two aspects of sensor characteristics: sensor detectability and sensor reliability. Sensor detectability specifies what kinds of features can be detected and in what condition the features are detected; sensor reliability is a confidence for the detected features. We define the configuration space to represent sensor characteristics. We propose a representation method for sensor detectability and rcliability in the configuration space. Finally, we investigate how to use the proposed sensor modcl in automatic generation of an objcct recognition program.

Towards automatic generation of object recognition programs

Abstract: This paper discusses issues and techniques to automatically compile object and sensor models into a visual recognition strategy for recognizing and locating an object in three-dimensional space from visual data. Historically, and even today, most successful model-based vision programs are handwritten; relevant knowledge of objects for recognition is extracted from examples of the object, tailored for the particular environment, and coded into the program by the implementors. If this is done properly, the resulting program is effective and efficient, but it requires long development time and many vision experts. Automatic generation of recognition programs by compilation attempts to automate this process. In particular, it extracts from the object and sensor models those features that are useful for recognition, and the control sequence which must be applied to deal with possible variations of the object appearances. The key components in automatic generation are: object modeling, sensor modeling, prediction of appearances, strategy generation, and program generation. An object model describes geometric and photometric properties of an object to be recognized. A sensor model specifies the sensor characteristics in predicting object appearances and variations of feature values. The appearances can be systematically grouped into aspects, where aspects are topologically equivalent classes with respect to the object features "visible" to the sensor. Once aspects are obtained, a recognition strategy is generated in the form of an interpretation tree from the aspects and their predicted feature values. An interpretation tree consists of two parts: a part which classifies an unknown region into one of the aspects, and a part which determines its precise attitude (position and orientation) within the classified aspect. Finally, the strategy is converted into a executable program by using object-oriented programming. One major emphasis of this paper is that sensors, as well as objects, must be explicitly modeled in order to achieve the goal of automatic generation of reliable and efficient recognition programs. Actual creation of interpretation trees for two toy objects and their execution for recognition from a bin of parts are demonstrated. University Libraries Carnegie Mellon University Pittsburgh, Pennsylvania 1521

Color Image Analysis With An Intrinsic Reflection Model

Abstract: In this paper, we present an approach to color image understanding that can be used to segment and analyze surfaces with color variations due to highlights and shading. We begin with a theory -the Dichromatic Reflection Model - that relates the reflected light from dielectric materials, such as plastic, to fundamental physical reflection processes, and describes the color of the reflected light as a linear combination of the color of the light due to surface reflection (highlights) and body reflection (object color). This dichromatic theory is used in an algorithm that separates a color image into two parts: an image of just the highlights, and the original image with the highlights removed. In the past, we have applied this method to hand- segmented images. This paper shows how to perform automatic segmentation by applying this theory in stages to identify the object and highlight colors, The result is a combination of segmentation and reflection analysis that is better than traditional heuristic segmentation methods and provides important physical information about the surface geometry and material properties at the same time. This line of research can lead to physics-based image understanding methods that are both more reliable and more useful than traditional methods.

Sensor Fusion of Range and Reflectance Data for Outdoor Scene Analysis

Abstract: In recognizing objects in an outdoor scene, range and reflectance (or color) data provide complementary information. Results of experiments in recognizing outdoor scenes containing roads, trees, and cars are presented. The recognition program uses range and reflectance data obtained by a scanning laser range finder, as well as color data from a color TV camera. After segmentation of each image into primitive regions, models of objects are matched using various properties.

The cycle of uncertainty and constraint in robot perception

Abstract: A memorizing aid convenient to memorize foreign words includes an endless tape passing around two rolls and intermittently rotated by pressing a pushbutton. The tape bears information to be memorized, the information being seen through a pair of windows formed in a casing.

Model-Based Vision By Cooperative Processing Of Evidence And Hypotheses Using Configuration Spaces

Abstract: This paper presents a model-based object recognition method which combines a bottom-up evidence accumulation process and a top-down hypothesis verification process. The hypothesize-and-test paradigm is fundamental in model-based vision. However, research issues remain on how the bottom-up process gathers pieces of evidence and when the top-down process should take the lead. To accumulate pieces of evidence, we use a configuration space whose points represent a configuration of an object (ie. position and orientation of an object in an image). If a feature is found which matches a part of an object model, the configuration space is updated to reflect the possible configurations of the object. A region in the configuration space where multiple pieces of evidence from such feature-part matches overlap suggests a high probability that the object exists in an image with a configuration in that region. The cost of the bottom-up process to further accumulate evidence for localization, and that of the top-down process to recognize the object by verification, are compared by considering the size of the search region and the probability of success of verification. If the cost of the top-down process becomes lower, hypotheses are generated and their verification processes are started. The first version of the recognition program has been written and applied to the recognition of a jet airplane in synthetic aperture radar (SAR) images. In creating a model of an object, we have used a SAR simulator as a sensor model, so that we can predict those object features which are reliably detectable by the sensors. The program is being tested with simulated SAR images, and shows promising performance.

