From image sequences towards conceptual descriptions
Image and Vision ComputingPublished 1 May 1988
Hans-Hellmut Nagel
Citations172
SJR quartileQ1
SJR score0.79
SNIP1.33
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
It is suggested to introduce a ‘generically describable situation’ as a new conceptual unit for the computer-internal representation of more complex discourse worlds.
Abstract
Four approaches towards the extraction of conceptual descriptions from image sequences which all evolved from the same 1977 proposal are surveyed. After a critical evaluation of the insights gained from these experimental approaches, the necessity to strive for a complete conceptual model of a (necessarily limited) discourse world is emphasized. It is suggested to introduce a 'generically describable situation' as a new conceptual unit for the computer-internal representation of more complex discourse worlds. References to other approaches for the extraction of descriptions from images and image sequences are pointed out for comparison.
Keywords
Computer Science
International Journal of Computer VisionSnakes: Active contour models
16,951 Citations1988Michael Kass, Andrew Witkin +1 more
This work uses snakes for interactive interpretation, in which user-imposed constraint forces guide the snake near features of interest, and uses scale-space continuation to enlarge the capture region surrounding a feature.
Artificial IntelligenceTowards a general theory of action and time
2,562 Citations1984James F. Allen
A formalism for reasoning about actions that is based on a temporal logic allows a much wider range of actions to be described than with previous approaches such as the situation calculus and a framework for planning in a dynamic world with external events and multiple agents is suggested.
Cognitive ScienceAn overview of the KL-ONE Knowledge Representation System
1,620 Citations1985R. J. Brachman, James G. Schmolze
The kernel ideas of KL-ONE are presented, emphasizing its ability to form complex structured descriptions, and notions of taxonomy and classification that are central to it are highlighted.
Cognitive ScienceAn Overview of the KL‐ONE Knowledge Representation System*
977 Citations1985Ronald J. Brachman, James G. Schmolze
IEEE Transactions on Pattern Analysis and Machine IntelligenceAn Investigation of Smoothness Constraints for the Estimation of Displacement Vector Fields from Image Sequences
766 Citations1986Hans-Hellmut Nagel, W. Enkelmann
Results are reported of an investigation about how an ``oriented smoothness'' constraint may be formulated and evaluated about how variations of the displacement vector field only in directions with small or no variation of gray values are restricted.
Cognitive ScienceA temporal logic for reasoning about processes and plans
760 Citations1982Drew McDermott
Artificial IntelligencePerceptual organization and the representation of natural form
561 Citations1986Alex Pentland
This work presents a representation that has proved competent to accurately describe natural and man-made forms in a succinct and psychologically natural manner and Superquadrics, a superset of traditional modeling primitives are the basic element in this representation.
Cognitive ScienceA Temporal Logic for Reasoning about Processes and Plans*
493 Citations1982Drew McDermott
A first-order temporal logic, in which it is possible to name and prove things about facts, events, plans, and world histories, and provides analyses of causality, continuous change in quantities, the persistence of facts, and the relationship between tasks and actions.
Image and Vision ComputingModel-based vision: a program to see a walking person
458 Citations1983David Hogg
The computer program described here, the WALKER model, maps images into a description in which a person is represented by the series of hierarchical levels, i.e. a person has an arm which has a lower-armWhich has a hand.
IEEE Transactions on Pattern Analysis and Machine IntelligenceModel-based image analysis of human motion using constraint propagation
426 Citations1980Joseph O’Rourke, Norman I. Badler
A system capable of analyzing image sequences of human motion is described, structured as a feedback loop between high and low levels: predictions are made at the semantic level and verifications are sought at the image level.
Artificial IntelligenceOn the estimation of optical flow: Relations between different approaches and some new results
425 Citations1987Hans-Hellmut Nagel
An exact solution for the system of partial differential equations proposed by Horn and Schunck (1981) is given at gray value corners and extrema and results in a modification of the “oriented smoothness” approach of Nagel (1983) which thereby becomes considerably simpler.
