检索结果-内蒙古大学图书馆

Closing the loop: Detection and pursuit of a moving object by a moving observer

IMAGE AND VISION computing 1996年第4期14卷 265-275页

作者： Nordlund, P Uhlin, T Computational Vision and Active Perception Laboratory (CVAP) Department of Numerical Analysis and Computing Science Royal Institute of Technology S-100 44 Stockholm Sweden

We present an integrated system which is able to pursue a moving object and maintain the object centered in the image by controlling a robot-head. The system contains three parts: independent motion detection, tracking, and control of a robot-head. This paper focuses on the detection mechanism, and briefly discusses the tracking and control issues. The system runs continuously in time and updates the object localization at a frame-rate of 25 Hz. The moving object can be tracked, although the observer performs an unknown independent motion, involving both translation and rotation. We focus on a simple motion detection algorithm, since computational cost is of major importance for real-time systems with feedback. The algorithm is noniterative and computationally inexpensive. The running time complexity is O(n) for an image containing n pixels. The image-processing takes place on a MaxVideo200 pipeline processor, and the head control algorithm is running on a Transputer T800 network. Some offline experimental results are presented, where comparisons are made between affine and translational image motion models.

关键词： normal velocity real-time system tracking

来源：评论

学校读者我要写书评

暂无评论

Dynamic fixation and active perception

引用

INTERNATIONAL JOURNAL OF COMPUTER VISION 1996年第2期17卷 113-135页

作者： Pahlavan, K Uhlin, T Eklundh, JO Computational Vision and Active Perception Laboratory (CVAP) Department of Numerical Analysis and Computing Science Royal Institute of Technology S-100 44 Stockholm Sweden

Fixation is the link between the physical environment and the visual observer, both of which can be dynamic. That is, dynamic fixation serves the task of preserving a reference point in the world, despite relative motion. In this respect, fixation is dynamical in two senses: in response to voluntary changes of fixation point or attentive cues-gaze shiftings, and in response to the desire to compensate for the retinal slip-gaze holding. The work presented here, addresses the vergence movement and preservation of binocular fixation during smooth pursuit. This movement is a crucial component of fixation. The two vergence processes, disparity vergence and accommodative vergence, are described;a novel algorithm for robust disparity vergence and an active approach for blur detection and depth from defocus are presented. The main characteristics of the disparity vergence technique are the simplicity of the algorithm, the influence of both left and right images in the course of fixation and the agreement with the fixation model of primates. The major characteristic of the suggested algorithm for blur detection is its active approach which makes it suitable for achieving qualitative and reasonable depth estimations without unrealistic assumptions about the structures in the images. The paper also covers the integration of the two processes disparity vergence and accommodation vergence which are in turn accomplished by an integration of the disparity and blur stimuli. This integration is accounted for in both static and dynamic experiments.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Segmentation and classification of edges using minimum description length approximation and complementary junction cues

引用

COMPUTER VISION AND IMAGE UNDERSTANDING 1997年第1期67卷 88-98页

作者： Lindeberg, T Li, MX Computational Vision and Active Perception Laboratory (CVAP) Department of Numerical Analysis and Computing Science Royal Institute of Technology S-100 44 Stockholm Sweden

This article presents a method for segmenting and classifying edges using minimum description length (MDL) approximation with automatically generated break points. A scheme is proposed where junction candidates are first detected in a multiscale preprocessing step, which generates junction candidates with associated regions of interest. These junction features are matched to edges based on spatial coincidence, For each matched pair, a tentative break point is introduced at the edge point closest to the junction. Finally, these feature combinations serve as input for an MDL approximation method which tests the validity of the break point hypotheses and classifies the resulting edge segments as either ''straight'' or ''curved.'' Experiments on real world image data demonstrate the viability of the approach. (C) 1997 Academic Press.

关键词： Edge detection

来源：评论

学校读者我要写书评

暂无评论

INVESTIGATING SEMI-INFINITE PROGRAMS USING PENALTY-FUNCTIONS AND LAGRANGIAN-METHODS

引用

JOURNAL OF THE AUSTRALIAN MATHEMATICAL SOCIETY SERIES B-APPLIED MATHEMATICS 1986年第2期28卷 158-169页

作者： GUSTAFSON, SA Department of Numerical Analysis and Computing Science The Royal Institute of Technology S-10044 Stockholm 70 Sweden.