End of Year Report for Parallel Vision Algorithm Design and Implementation

Abstract: : Progress on the Parallel Vision project is reported. Three major accomplishments are noted: the development of the Apply language, the WEB library, and benchmarks of Warp for the DARPA image understanding architecture comparisons. The Apply language development includes a description of the language and its implementation on Warp, the Sun, and the Hughes HBA, together with benchmark comparisons of these very different architectures. The WEB library includes over 100 routines; included in this report are performance numbers of these routines on the CMU Warp machine. Finally, a detailed analysis of the Warp routines implemented for the DARPA Image Understanding benchmarks is given. Keywords: Parallel vision, Edge detection, Apply programming language.

Model-Based Vision System by Object-Oriented Programming

Abstract: : This paper presents an approach to using object-oriented programming for the generation of a object recognition program that recognizes a complex 3-D object within a jumbled pile. We generate a recognition program from an interpretation tree that classifies an object into an appropriate attitude group, which has a similar appearance. Each node of an interpretation tree represents a feature matching. We convert each feature extracting or matching operation into an individual processing entity, called an object. Two kinds of objects have been prepared: data objects and event objects. A data object is used for representing geometric objects (such as edges and regions) and extracting features from geometric objects. An event object is used for feature matching and attitude determination. A library of prototypical objects is prepared and an executable program is constructed by properly selecting and instantiating modules from it. The object-oriented programming paradigm provides modularity and extensibility. This method has been applied to the generation of a recognition program for a toy wagon. The generated program has been tested with real scenes and has recognized the wagon in a pile. Keywords: Robotics; Libraries.

Toward Automatic Generation Of Object Recognition Program --- Modeling Sensors ---

Abstract: A model-based vision system requires models in order to predict object appearances. How an object appears in the image is the result of interaction between the object properties and the sensor characteristics. Thus in model-based vision, we ought to model the sensor as well as the object. Previously, the sensor model was not used in model-based vision or, at least, was contained in the object model implicitly. This paper presents a framework between an object model and the object's appearances. We consider two aspects of sensor characteristics: sensor detectability and sensor reliability. Sensor detectability specifies what kinds of features can be detected and in what condition the features are detected; sensor reliability is a confidence for the detected features. We define the configuration space to represent sensor characteristics. We propose a representation method for sensor detectability and reliability in the configuration space. Finally, we investigate how to apply the sensor model to a model-based vision system, in particular, automatic generation of an object recognition program from a given model.

Modeling sensor performance for model-based vision

Abstract: The model-based vision requires object appearances in the computer. How 8n object appears in the image is a result of interaction between the object properties and the sensor characteristics. Thus, in model-based vision, we ought to model the sensor as well as modeling the object. In the past, however, the sensor model was not used in the model-based vision or, at least, was contained in the object model implicitly.

1987 year end report for road following at Carnegie Mellon

Abstract: : This report describes progress in vision and navigation for outdoor mobile robots at the Carnegie Mellon Robotics Institute during 1987. This research centers on guiding outdoor autonomous vehicles. In 1987 we concentrated on five areas: 1) Road following. We expanded our road tracking system to better handle shadows and bright sunlight. 2) Range data interpretation. Our range interpretation work has expanded from processing a single frame, to combining several frames of data into a terrain map. 3) Expert systems for image interpretation. We explored finding roads in very difficult scenes, without relying on strong a priori road color or shape models. 4) Car recognition. We recognize cars in color images by a hierarchy of grouping image features, and predicting where to look for other image features. 5) Geometric camera calibration. Our new method for calibration avoids complex non-linear optimizations found in other calibration schemes.

Nonlinear Feedback and Feedforward Control Schemes for Manipulators

Abstract: 1. Introduction The manipulator trajectory tracking control problem revolves around computing the torques to be applied to achieve accu- rate tracking. This problem has been extensively studied in simulations, but real-time results have been lacking in the robotics lilerature. In this paper, we present the experimental results of the real-time pe$ormance of model-based control algorithms. We compare the computed-torque control scheme with the feedforward dynamics compensation scheme. The feedforward scheme compensates for the manipulator dy- namics in the fiedforward path, whereas the computed-torque scheme uses the dynamics in the feedback loop for lineariza- tion and decoupling. The parameters in the dynamics model for the computed-torque and feedforward schemes were esti- maled by using an identification algorithm. Our experiments underscore the importance of including the ofldiagonal terms of the manipulator inertia matrix in the torque compu- tation. This observation is further supported by our analysis

A novel manipulator technology for space applications

Abstract: Modular manipulator designs have long been considered for use as research tools, and as the basis for easily modified industrial manipulators. In these manipulators the links and joints are discrete and modular components that can be assembled into a desired manipulator configuration. As hardware advances have made actual modular manipulators practical, various capabilities of such manipulators have gained interest. Particularly desirable is the ability to rapidly reconfigure such a manipulator, in order to custom tailor it to specific tasks. The reconfiguration greatly enhances the capability of a given amount of manipulator hardware. The development of a prototype modular manipulator is discussed as well as the implementation of a configuration independent manipulator kinematics algorithm used for path planning in the prototype.