Computer Vision Graphics and Image ProcessingDisplacement vectors derived from second-order intensity variations in image sequences
424 Citations1983Hans-Hellmut Nagel
A local approach by minimization of the squared differences between a second-order Taylor expansion of gray values from one frame and the observed gray values within the same window from the next frame appears to be an interesting model for the local computation of optical flow.
PerceptionMaximizing Rigidity: The Incremental Recovery of 3-D Structure from Rigid and Nonrigid Motion
295 Citations1984Shimon Ullman
It is shown how the 3-D structure of rigid as well as nonrigid objects can be recovered by maintaining an internal model of the viewed object and modifying it at each instant by the minimal nonrigidity change that is sufficient to account for the observed transformation.
Artificial IntelligenceTemporal logics in AI: Semantical and ontological considerations
267 Citations1987Yoav Shoham
This paper examines this method by looking closely at two of the more influential formalisms featuring reified propositions, those of Allen and McDermott, and presents a new formalism that does not suffer from these disadvantages.
Recognition by Parts
243 Citations1987Alex Pentland
It is argued that most natural objects have a part structure that the authors can recover from image data and thus use as the basis for "general-purpose" recognition and a "parts" representation is described that is fairly general purpose, despite having only a small number of parameters.
Computer Vision Graphics and Image ProcessingDetermination of 3D human body postures from a single view
202 Citations1985Hsi-Jian Lee, Zen Chen
A method is proposed to recover and interpret the 3D body structures of a person from a single view, provided that at least six feature points on the head and a set of body joints are available on the image plane, and the geometry of head and lengths of body segments formed by joints are known.
DSpace@MIT (Massachusetts Institute of Technology)Learning physical descriptions from functional definitions, examples, and precedents
198 Citations1983Patrick Henry Winston, Thomas O. Binford +2 more
The theory is a synthesis of two sets of ideas: ideas about learning from precedents and exercises developed at MIT and ideas about physical description developed at Stanford, and is illustrated by way of representative experiments.
International Journal of Computer VisionGenerating an interpretation tree from a CAD model for 3D-object recognition in bin-picking tasks
189 Citations1987Katsushi Ikeuchi
A set of rules to find out what appropriate features are to be used in what order to generate an efficient and reliable interpretation tree are developed and applied in a task for bin-picking objects that include both planar and cylindrical surfaces.
The Journal of the Acoustical Society of AmericaReview of the ARPA speech understanding project
188 Citations1976Dennis H. Klatt
Proceedings of the Royal Society of London. Series B, Biological sciencesRepresentation and recognition of the movements of shapes
183 Citations1982David Marr, Lucia M. Vaina
A representation is proposed for the movements of shapes that lie within the scope of the Marr & Nishihara (1978) 3-D model representation of static shapes, called the state─motion─state (SMS) moving shape representation, and several examples of its application are given.
ACM Computing SurveysDigital Representations of Human Movement
181 Citations1979Norman I. Badler, Stephen W. Smoliar
The interpretation of one partmular notation system, Labanotatlon, is examined to extract a set of "primitive movement concepts" which can be used to animate a realistic human body on a graphics display.
IEEE Computer Graphics and ApplicationsMotor Control Techniques for Figure Animation
178 Citations1982Zeltzer
Computer models of skeletons may not show muscle tissue or clothing, but they are an excellent means of displaying the fundamental properties of human motion.
Pattern RecognitionImage sequence analysis of real world human motion
178 Citations1984Koichiro Akita
Three fundamental problems of image sequence analysis are investigated for real world human motions, including the modelling of body motion, the analysis of occluding regions, and the correspondence of feature points in the consecutive frames.
The Journal of the Acoustical Society of AmericaReview of the ARPA Speech Understanding Project
176 Citations1977Dennis H. Klatt
Computer Vision Graphics and Image ProcessingNew likelihood test methods for change detection in image sequences
173 Citations1984Yun-Hsiang Hsu, Hans-Hellmut Nagel +1 more
Results encouraged investigations into modeling the picture as a mosaic of patches where the gray-value function within each patch is described as a second-order bivariate polynomial of the pixel coordinates, facilitating the determination of threshold values related to a priori confidence limits.
