Book Chapter10.1007/978-3-642-77785-1_12
Object Recognition with Deformable Models Using Constrained Elastic Nets
Michael Schwarzinger,Detlev Noll,Werner von Seelen +2 more
- 14 Sep 1992
- pp 96-104
8
TL;DR: A model-based method for object identification in images from natural scenes based on the elastic net technique has successfully been implemented for the classification of cars based on their rear view.
read more
Abstract: We present a model-based method for object identification in images from natural scenes. It has successfully been implemented for the classification of cars based on their rear view. In a first step characteristic features such as lines and corners are detected within the image. Generic models of object-classes, described by the same set of features, are stored in a database. Each model represents a whole class of objects (e.g. passenger cars, vans, big trucks). A pre-processing module suggests a region of interest. A method based on the elastic net technique [2] then is used to map the model on the image features. During this iterative process the model is allowed to undergo changes in scale, position and certain deformations. Deformations are kept within limits such that one model can fit to all objects belonging to the same class, but not to objects of other classes. In each iteration step a value to assess the matching process is obtained.
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
Scale-invariant image recognition based on higher-order autocorrelation features
TL;DR: A framework and a complete implementation of a translation and scale-invariant image recognition system for natural indoor scenes that employs higher-order autocorrelation features of scale space data which permit linear classification is proposed.
52
Adaptive computation methods in digital image sequence analysis
Włodzimierz Kasprzak
- 01 Jan 2000
TL;DR: This document is intended to be used for educational purposes only and should not be used as a guide for making decisions about copyrighted material.
14
Image processing methods for interactive robot control
C. Theis,Ioannis Iossifidis,Axel Steinhage +2 more
- 18 Sep 2001
TL;DR: A straight forward technique for tracking a human hand based on images acquired by an active stereo camera system is described and the implementation on an anthropomorphic assistance robot as part of a multi-modal man-machine interaction system is demonstrated.
14
•Dissertation
Modèles déformables et Multirésolution pour la détection de contours en traitement d'images
Youssef El Omary
- 24 Oct 1994
TL;DR: In this paper, the authors propose a multiresolution approach based on the notion of minimisation d'energies, which consists of a cooperer between contours actifs and the multireolution.
10
•Journal Article
Adaptive methods of moving car detection in monocular image sequences
TL;DR: This paper focuses on the moving object detection/tracking task on four different data abstraction levels: image segmentation, 2D object tracking, model-based 3D objecttracking and multi-object traffic scene description.
References
An analogue approach to the travelling salesman problem using an elastic net method
TL;DR: This work describes how a parallel analogue algorithm, derived from a formal model for the establishment of topographically ordered projections in the brain, can be applied to the travelling salesman problem, and produces shorter tour lengths than another recent parallel analogue algorithms.
869
•Proceedings Article
Linear feature extraction and description
Ramakant Nevatia,K. Ramesh Babu +1 more
- 20 Aug 1979
TL;DR: A technique of edge detection and linking for linear feature extraction and its applications to detection of roads and runway like structures is described.
738
Intensity and Edge-Based Symmetry Detection Applied to Car-Following
Thomas Zielke,Michael Brauckmann,Werner von Seelen +2 more
- 19 May 1992
TL;DR: Two methods for detecting symmetry in images are presented, one based directly on the intensity values and another one based on a discrete representation of local orientation, which is applied to the problem of visually guided car-following.
Aligning pictorial descriptions: an approach to object recognition
Shimon Ullman,Shimon Ullman +1 more
TL;DR: The proposed alignment method also uses abstract description, but unlike structural description methods it uses them pictorially, rather than in symbolic structural descriptions.
Linear feature extraction and description
Ramakant Nevatia,K. Ramesh Babu +1 more
TL;DR: In this paper, a technique of edge detection and line finding for linear feature extraction is described, where edge detection is by convolution with small edge-like masks, and the resulting output is thinned and linked by using edge positions and orientations and approximated by piecewise linear segments.