Showing papers by "Takeo Kanade published in 1989"

Kalman Filter-based Algorithms for Estimating Depth from Image Sequences

Abstract: Using known camera motion to estimate depth from image sequences is an important problem in robot vision. Many applications of depth-from-motion, including navigation and manipulation, require algorithms that can estimate depth in an on-line, incremental fashion. This requires a representation that records the uncertainty in depth estimates and a mechanism that integrates new measurements with existing depth estimates to reduce the uncertainty over time. Kalman filtering provides this mechanism. Previous applications of Kalman filtering to depth-from-motion have been limited to estimating depth at the location of a sparse set of features. In this paper, we introduce a new, pixel-based (iconic) algorithm that estimates depth and depth uncertainty at each pixel and incrementally refines these estimates over time. We describe the algorithm and contrast its formulation and performance to that of a feature-based Kalman filtering algorithm. We 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 new method is an effective way to extract depth from lateral camera translations. This approach can be extended to incorporate general motion and to integrate other sources of information, such as stereo. The algorithms we have developed, which combine Kalman filtering with iconic descriptions of depth, therefore can serve as a useful and general framework for low-level dynamic vision.

A physical approach to color image understanding

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. The work is based on a theory—the Dichromatic Reflection Model—which describes the color of the reflected light as a mixture of light from surface reflection (highlights) and body reflection (object color). In the past, we have shown how the dichromatic theory can be used to separate a color image into two intrinsic reflection images: an image of just the highlights, and the original image with the highlights removed. At that time, the algorithm could only be applied to hand-segmented images. This paper shows how the same reflection model can be used to include color image segmentation into the image analysis. The result is a color image understanding system, capable of generating physical descriptions of the reflection processes occurring in the scene. Such descriptions include the intrinsic reflection images, an image segmentation, and symbolic information about the object and highlight colors. This line of research can lead to physicsbased image understanding methods that are both more reliable and more useful than traditional methods.

Determining shape and reflectance of hybrid surfaces by photometric sampling

Abstract: A method is presented for determining the shapes of hybrid surfaces without prior knowledge of the relative strengths of the Lambertian and specular components of reflection. The object surface is illuminated using extended light sources and is viewed from a single direction. Surface illumination using extended sources makes it possible to ensure the detection of both Lambertian and specular reflections. Uniformly distributed source directions are used to obtain an image sequence of the object. This method of obtaining photometric measurements is called photometric sampling. An extraction algorithm uses the set of image intensity values measured at each surface point to compute orientation as well as relative strengths of the Lambertian and specular reflection components. The simultaneous recovery of shape and reflectance parameters enables the method to adapt to variations in reflectance properties from one scene point to another. Experiments were conducted on Lambertian surfaces, specular surfaces, and hybrid surfaces. >

Terrain mapping for a roving planetary explorer

Abstract: The authors are prototyping a legged vehicle, the Ambler, for an exploratory mission on another planet, conceivably Mars, where it is to traverse uncharted areas and collect material samples. They describe how the rover can construct from range imagery a geometric terrain representation, i.e., elevation map that includes uncertainty, unknown areas, and local features. First, they present an algorithm for constructing an elevation map from a single range image. By virtue of working in spherical-polar space, the algorithm is independent of the desired map resolution and the orientation of the sensor, unlike algorithms that work in Cartesian space. Secondly, the authors present a two-stage matching technique (feature matching followed by iconic matching) that identifies the transformation T corresponding to the vehicle displacement between two viewing positions. Thirdly, to support legged locomotion over rough terrain, they describe methods for evaluating regions of the constructed elevation maps as footholds. >