IEEE Transactions on Pattern Analysis and Machine IntelligenceA framework for visual motion understanding
173 Citations1980John K. Tsotsos, John Mylopoulos +2 more
The purpose behind this system is to provide an evolving research prototype for experimenting with the analysis of certain classes of biomedical imagery, and for refining and quantifying the body of relevant medical knowledge.
IEEE Computer Graphics and ApplicationsArticulated Figure Positioning by Multiple Constraints
161 Citations1987Norman I. Badler, Kamran H. Manoochehri +1 more
This work presents a method that automatically solves multiple simultaneous joint position goals using a six-degree-of-freedom input device to specify joint angles and goal positions interactively.
IEEE Transactions on Pattern Analysis and Machine Intelligence3-D Motion Estimation, Understanding, and Prediction from Noisy Image Sequences
148 Citations1987Juyang Weng, Thomas S. Huang +1 more
An approach to understanding general 3-D motion of a rigid body from image sequences using a locally constant angular momentum (LCAM) model, which constrains the motion to be a superposition of precession and translation over a local frame subsequence.
Repository of the University of Ljubljana (University of Ljubljana)Three dimensional object representation revisited
147 Citations1987Ruzena Bajcsy, Franc Solina
A modeling system for generic objects to recognize different objects from the same category with only one generic model is proposed, based upon the current psychological theories of categorization and human visual perception.
IEEE Computer Graphics and ApplicationsTechniques for Generating the Goal-Directed Motion of Articulated Structures
145 Citations1982Korein, Badler
Analytic and numerical computations used in robotics research provide tools for automated computer animation of the human figure.
IEEE Computer Graphics and ApplicationsUsing Dynamic Analysis for Realistic Animation of Articulated Bodies
127 Citations1987Jane Wilhelms
There is evidence that dynamics offers hope for more realistic, natural, and automatic motion control, particularly in such complex articulated bodies as humans and other animals.
IEEE Computer Graphics and ApplicationsAspects of the Kinematic Simulation of Human Movement
109 Citations1982Calvert, Chapman +1 more
A kinematic simulation model allows realistic animation of the human body-provided the body is in contact with the ground and input data is accurate.
Proceedings of the IEEEA spherical representation of a human body for visualizing movement
86 Citations1979Norman I. Badler, Joseph O’Rourke +1 more
A three-dimensional human body model for displaying body movements on a computer graphics display that includes joints which do not deform during movement, simple hidden surface removal, and efficient collision and contact detection is described.
IEEE Computer Graphics and ApplicationsNear-Real-Time Control of Human Figure Models
82 Citations1987William W. Armstrong, Mark F. Green +1 more
An interactive interface to a dynamics package, along with a collection of low-level motion processes, can be used to control the motion of a human figure model.
Journal of BiomechanicsPlanar control in multi-camera calibration for 3-D gait studies
75 Citations1980Herman J. Woltring
This paper focuses on photogrammetric calibration of a given camera configuration in which the usual requirement of a 3-D calibration object with known control point coordinates (“absolute control”) is circumvented.
Proceedings of the IEEEImportant issues in knowledge representation
73 Citations1986William A. Woods
The relationship between knowledge and the world and the use of knowledge by reasoning agents and the structure of conceptual representations are considered and it is argued that taxonomic classification structures can advance both expressive adequacy and notational efficacy.
Computer Graphics and Image ProcessingFormation of an object concept by analysis of systematic time variations in the optically perceptible environment
69 Citations1978Hans-Hellmut Nagel
An algorithm to isolate a representation for a moving object of unknown form and size from a sequence of TV frames based on the assumption that a group of connected regions being jointly displaced in a systematic way from frame to frame without changing their relative positions is described.
IEEE Transactions on Pattern Analysis and Machine IntelligenceA Knowledge Based System for Analysis of Gated Blood Pool Studies
64 Citations1985Heinrich Niemann, Horst Bunke +4 more
A system for obtaining a complete diagnostic description of an image sequence taken in nuclear medicine from the human heart has been developed, implemented, and tested.
Pattern RecognitionHuman body motion segmentation in a complex scene
64 Citations1987M.K.H. Leung, Yee‐Hong Yang
Experimental results show that the technique can eliminate a lot of stationary regions and thus can reduce the amount of processing required in the interpretation process.
