Open AccessJournal Article
View-based recognition
TL;DR: An upper bound on the number of views needed to be stored by a view-based recognition system in order to achieve zero probability of false negative matches is derived.
read more
Abstract: In this paper, we propose view-based recognition, a method for 3D object recognition based on multi-view representations. We analyze view-based recognition and compare its performance theoretically and empirically with one of the most commonly used method for 3D object recognition, 3D bounded error recognition. In particular, we show that the probability of false positive or false negative matches in a view-based recognition system is not substantially different from the probability of similar errors in other commonly used recognition systems. Furthermore, we derive an upper bound on the number of views needed to be stored by a view-based recognition system in order to achieve zero probability of false negative matches. Simulations and experiments on real images suggest that these estimates are conservative and that view-based recognition is a robust and simple alternative to the more traditional 3D shape based recognition methods.
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
Task-specific gesture analysis in real-time using interpolated views
TL;DR: This work applies an appearance-based approach to the problem of context-specific gesture interpolation and recognition, and demonstrates real-time systems which perform these tasks.
139
Implementation techniques for geometric branch-and-bound matching methods
TL;DR: A method for globally optimal partial line segment matching under bounded or Gaussian error, point matching under aGaussian error model with subpixel accuracy and precise orientation models, and a simple and robust technique for finding multiple distinct objcct instances are presented.
131
A Practical, Globally Optimal Algorithm for Geometric Matching under Uncertainty
TL;DR: A simple and efficient branch-and-bound algorithm for finding globally optimal solutions to geometric matching problems under a wide variety of allowable transformations and a wide range of allowable feature types is presented.
41
•Proceedings Article
Classifying Hand Gestures with a View-Based Distributed Representation
Trevor Darrell,Alex Pentland +1 more
- 29 Nov 1993
TL;DR: A view-based representation is used to model aspects of the hand relevant to the trained gestures, and is found using an unsupervised clustering technique, which uses normalized correlation networks, with dynamic time warping in the temporal domain, as a distance function for unsuper supervised clustering.
Object recognition by fast hypothesis generation and reasoning about object interactions
M. Westling,Larry S. Davis +1 more
- 25 Aug 1996
TL;DR: This work presents a two-step approach for recognizing multiple 3-D objects in single 2-D images, which relies on an array that associates a large number of object poses with corresponding image features and calculates the configuration of hypotheses that best interprets the image using a Bayesian network.
14
References
•Book
Geometric Aspects of Visual Object Recognition
Thomas M. Breuel
- 28 Aug 2011
TL;DR: A recognition algorithm (RAST) that works efficiently even when no correspondence or grouping information is given; that is, it works in the presence of large amounts of clutter and with very primitive features form the basis for a simple, efficient, and robust approach to the geometric aspects of 3D object recognition from 2D image.
Applying Sensor Models To Automatic Generation Of Object Recognition Programs
Katsushi Ikeuchi,Takeo Kanade +1 more
- 05 Dec 1988
TL;DR: This paper concentrates on sensor modeling and its relationship with strategy generation, because it is regarded as the bottle neck to automatic generation of object recognition programs.
35
Model-based recognition in robot vision
Roland T. Chin,Charles R. Dyer +1 more
TL;DR: This paper presents a comparative study and survey of model-based object-recognition algorithms for robot vision, and an evaluation and comparison of existing industrial part- recognition systems and algorithms is given, providing insights for progress toward future robot vision systems.
Fast recognition using adaptive subdivisions of transformation space
Thomas M. Breuel
- 15 Jun 1992
TL;DR: Its performance is better than that of alignment and Hough transform methods, and, as opposed to these methods; RAST finds solutions satisfying simple, well-defined bounded error criteria.