Ambler: an autonomous rover for planetary exploration

Abstract: The authors are building a prototype legged rover, called the Ambler (loosely an acronym for autonomous mobile exploration robot) and testing it on full-scale, rugged terrain of the sort that might be encountered on the Martian surface. They present an overview of their research program, focusing on locomotion, perception, planning, and control. They summarize some of the most important goals and requirements of a rover design and describe how locomotion, perception, and planning systems can satisfy these requirements. Since the program is relatively young (one year old at the time of writing) they identify issues and approaches and describe work in progress rather than report results. It is expected that many of the technologies developed will be applicable to other planetary bodies and to terrestrial concerns such as hazardous waste assessment and remediation, ocean floor exploration, and mining. >

3-D vision techniques for autonomous vehicles

Abstract: A mobile robot is a vehicle that navigates autonomously through an unknown or partially known environment. Research in the field of mobile robots has received considerable attention in the past decade due to its wide range of potential applications, from surveillance to planetary exploration, and the research opportunities it provides, including virtually the whole spectrum of robotics research from vehicle control to symbolic planning (see for example [Har88b] for an analysis of the research issues in mobile robots). In this paper we present our investigation of some the issues in one of the components of mobile robots: perception. The role of perception in mobile robots is to transform data from sensors into representations that can be used by the decision-making components of the system. The simplest example is the detection of potentially dangerous regions in the environment (i. e. obstacles) that can be used by a path planner whose role is to generate safe trajectories for the vehicle. An example of a more complex situation is a mission that requires the recognition of specific landmarks, in which case the perception components must produce complex descriptions of the sensed environment and relate them to stored models of the landmarks.

Real-time implementation and evaluation of the computed-torque scheme

Abstract: Experimental results on the real-time performance of model-based control algorithms are presented. The computed-torque scheme which utilizes the complete dynamics model of the manipulator was compared to the independent joint control scheme, which assumes a decoupled and linear model of the manipulator dynamics. The two manipulator control schemes have been implemented on the Carnegie-Mellon University DD (direct-drive) Arm II with a sampling period of 2 ms. The authors discuss the design of controller gains for both the computed-torque and the independent joint control schemes and establish a framework for comparing their trajectory-tracking performances. It is shown that the computed-torque scheme outperforms the independent joint control scheme as long as there is not torque saturation in the actuators. Based on the experimental results, the authors conclusively establish the importance of compensating for the nonlinear Coriolis and centrifugal forces even at low speeds of operation. >

Surface reflection: Physical and geometrical perspectives

Abstract: Reflectance models based on physical optics and geometrical optics are studied. Specifically, the authors consider the Beckmann-Spizzichino (physical optics) model and the Torrance-Sparrow (geometrical optics) model. These two models were chosen because they have been reported to fit experimental data well. Each model is described in detail, and the conditions that determine the validity of the model are clearly stated. By studying reflectance curves predicted by the two models, the authors propose a reflectance framework comprising three components: the diffuse lobe, the specular lobe, and the specular spike. The effects of surface roughness on the three primary components are analyzed in detail. >

Modeling sensors: toward automatic generation of object recognition program

Abstract: One of the most important and systematic methods of building model-based vision systems is that of generating 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 the object to be recognized, sensor models to predict object appearances from the object model under a given sensor, strategy generation using the predicted appearances to produce a recognition strategy, and program generation converting the recognition strategy into an executable code. This paper concentrates on sensor modeling and its relationship to strategy generation, because we regard it as the bottleneck 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 featuers can be detected and under what conditions the features are detected; sensor reliability is a confidence level for the detected features. We define a configuration space to represent sensor characteristics. Then, we propose a representation method for sensor detectability and reliability in the configuration space. Finally, we investigate how to use the proposed sensor model in automatic generation of object recognition programs.