IEEE Computer Graphics and ApplicationsToward Automatic Motion Control
64 Citations1987Jane Wilhelms
More automic methods will allow the production of sophisticated animation with less user effort, including dynamic analysis, path planning and collision avoidance, stimulus-response control, and learning algorithms.
On the Selection of Critical Points and Local Curvature Extrema of Region Boundaries for Interframe Matching
55 Citations1983L. Dreschler, Hans-Hellmut Nagel
The mathematical relations between the two-stage interest operator of DRESCHLER+NAGEL 81, the zero-crossing contours of the “Mexican Hat”-operator of MARR+HILDRETH 80, and thezero-lines of the gaussian curvature are discussed.
Pattern RecognitionA region based approach for human body motion analysis
52 Citations1987M.K.H. Leung, Yee‐Hong Yang
Techniques developed for the second phase of the analysis of human body motion analysis are discussed, using the notion of antiparallel lines to abstract the regions into a higher level primitive which enables one to define and develop operations such as concatenation and deletion.
Proceedings of the IEEEA formal logic of plans in temporally rich domains
43 Citations1986Richard N. Pelavin, James F. Allen
A temporal logic extended with two modalities that can be used to support planning in temporally rich domains that can represent planning environments that have assertions about future possibilities in addition to the present state, and plans that contain concurrent actions.
Pattern RecognitionDetection of the movements of persons from a sparse sequence of TV images
37 Citations1985Toshifumi Tsukiyama, Yoshiaki Shirai
This paper describes a method for detecting persons walking in a passageway from two consecutive TV images at long intervals by extracting candidate areas for persons from TV images by image processing.
Overview on Image Sequence Analysis
34 Citations1983Hans-Hellmut Nagel
Current research in image sequence analysis is concerned with the design of computer-internal representations for objects and associated dynamic phenomena.
Proceedings of the IEEEReasoning about scene descriptions
27 Citations1986M. DiManzo, Giovanni Adorni +1 more
The specific topics covered by this work are the analysis of the meaning of spatial prepositions, the problem of the reference system and dimensionality, the activation of expectations about unmentioned objects, the role of default knowledge about object positions and its integration with contextual information sources, and the issue of space representation.
International Joint Conference on Artificial IntelligenceNatural language dialogue about moving objects in an automatically analyzed traffic scene
26 Citations1981Heinz Marburger, Bernd Neumann +1 more
Two systems are connected, a natural language dialogue system originally conceived for static scenes and an emerging scene analysis system for real-world TV-frame sequences which produces time dependent object descriptions which serve as a referential database for inquiries.
Fraunhofer-Publica (Fraunhofer-Gesellschaft)A versatile method for the estimation of displacement vector fields in image sequences
25 Citations1985Kories, R., Zimmermann, G.
Characterizing Trajectories of Moving Objects Using Natural Language Path Descriptions
23 Citations2003Elisabeth André, Guido Bosch +2 more
The German dialogue system CITYTOUR, which answers questions about the spatial relations of objects in a scene, is presented by means of a simple dialogue example, and the representational prerequisites of the static and the dynamic objects, required for computational analysis are presented.
International Joint Conference on Artificial IntelligenceLandScan: a natural language and computer vision system for analyzing aerial images
23 Citations1985Růžena Bajcsy, Aravind K. Joshi +2 more
LandScan (LANguage Driven SCene ANalysis) is presented as an integrated vision system which covers most levels of both vision and natural language processing and the design of the vision and control modules is focused on.
Computer Vision Graphics and Image ProcessingRepresentation of three-dimensional motion in dynamic scenes
22 Citations1983Minoru Asada, Saburo Tsuji
A framework that finds a meaningful representation of rigid and joint motion, given correspondences of points on each object in an image sequence is described, and a geometrical model of rotation is introduced to explore relationships between an apparent rotation vector and actual rotations around multiple physical axes.
Proceedings of the IEEEPlans, goals, and language
21 Citations1986James F. Allen, Diane Litman
This work describes techniques that allow systems to handle many dialogues that are problematic for other systems, including the use of sentence fragments, indirect speech, helpful responses, the tracking of the topic of conversations both with and without interrupting subdialogues, and topic change.
