Journal Article10.1109/TPAMI.1987.4767935
Localizing Overlapping Parts by Searching the Interpretation Tree
TL;DR: The approach operates by examining all hypotheses about pairings between sensed data and object surfaces and efficiently discarding inconsistent ones by using local constraints on distances between faces, angles between face normals, and angles of vectors between sensed points.
read more
Abstract: This paper discusses how local measurements of positions and surface normals may be used to identify and locate overlapping objects. The objects are modeled as polyhedra (or polygons) having up to six degrees of positional freedom relative to the sensors. The approach operates by examining all hypotheses about pairings between sensed data and object surfaces and efficiently discarding inconsistent ones by using local constraints on: distances between faces, angles between face normals, and angles (relative to the surface normals) of vectors between sensed points. The method described here is an extension of a method for recognition and localization of nonoverlapping parts previously described in [18] and [15].
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Planning in a the Motions of a Mobile Robot Sensorv Uncertaintv Field
Haruo Takeda,Jean-Claude Latombe +1 more
- 01 Jan 1994
TL;DR: In this paper, the authors proposed the notion of a Sensory Uncertainty Field (SUF) to estimate the distribution of possible errors in the robot configuration that would be computed by a localization function matching the data given by the sensors against an environment model, if the robot was at q. They also presented an implemented SUF-based motion planner for this robot and showed paths generated by this planner.
MIT Open Access Articles Exploiting feature dynamics for active object recognition
TL;DR: In this paper , a motion model is proposed to reveal structural information about the object that can be exploited for recognition, and a recognition system is presented that extends invariant local features (shape contexts) into the time domain by integration of the motion model.
Model-Based Pose Proposal for 2-D Object Recognition
Hemant D. Tagare,Drew McDermott +1 more
- 23 Oct 1996
TL;DR: This work considers the problem of finding a known two- dimensional object in an image, or verifying that it does not appear in the image, by adopting the strategy of doing a fast scan for potential places in theimage where the object could be, and proposes a scan pose proposal, which works by finding U- shaped segments of object boundaries.
Recognition of man-made objects from range data
Olgun Sadik
- 18 Nov 2022
TL;DR: In this article , an optimal representation and recognition of the objects from range data is developed for applications of machine vision in engineering tasks, the discussion of this subject is restricted to the class of man-made objects where object surfaces can be modeled with quadric primitives.
Evaluating the Trade-Offs in the Parallelization of Probabilistic Search Algorithms
R. L. Carceronif,Wagner Meira,Jr.t R. Stetst,S. Dwarkadast +3 more
- 01 Jan 2013
TL;DR: A parallel version of one such algorithm for a real-time computer vision problem with many practical applications is designed and a runtime system that is normally not the most efficient among these four (RSM) is found to be the best choice for the combination of alg~ rithm and architecture.
References
Theory of Edge Detection
David Marr,Ellen C. Hildreth +1 more
TL;DR: The theory of edge detection explains several basic psychophysical findings, and the operation of forming oriented zero-crossing segments from the output of centre-surround ∇2G filters acting on the image forms the basis for a physiological model of simple cells.
7.3K
•Journal Article
Computer vision
TL;DR: How the field of computer (and robot) vision has evolved, particularly over the past 20 years, is described, and its central methodological paradigms are introduced.
4K
Consistency in Networks of Relations
TL;DR: The primary aim is to provide an accessible, unified framework, within which to present the algorithms including a new path consistency algorithm, to discuss their relationships and the may applications, both realized and potential of network consistency algorithms.
2.8K
Understanding Line drawings of Scenes with Shadows
David L. Waltz
- 01 Jan 1975
TL;DR: A detailed discussion of the standard approach to computer interpretation of line drawings as three-dimensional scenes as well as some alternative approaches to this approach are discussed.
1.2K
Three-dimensional object recognition
Paul J. Besl,Ramesh Jain +1 more
TL;DR: In this paper, a precise definition of the 3D object recognition problem is proposed, and basic concepts associated with this problem are discussed, and a review of relevant literature is provided.
1.2K