Determining shape and reflectance of Lambertian, specular, and hybrid surfaces using extended sources

Abstract: A method is presented for determining the shape of surfaces whose reflectance properties can vary from Lambertian to specular, without prior knowledge of the relative strengths of the Lambertian and specular components of reflection The object surface is illuminated using extended light sources and is viewed from a single direction Surface illumination using extended sources makes it possible to ensure the detection of both Lambertian and specular reflections Multiple source directions are used to obtain an image sequence of the object An extraction algorithm uses the set of image intensity values measured at each surface point to compute orientation as well as relative strengths of the Lambertian and specular reflection components The method, photometric sampling, uses samples of a photometric function that relates image intensity to surface orientation, reflectance, and light source characteristics Experiments conducted on Lambertian surfaces, specular surfaces, and hybrid surfaces show high accuracy in measured orientations and estimated reflectance parameters >

CHIMERA: a real-time programming environment for manipulator control

Abstract: CHIMERA is a real-time computing environment used in the Reconfigurable Modular Manipulator System project. CHIMERA, which is both a hardware and software environment, allows rapid development and implementation of real-time control programs. It provides a C/Unix-flavored concurrent programming environment for a Motorola 68020 multiprocessor hardware configuration connected to a Sun workstation. CHIMERA has been implemented using commercial hardware in conjunction with a sophisticated, locally developed software package, resulting in a reliable, reasonably priced, and easily duplicated system. CHIMERA is currently being ported for real-time control of the CMU Direct Drive Arm II. The authors describe the implementation and capabilities of the CHIMERA environment and illustrate how these features are used in robot control applications. >

A perception system for a planetary explorer

Abstract: To perform planetary exploration without human supervision, a completely autonomous robot must be able to model its environment and to locate itself while exploring its surroundings. For that purpose, the authors propose a modular perception system for an autonomous explorer. The perception system maintains a consistent internal representation of the observed terrain from multiple sensor views. The representation can be accessed from other modules through queries. The perception system is intended to be used by the Ambler, a six-legged vehicle being built at the authors' university. A partial implementation of the system using a range scanner is presented as well as experimental results on a testbed that includes the sensor, one computer-controlled leg, and obstacles on a sandy surface. >

1988 Year End Report for Road Following at Carnegie Mellon

Abstract: : This report describes the progress in vision and navigation for outdoor mobile robots at the Carnegie Mellon Robotics Institute during 1988 This research was primarily sponsored by DARPA as part of the Strategic Computing Initiative Portions of this research were also partially supported by the National Science Foundation and Digital Corporation In the four years of the project, we have built perception modules for following roads, detecting obstacles, mapping terrain, and recognizing objects Together with our sister 'Integration' contract, we have built systems that drive mobile robots along roads and cross country, and have gained valuable insights into viable approaches for outdoor mobile robot research This work is briefly summarized in Chapter 1 of this report Specifically in 1988, we have completed one color vision system for finding roads, begun two others that handle difficult lighting and structured public roads and highways, and built a road-following system that uses active scanning with a laser rangefinder We have used 3-D information to build elevation maps for cross-country path planning, and have used maps to retraverse a route Progress in 1988 on these projects is described briefly in Chapter 1, and in more detail in the following chapters

Perception For Rugged Terrain

Abstract: A three-dimensional perception system for building a geometrical description of rugged terrain environments from range image data is presented with reference to the exploration of the rugged terrain of Mars. An intermediate representation consisting of an elevation map that includes an explicit representation of uncertainty and labeling of the occluded regions is proposed. The locus method used to convert range image to an elevation map is introduced, along with an uncertainty model based on this algorithm. Both the elevation map and the locus method are the basis of a terrain matching algorithm which does not assume any correspondences between range images. The two-stage algorithm consists of a feature-based matching algorithm to compute an initial transform and an iconic terrain matching algorithm to merge multiple range images into a uniform representation. Terrain modeling results on real range images of rugged terrain are presented. The algorithms considered are a fundamental part of the perception system for the Ambler, a legged locomotor.