Very Large Data BasesDatabase Support for Knowledge-Based Image Evaluation
19 Citations1987Ingrid Walter, Peter C. Lockemann +1 more
This contribution introduces a subproblem of image sequence evaluation, the extraction of so-called episodes, and describes the abstraction level of episodes, the system architecture of an episode extraction system EPEK, and discusses the novel requirements that database systems must observe for image evaluation applications.
IEEE Computer Graphics and ApplicationsScreen-Area Coherence for Interactive Scanline Display Algorithms
16 Citations1987Gary A. Crocker
A scanline hidden-surface removal procedure that uses screen-area coherence to achieve interactive speeds is described that reduced the average frame update time to about one quarter of the original time for three test sequences of CSG modeling operations.
Computer Vision Graphics and Image ProcessingToward the derivation of three-dimensional descriptions from image sequences for nonconvex moving objects
16 Citations1986H. Westphal, Hans-Hellmut Nagel
Techniques to improve the object description by incorporation of surface concavities and surface markings are described.
Pattern RecognitionAnalysis of three-dimensional motions in blocks world
16 Citations1984Minoru Asada, Masahiko Yachida +1 more
A computational analysis of three-dimensional motion in the blocks world using a sequence of line drawings of rigid trihedral blocks projected orthogonally on an image plane to evaluate geometrical parameters, such as orientations and edge lengths.
Informatik-FachberichteDetektion und Verfolgung Mehrerer Objekte in Bilfolgen
13 Citations1986Chang Kyung Sung, G. Zimmerman
Eine Methode zur Auswertung of TV-Bildfolgen des Verkehrsgeschehens vorgeschlagen, with der diese Informationen zu einem grosen Teil gewonnen werden konnen, ist eine Ubersicht uber Methoden der Bildfolgenverarbeitung siehe.
Generating a coherent text describing a traffic scene
12 Citations1986Hans-Joachim Novak
If a system that embodies a reference semantic for motion verbs and prepositions is to generate a coherent text describing the recognized motions it needs a decision procedure to select the events.
Medical & Biological Engineering & ComputingAnalysis of human movements: spatial localisation with multiple perspective views
12 Citations1983Pietro Morasso, V. Tagliasco
A system is presented which tracks the three-dimensional trajectory of points of the human body by means of the digitised co-ordinates of corresponding points which result from multiple perspective views.
Fundamentals in computer understanding: speech and vision
12 Citations1987Jean‐Paul Haton
This book emphasizes relevant aspects of man-machine dialogue by voice (acoustic-phonetic decoding, multi-speaker aspects, dialogue architectures, etc.) and presents analogies with the related fields of computer vision and natural language processing.
Informatik-FachberichteTextgenerierung aus visuellen Daten: Beschreibungen von Straßenszenen
11 Citations1987Hans-Joachim Novak
Computer Vision Graphics and Image ProcessingTask frames: Primitives for sensory-motor coordination
10 Citations1986Dana H. Ballard, Leo Hartman
It is argued that an extension of object-centered coordinate frames, termed task frames, is an essential ingredient in such models as well as how these models are constructed from sensory input.
Lernen durch Beobachtung von Szenen mit bewegten Objekten: Phasen einer Systementwicklung
9 Citations1983Leonie Dreschler-Fischer, W. Enkelmann +1 more
National Conference on Artificial IntelligenceToward a learning of object models using analogical objects and verbal instruction
5 Citations1982Norihiro Abe, Fumihide Itoh +1 more
An attempt of analogical learning method by verbalism is shown in order to create a model for an identification of unknown objects that can augment or create new descriptions by making use of explicit verbal instructions.
Informatik-FachberichteEin Datenmodell für die Extraktion von Episoden aus Bildfolgen
4 Citations1986Ingrid Walter
Bei der Analyse von Bildfolgen auf der Abstraktionsebene von Episoden benotigt man Reprasentationen der physikalischen Objekte, der einfachen und komplexen Ablaufe, sowie des Ableitungs- and Kontrollwissens.