Results 1  10
of
11
Active perception
 Proc IEEE, 76:9961005
, 1988
"... Most past and present work in machine perception has involved extensive static analysis of passively sampled data. However, it should be axiomatic that perception is not passive, but active. Perceptual activity is exploratory, probing, searching; percepts do not simply fall onto sensors as rain fall ..."
Abstract

Cited by 340 (6 self)
 Add to MetaCart
Most past and present work in machine perception has involved extensive static analysis of passively sampled data. However, it should be axiomatic that perception is not passive, but active. Perceptual activity is exploratory, probing, searching; percepts do not simply fall onto sensors as rain falls onto ground. We do not just see, we look. And in the course,
Multiple Resolution Segmentation of Textured Images
 IEEE Transactions on Pattern Analysis and Machine Intelligence
, 1991
"... This paper presents a multiple resolution algorithm for segmenting images into regions with differing statistical behavior. In addition, an algorithm is developed for determining the number of statistically distinct regions in an image and estimating the parameters of those regions. Both algorithms ..."
Abstract

Cited by 123 (7 self)
 Add to MetaCart
This paper presents a multiple resolution algorithm for segmenting images into regions with differing statistical behavior. In addition, an algorithm is developed for determining the number of statistically distinct regions in an image and estimating the parameters of those regions. Both algorithms use a causal Gaussian autoregressive (AR) model to describe the mean, variance and spatial correlation of the image textures. Together the algorithms may be used to perform unsupervised texture segmentation. The multiple resolution segmentation algorithm first segments images at coarse resolution and then progresses to finer resolutions until individual pixels are classified. This method results in accurate segmentations and requires significantly less computation than some previously known methods. The field containing the classification of each pixel in the image is modeled as a Markov random field (MRF). Segmentation at each resolution is then performed by maximizing the a posteriori prob...
Texture Synthesis via a Noncausal Nonparametric Multiscale Markov Random Field
, 1998
"... Our noncausal, nonparametric, multiscale, Markov random field (MRF) model is capable of synthesising and capturing the characteristics of a wide variety of textures, from the highly structured to the stochastic. We use a multiscale synthesis algorithm incorporating local annealing to obtain larger r ..."
Abstract

Cited by 48 (7 self)
 Add to MetaCart
Our noncausal, nonparametric, multiscale, Markov random field (MRF) model is capable of synthesising and capturing the characteristics of a wide variety of textures, from the highly structured to the stochastic. We use a multiscale synthesis algorithm incorporating local annealing to obtain larger realisations of texture visually indistinguishable from the training texture.
Compound GaussMarkov random fields for image estimation and restoration
 Rensselaer Polytechnic Institute
, 1988
"... AbstmctThis paper is concerned with algorithms for obtaining approximations to statistically optimal estimates for images modeled as compound GaussMarkov random fields. We consider both the maximum aposteriori probability (MAP) estimate and the minimum meansquared error (MMSE) estimate for both ..."
Abstract

Cited by 42 (0 self)
 Add to MetaCart
AbstmctThis paper is concerned with algorithms for obtaining approximations to statistically optimal estimates for images modeled as compound GaussMarkov random fields. We consider both the maximum aposteriori probability (MAP) estimate and the minimum meansquared error (MMSE) estimate for both image estimation and image restoration. Compound image models consist of several submodels having different characteristics along with an underlying structure model which governs transitions between these image submodels. Compound GaussMarkov field models can be attractive for image estimation because the resulting estimates do not suffer the oversmoothing of edges that usually occurs with Gaussian image models. Two different compound random field models are employed in this paper, the doubly stochastic Gaussian (DSG) random field and a newly defined compound GaussMarkov (CGM) random field. We present MAP estimators for DSG and CGM random fields using simulated annealing, a powerful optimization method best suited to massively parallel processors. A fast converging algorithm called deterministic relaxation, which however converges to only a locally optimal MAP estimate, is also presented as an alternative for reducing computational loading on sequential machines. For comparison purposes, we also include results on the fixedlag smoothing MMSE estimator for the DSG field and its suboptimal Malgorithm approximation. The incorporation of causal and nodcausal modeling together with causal and noncausal estimates on the same data sets allows meaningful visual comparisons to be made. We also include Wiener and reduced update Kalman filter (RUKF) estimates to allow visual comparison of the near optimal estimates based on c6mpound GaussMarkov models to those based on simple Gaussian image models. I.
Computer Vision Algorithms on Reconfigurable Logic Arrays
 IEEE TRANS. ON PARALLEL AND DISTRIBUTED SYSTEMS
, 1999
"... Computer vision algorithms are natural candidates for high performance computing due to their inherent parallelism and intense computational demands. For example, a simple 3 x 3 convolution on a 512 x 512 gray scale image at 30 frames per second requires 67.5 million multiplications and 60 million a ..."
Abstract

Cited by 15 (1 self)
 Add to MetaCart
Computer vision algorithms are natural candidates for high performance computing due to their inherent parallelism and intense computational demands. For example, a simple 3 x 3 convolution on a 512 x 512 gray scale image at 30 frames per second requires 67.5 million multiplications and 60 million additions to be performed in one second. Computer vision tasks can be classified into three categories based on their computational complexity andcommunication complexity: lowlevel, intermediatelevel and highlevel. Specialpurpose hardware provides better performance compared to a generalpurpose hardware for all the three levels of vision tasks. With recent advances in very large scale integration (VLSI) technology, an application specific integrated circuit (ASIC) can provide the best performance in terms of total execution time. However, long design cycle time, high development cost and inflexibility of a dedicated hardware deter design of ASICs. In contrast, field programmable gate arrays (FPGAs) support lower design verification time and easier design adaptability atalower cost. Hence, FPGAs with an array of reconfigurable logic blocks canbevery useful compute elements. FPGAbased custom computing machines are
Parallel algorithms for image enhancement and segmentation by region growing with an experimental study
 THE JOURNAL OF SUPERCOMPUTING
, 1996
"... This paper presents efficient and portable implementations of a useful image enhancement process, the Symmetric Neighborhood Filter (SNF), and an image segmentation technique which makes use of the SNF and a variant of the conventional connected components algorithm which we call deltaConnected Com ..."
Abstract