Shape and reflectance from an image sequence generated using extended sources

Abstract: The authors present a method for determining the shapes of surfaces whose reflectance properties may vary from Lambertian to specular, without prior knowledge of the relative strengths of the Lambertian and specular components of reflection. The object surface is illuminated using extended light sources and is viewed from a single direction. Surface illumination using extended sources makes it possible to ensure the detection of both Lambertian and specular reflections. Multiple source directions are used to obtain an image sequence of the object. An extraction algorithm uses the set of image intensity values measured at each surface point to compute orientation as well as relative strengths of the Lambertian and specular reflection components. The proposed method is called photometric sampling, as it uses samples of photometric function that relates image intensity to surface orientation, reflectance, and light source characteristics. Experiments were conducted on Lambertian surfaces, specular surfaces, and hybrid surfaces, whose reflectance models are composed of both Lambertian and specular components. The results show high accuracy in measured orientations and estimated reflectance parameters. >

First Results in Terrain Mapping for a Roving Planetary Explorer

Abstract: To perform planetary exploration without human supervision, a complete autonomous rover must be able to model its environment while exploring its surroundings. Researchers present a new algorithm to construct a geometric terrain representation from a single range image. The form of the representation is an elevation map that includes uncertainty, unknown areas, and local features. By virtue of working in spherical-polar space, the algorithm is independent of the desired map resolution and the orientation of the sensor, unlike other algorithms that work in Cartesian space. They also describe new methods to evaluate regions of the constructed elevation maps to support legged locomotion over rough terrain.

Computer analysis of regular repetitive textures

Abstract: Regular rcpttitive texam arc common in rcal-workl scaux, occurring in both n a n d and man-made environments. Their analysis is important for image segmentatim and fos shape recovery from surf= texture. There are two fundamental problems in analyzing reguiar repetitive texture. F d y , rbc frcsucncy interpretation of any regular t e x m is ambiguous since that arc many altanative imqmatiap tbatccmspmd to the same texture. Secondiy, the v a y definition of regular repetition is c i m h since the elanencard the repetitive hzquency are defined in tamsof each otber. In this papa, we address tbcsc t w o p o b l a n s a n d ~ a n a u s w c r to each. To address the ambiguity of finqpmcy htmpmaa 'on we p~lll to the lattice theory and choose sucassiivc minima as the most fpndamental fnquaq vccuxs of the t~topre. To deal with thedcfidkm OfregularnpetitiOn, we compare t h e S t C U C t U d ~ topnmimtntfcaMesinthe~Tbesttbearmcal concepsarehrporatcdintoa working systrm, capable of d y z i a g and scgmauing regular repshive tcxtlacs in real-world images. In contrast with pevioruwark, ora tcchniqueinvolv csentirely localanalysisaadistherebyrobusttotcxture distonion. Regular repetitive exaxes are CQI~IIY)EI in real-worfd scenes. Tbey occur both as arcSulL of natural pmcesses (e-g. the repetitive mom of reptile skin) and the eff.m of man (eg. man's aukiag of a city scc11c). Understanding these textures is imponam not only as abasis for image SCgmGntation butaiso because regular repetitive textures can provi&valuabIcinfonnationfor~gsrtrfactopieatatioa A fundamental problem in analyzing regular textures, howeva, is that the &finition of regular repetitive texture is circular. The fnsoencr of the texture is Mined as the spatial dispiacancnt becwccn elantnts of the texture. but the element of the texture is defined as that portion of the image that is ngulariy rcpeatcd This circular dependency is usually handXed by obtaining information about the reptitivc iiesuenCy without considaing the natllre of the texture element or vice vasa. In both applloaches a global adysis of the textme is pufkxmcd, restricting the applicability oftheaIglxithstoundistoro#i samplesdasin@crepetitivetcxture In comas to these approaches, omwurkanploys apmdyfocalaaaiysis toidentify tbe repetitive structure of the m o s ~ (&minant) fin nsplarnqeitive ocrmres i n d d images. In this way, we identify the resnlarnpecitive=hti-m * between textme elemenowithoatirtntifvinp the texMeeianeau themselves. A second problem in aaaIyzing regular repetitive textmw is that: cvtll whea we know the locations of textw eluxmts, tbue are many alternative pairs of fhqwncy vccmrs hat equally dcscribc the pattcnr of the texture