In this paper the relations between semi-infinite programs and optimisation problems with finitely many variables and constraints are reviewed. Two classes of convex semi-infinite programs are defined, one based on the fact that a convex set may be represented as the intersection of closed halfspaces, while the other class is defined using the representation of the elements of a convex set as convex combinations of points and directions. Extension to nonconvex problems is given. A common technique of solving a semi-infinite program computationally is to derive necessary conditions for optimality in the form of a nonlinear system of equations with finitely many equations and unknowns. In the three-phase algorithm, this system is constructed from the optimal solution of a discretised version of the given semi-infinite program. i.e. a problem with finitely many variables and constraints. The system is solved numerically, often by means of some linearisation method. One option is to use a direct analog of the familiar SOLVER method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Active fixation for scene exploration

引用

INTERNATIONAL JOURNAL OF COMPUTER VISION 1996年第2期17卷 137-162页

作者： Brunnstrom, K Eklundh, JO Uhlin, T Computational Vision and Active Perception Laboratory (CVAP) Department of Numerical Analysis and Computing Science KTH (Royal Institute of Technology) S-100 44 Stockholm Sweden

It is well-known that active selection of fixation points in humans is highly context and task dependent. It is therefore likely that successful computational processes for fixation in active vision should be so too. We are considering active fixation in the context of recognition of man-made objects characterized by their shapes. In this situation the qualitative shape and type of observed junctions play an important role. The fixations are driven by a grouping strategy, which forms sets of connected junctions separated from the surrounding at depth discontinuities. We have furthermore developed a methodology for rapid active detection and classification of junctions by selection of fixation points. The approach is based on direct computations from image data and allows integration of stereo and accommodation cues with luminance information. This work form a part of an effort to perform active recognition of generic objects, in the spirit of Malik and Biederman, but on real imagery rather than on line-drawings.

关键词： active vision Active detection Junction Device Component fixation image data Fixation Recognition (Psychology) Accommodation Line drawings Shape Ocular Accommodation

来源：评论

学校读者我要写书评

暂无评论

Machine vision research at CVAP: An introduction

引用

INTERNATIONAL JOURNAL OF COMPUTER VISION 1996年第2期17卷 107-112页

作者： Eklundh, JO Computational Vision and Active Perception Laboratory (CVAP) Department of Numerical Analysis and Computing Science KTH (Royal Institute of Technology) S-100 44 Stockholm Sweden

This paper deals with the problems on the recovery and shape and motion. It also focuses on what is representing shape. In addition, it touches a briefly on the geometry for computer vision which concerns surface modeling. However, this paper goes beyond the need to model geometry and shape for computer vision, in that is also aims at developing mathematically well-founded computational environments for studying geometry by itself.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Projectively invariant decomposition and recognition of planar shapes

引用

INTERNATIONAL JOURNAL OF COMPUTER VISION 1996年第2期17卷 193-209页

作者： Carlsson, S Computational Vision and Active Perception Laboratory (CVAP) Department of Numerical Analysis and Computing Science KTH (Royal Institute of Technology) S-100 44 Stockholm Sweden

An algorithm is presented for computing a decomposition of planar shapes into convex subparts represented by ellipses, The method is invariant to projective transformations of the shape, and thus the conic primitives can be used for matching and definition of invariants in the same way as points and lines. The method works for arbitrary planar shapes admitting at least four distinct tangents and it is based on finding ellipses with four points of contact to the given shape. The cross ratio computed from the four points on the ellipse can then be used as a projectively invariant index. It is demonstrated that a given shape has a unique parameter-free decomposition into a finite set of ellipses with unit cross ratio. For a given shape, each pair of ellipses can be used to compute two independent projective invariants. The set of invariants computed for each ellipse pair can be used as indexes to a hash table from which model hypothesis can be generated Examples of shape decomposition and recognition are given for synthetic shapes and shapes extracted from grey level images of real objects using edge detection.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Shape-adapted smoothing in estimation of 3-D shape cues from affine deformations of local 2-D brightness structure