Cited by 14 (4 self)
 Add to MetaCart
This paper presents efficient and portable implementations of a useful image enhancement process, the Symmetric Neighborhood Filter (SNF), and an image segmentation technique which makes use of the SNF and a variant of the conventional connected components algorithm which we call deltaConnected Components. Our general framework is a singleaddress space, distributed memory programming model. We use efficient techniques for distributing and coalescing data as well as efficient combinations of task and data parallelism. The image segmentation algorithm makes use of an efficient connected components algorithm which uses a novel approach for parallel merging. The algorithms have been coded in SplitC and run on a variety of platforms, including the Thinking Machines CM5, IBM SP1 and SP2, Cray Research T3D, Meiko Scientific CS2, Intel Paragon, and workstation clusters. Our experimental results are consistent with the theoretical analysis (and provide the best known execution times for segmentation, even when compared with machinespecific implementations.) Our test data include difficult images from the Landsat Thematic Mapper (TM) satellite data. More efficient implementations of SplitC will likely result in even faster execution times.
An Adaptive Approach for Texture Segmentation by Multichannel Wavelet Frames
 in SPIE Proceedings on Mathematical Imaging: Wavelet Applications in Signal and Image Processing
, 1993
"... We introduce an adaptive approach for texture feature extraction based on multichannel wavelet frames and twodimensional envelope detection. Representations obtained from both standard wavelets and wavelet packets are evaluated for reliable texture segmentation. Algorithms for envelope detection b ..."
Abstract

Cited by 8 (1 self)
 Add to MetaCart
We introduce an adaptive approach for texture feature extraction based on multichannel wavelet frames and twodimensional envelope detection. Representations obtained from both standard wavelets and wavelet packets are evaluated for reliable texture segmentation. Algorithms for envelope detection based on edge detection and the Hilbert transform are presented. Analytic filters are selected for each technique based on performance evaluation. A Kmeans clustering algorithm was used to test the performance of each representation feature set. Experimental results for both natural textures and synthetic textures are shown. 1 Introduction In the field of computer vision, texture segmentation has been investigated by many researchers using a diversity of approaches. In general, each method consists of two phases: feature extraction and segmentation. Features for texture representation are of crucial importance for accomplishing segmentation[1]. Previous approaches for representing texture...
Parallel image processing system on a cluster of personal computers
 in VECPAR 2000, 4th Int. Conf
, 2001
"... Abstract. The most demanding image processing applications require real time processing, often using special purpose hardware. The work herein presented refers to the application of cluster computing for o line image processing, where the end user bene ts from the operation of otherwise idle process ..."
Abstract

Cited by 3 (0 self)
 Add to MetaCart
Abstract. The most demanding image processing applications require real time processing, often using special purpose hardware. The work herein presented refers to the application of cluster computing for o line image processing, where the end user bene ts from the operation of otherwise idle processors in the local LAN. The virtual parallel computer is composed by otheshelf personal computers connected by alow cost network, such as a 10 Mbits=s Ethernet. The aim is to minimise the processing time of a high level image processing package. The system developed to manage the parallel execution is described and some results obtained for the parallelisation of high level image processing algorithms are discussed, namely for active contour and modal analysis methods which require the computation of the eigenvectors of a symmetric matrix. 1
Texture Synthesis and Unsupervised Recognition with a Nonparametric Multiscale Markov Random Field Model
 FOURTEENTH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION
, 1998
"... In this paper we present noncausal, nonparametric, multiscale, Markov Random Field (MRF) model for syntheslslng and recognislng texture. The model has the ability to capture the characteristics of a wide variety of textures, varying from the structured to the stochastic. For texture synthesis, we us ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
In this paper we present noncausal, nonparametric, multiscale, Markov Random Field (MRF) model for syntheslslng and recognislng texture. The model has the ability to capture the characteristics of a wide variety of textures, varying from the structured to the stochastic. For texture synthesis, we use our own novel multiscale approach, incorporating local annealing, allowing us to use large neighbourhood systems to model some complex textures. We show how we are able to manipulate the statistical order of our high dimensional model without over compromising the integrity of the representation. Also by varying the statistical order of our model we are able to optimise it for the unsupervised recognition of textures with respect to textures that have not been modelled.
Invited Paper
"... Active Perception (Active Vision specifically) is defined as a study of Modeling and Control strategies for perception. By modeling we mean models of sensors, processing modules and their interaction. We distinguish local models from global models by their extent of application in space and time. T ..."
Abstract
 Add to MetaCart
Active Perception (Active Vision specifically) is defined as a study of Modeling and Control strategies for perception. By modeling we mean models of sensors, processing modules and their interaction. We distinguish local models from global models by their extent of application in space and time. The local models represent procedures and parameters such as optical distortions of the lens, focal lens, spatial resolution, bandpass filter, etc. The global models on the other hand characterize the overall performance and make predictions on how the individual modules interact. The control strategies are formulated as a search of such sequence of steps that would minimize a loss function while one is seeking the most information. Examples are shown as the existence proof of the proposed theory on obtaining range from focus and sterolvergence on 20 segmentation of an image and 30 shape parametriza tion. I.