Distributed quadtree processing

Abstract: Quadtrees have been widely used in computer vision, spatial database, and related area due to their compactness and regularity. It has long been claimed that quadtree related algorithms are suitable for parallel and distributed implementation, but only little work has been done to justify this claim. The simple input partitioning method used in low level image processing could not be equally applied to distributed quadtree processing since it suffers the problem of load imbalance. Load balancing is one of the most crucial issues in distributed processing. In the context of distributed quadtree processing, it appears at various stages of processing in different forms; each requires its own solutions. The diversity in approaches to load balancing is further multiplied by the differences in the characteristics of types of data represented by,and spatial operations performed on quadtrees. In this paper, we propose a new approach to distributed quadtree processing using a task queue mechanism. We discuss dynamic load balancing and related issues in the context of distributed quadtree processing, and provide possible solutions. The proposed algorithms have been implemented on the Nectar system (currently being developed at Carnegie Mellon). Experimental results are also included in the paper.

A fast lightstripe rangefinding system with smart VLSI sensor

Abstract: The focus of the research is to build a compact, high performance lightstripe rangefinder using a Very Large Scale Integration (VLSI) smart photosensor array. Rangefinding, the measurement of the three-dimensional profile of an object or scene, is a critical component for many robotic applications, and therefore many techniques were developed. Of these, lightstripe rangefinding is one of the most widely used and reliable techniques available. Though practical, the speed of sampling range data by the conventional light stripe technique is severely limited. A conventional light stripe rangefinder operates in a step-and-repeat manner. A stripe source is projected on an object, a video image is acquired, range data is extracted from the image, the stripe is stepped, and the process repeats. Range acquisition is limited by the time needed to grab the video images, increasing linearly with the desired horizontal resolution. During the acquisition of a range image, the objects in the scene being scanned must be stationary. Thus, the long scene sampling time of step-and-repeat rangefinders limits their application. The fast range sensor proposed is based on the modification of this basic lightstripe ranging technique in a manner described by Sato and Kida. This technique does not require a sampling of images at various stripe positions to build a range map. Rather, an entire range image is acquired in parallel while the stripe source is swept continuously across the scene. Total time to acquire the range image data is independent of the range map resolution. The target rangefinding system will acquire 1,000 100 x 100 point range images per second with 0.5 percent range accuracy. It will be compact and rugged enough to be mounted on the end effector of a robot arm to aid in object manipulation and assembly tasks.

Methods for Identifying Footfall Positions Robot

Abstract: We are designing a complete autonomous legged robot to perfom planetary exploration without human supervision. This robot must traverse unknown and geographically diverse areas in order a collect samples of materials. This paper describes how a geometric terrain representation from range imagery can be used to identify footfall positions. First, we present previous research aimed to determine footfall positions. Second, we describe several methods for determining the positions for which the shape of the terrain is nearest to the shape of the foot. Third, we evaluate and compare the efficiency of these methods as functions of some parameters such as particularities of the shape of the terrain. Fourth, we introduce other methods that use thermal imaging in order to differentiate materials.

Development Of Autonomous Systems

Abstract: In the last several years at the Robotics Institute of Carnegie Mellon University, we have been working on two projects for developing autonomous systems: Nablab for Autonomous Land Vehicle and Ambler for Mars Rover. These two systems are for different purposes: the Navlab is a four-wheeled vehicle (van) for road and open terrain navigation, and the Ambler is a six-legged locomotor for Mars exploration. The two projects, however, share many common aspects. Both are large-scale integrated systems for navigation. In addition to the development of individual components (eg., construction and control of the vehicle, vision and perception, and planning), integration of those component technologies into a system by means of an appropriate architecture is a major issue.