Function from motion
IEEE Transactions on Pattern Analysis and Machine IntelligencePublished 1 June 1996
Zoran Đurić, Jeffrey A. Fayman, Ehud Rivlin
Citations33
SJR quartileQ1
SJR score3.91
SNIP5.99
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 shown that the motion of an object, when combined with information about the object and its normal uses, provides us with strong constraints on possible functions that the object might be performing.
Abstract
In order for a robot to operate autonomously in its environment, it must be able to perceive its environment and take actions based on these perceptions. Recognizing the functionalities of objects is an important component of this ability. In this paper, we look into a new area of functionality recognition: determining the function of an object from its motion. Given a sequence of images of a known object performing some function, we attempt to determine what that function is. We show that the motion of an object, when combined with information about the object and its normal uses, provides us with strong constraints on possible functions that the object might be performing.
Keywords
Computer ScienceEngineering
Artificial IntelligenceDetermining optical flow
9,940 Citations1981Berthold K. P. Horn, Brian G. Schunck
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE<title>Determining Optical Flow</title>
7,496 Citations1981Berthold K. P. Horn, Brian G. Schunck
An iterative implementation is shown which successfully computes the optical flow for a number of synthetic image sequences and is robust in that it can handle image sequences that are quantized rather coarsely in space and time.
International Journal of Computer VisionModel-based object pose in 25 lines of code
996 Citations1995Daniel DeMenthon, Larry S. Davis
Compared to classic approaches making use of Newton's method, POSIT does not require starting from an initial guess, and computes the pose using an order of magnitude fewer floating point operations; it may therefore be a useful alternative for real-time operation.
IEEE Transactions on Pattern Analysis and Machine IntelligenceRecognition by linear combinations of models
817 Citations1991Shimon Ullman, Ronen Basri
An approach to visual object recognition in which a 3D object is represented by the linear combination of 2D images of the object is proposed and it is shown that for objects with sharp edges as well as with smooth bounding contours, the set of possible images of a given object is embedded in a linear space spanned by a small number of views.
Computer Vision Graphics and Image ProcessingHuman image understanding: Recent research and a theory
607 Citations1985Irving Biederman
Recognition-by-components (RBC) provides a principled account of the heretofore undecided relation between the classic principles of perceptual organization and pattern recognition.
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.
IEEE Transactions on Pattern Analysis and Machine IntelligenceAchieving generalized object recognition through reasoning about association of function to structure
153 Citations1991Louise Stark, Kevin W. Bowyer
Computer Vision and Image UnderstandingRecognition by Functional Parts
137 Citations1995Ehud Rivlin, Sven Dickinson +1 more
It is shown how these shape primitives and relations can be easily recovered from superquadric ellipsoids which, in turn, can be recovered from either range or intensity images of occluded scenes.
FigshareA model for functional reasoning in design
121 Citations2018Peter Freeman, Allen Newell
A model of the design process is developed in two stages corresponding to the task environment of design and the activity of posing and solving design problems, and issues raised by the model's qualitative aspects, its suitability to automated design, and lines for further development are discussed.
Journal of Visual Communication and Image RepresentationDetecting Activities
116 Citations1994Ramprasad Polana, Randal C. Nelson
It is shown that the technique robustly detects complex periodic activities, while excluding nonperiodic motion, and the authors believe that the phase information is valuable for activity recognition.
International Journal of Intelligent SystemsObject structure and action requirements: A compatibility model for functional recognition
48 Citations1991Lucia M. Vaina, Marie‐Christine Jaulent
This study describes an approach to the recognition of functions that combines ideas about representations of shapes, concepts, and object categories, with goal requirements of actions, in the framework of fuzzy sets and possibility theory.
The trajectory primal sketch: a multi-scale scheme for representing motion characteristics
46 Citations2003Kristy L. Gould, Mubarak Shah
A different approach is proposed for the use of motion in a computer vision system which uses the motion characteristics of moving objects without actually recovering the structure, and the extended trajectories followed by the objects are considered.
National Conference on Artificial IntelligenceLearning object models from appearance
38 Citations1993Hiroshi Murase, Shree K. Nayar
This work presents a new compact representation of object appearance that is parametrized by pose and illumination and suggests the proposed appearance representation to be a valuable tool for a variety of machine vision applications.
IEEE ExpertNaive mechanics: a computational model of device use and function in design improvisation
35 Citations1992Jack Hodges
The EDISON project, which is developing computational models that can solve problems and reason creatively about mechanical devices, is discussed, and this approach supports mechanical improvisation by applying the concept of device functional equivalence in different situations.
Function-based recognition from incomplete knowledge of shape
31 Citations1993Louise Stark, Adam Hoover +2 more
The work represents the first function-based recognition system to reason from incomplete knowledge of 3D object shape and also the first to analyze 3D shape descriptions acquired from real image data.
International Joint Conference on Artificial IntelligenceWhat is a degenerate view
30 Citations1987John R. Kender, D. Freudenstein
It is shown that given the finite viewing resolution of a two-dimensional retina, in practice the concept of a characteristic view is often not characteristic of real imagery, and an aspect graph is less a discrete graph, and more properly a partitioning of the surface of the viewing sphere into "fuzzy" regions of non-zero area: an aspect map.
Generic recognition through qualitative reasoning about 3-D shape and object function
26 Citations2002Louise Stark, Kevin W. Bowyer
The authors construct a definition of a generic object category in terms of the function required of the object, based on qualitative reasoning about 3-D shape, which has the potential to lead to recognition systems of much greater generality than current CAD-based or model-based approaches.
Indexing function-based categories for generic recognition
12 Citations2003Louise Stark, Kevin W. Bowyer
The authors report the implementation and evaluation of a function-based recognition system that takes an uninterrupted 3-D object shape as its input and reasons to determine if the object belongs to the superordinate category furniture, and if so, into which (sub)category it falls.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIEShape and Function
10 Citations1987Franc Solina, Ruzena Bajcsy
A modeling system for generic objects in order to recognize different objects from the same category with only one generic model is proposed, based upon the current psychological theories of categorization and of human visual perception.
Generic recognition of articulated objects by reasoning about functionality
6 Citations2002K. Green, Daniel Eggert +2 more
This paper introduces a scenario in which object recognition is accomplished by first deriving an articulated shape model from an observed sequence of 3-D shapes and by then reasoning about the possible functionality of the articulatedshape model.
ASME/JSME 2011 8th Thermal Engineering Joint ConferenceFunctional Materials for Energy Storage: Fabrication of Shape Stabilized Polymeric Phase Change Composites and the Determination of Their Thermophysical Properties for Use in Energy Conservation Applications
1 Citations2011Anjum Saleem, Lars Frormann