引用

IMAGE AND VISION computing 1997年第6期15卷 415-434页

作者： Lindeberg, T Garding, J Computational Vision and Active Perception Laboratory (CVAP) Department of Numerical Analysis and Computing Science KTH (Royal Institute of Technology) S-100 44 Stockholm Sweden

This article describes a method for reducing the shape distortions due to scale space smoothing that arise in the computation of 3-D shape cues using operators (derivatives) defined from scale-space representation. More precisely, we are concerned with a general class of methods for deriving 3-D shape cues from a 2-D image data based on the estimation of locally linearized deformations of brightness patterns. This class constitutes a common framework for describing several problems in computer vision (such as shape-from-texture, shape-from disparity-gradients, and motion estimation) and for expressing different algorithms in terms of similar types of visual front-end-operations. It is explained how surface orientation estimates will be biased due to the use of rotationally symmetric smoothing in the image domain. These effects can be reduced by extending the linear scale-space concept into an affine Gaussian scale-space representation and by performing affine shape adaptation of the smoothing kernels. This improves the accuracy of the surface orientation estimates, since the image descriptors, on which the methods are based, will be relative invariant under affine transformations, and the error thus confined to the higher-order terms in the locally linearized perspective transformation. A straightforward algorithm is presented for performing shape adaptation in practice. Experiments on real and synthetic images with known orientation demonstrate that in the presence of moderately high noise levels the accuracy is improved by typically one order of magnitude.

关键词： shape estimation shape from texture disparity adaptation affine deformation optic flow

来源：评论

学校读者我要写书评

暂无评论

Direct computation of shape cues using scale-adapted spatial derivative operators

引用

INTERNATIONAL JOURNAL OF COMPUTER VISION 1996年第2期17卷 163-191页

作者： Garding, J Lindeberg, T Computational Vision and Active Perception Laboratory (CVAP) Department of Numerical Analysis and Computing Science KTH (Royal Institute of Technology) S-100 44 Stockholm Sweden

This paper addresses the problem of computing cues to the three-dimensional structure of surfaces in the world directly from the local structure of the brightness pattern of either a single monocular image or a binocular image pair. It is shown that starting from Gaussian derivatives of order up to two at a range of scales in scale-space, local estimates of (i) surface orientation from monocular texture foreshortening, (ii) surface orientation from monocular texture gradients, and (iii) surface orientation from the binocular disparity gradient can be computed without iteration or search, and by using essentially the same basic mechanism. The methodology is based on a multi-scale descriptor of image structure called the windowed second moment matrix, which is computed with adaptive selection of both scale levels and spatial positions. Notably, this descriptor comprises two scale parameters;a local scale parameter describing the amount of smoothing used in derivative computations, and an integration scale parameter determining over how large a region in space the statistics of regional descriptors is accumulated. Experimental results for both synthetic and natural images are presented, and the relation with models of biological vision is briefly discussed.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

LOW SPIKING RATES IN A POPULATION OF MUTUALLY EXCITING PYRAMIDAL CELLS (VOL 6, PG 271, 1995)

引用

NETWORK-COMPUTATION IN NEURAL SYSTEMS 1995年第3期6卷 511-511页

作者： FRANSEN, E LANSNER, A SANS — Studies of Artificial Neural Systems Department of Numerical Analysis and Computing Science Royal Institute of Technology S-100 44 Stockholm Sweden

In a recurrent artificial neural network, the units active in an attractor state typically reach their maximum activity value while the others are quiescent. In contrast, recordings of cortical cell activity in vivo rarely reveal cells firing at their maximum rate. This discrepancy has been one of the main arguments against using attractor networks as models of cortical associative memory. In this study we show that low-rate sustained after-activity can be obtained in a simulated network of mutually exciting pyramidal cells. This is achieved by assuming that the synapses in the network are of a saturating type. When the application of a monoamine neuromodulator is simulated, after-activity with firing rates around 60?s^?1 can be produced. The firing pattern of the network was found to be similar to that of the experimentally most comparable system, the disinhibited hippocampal slice. The results obtained are robust against simulated biological variation and background noise.

关键词： Primate temporal cortex Computer-based model Neural networks Visual-cortex Realistic simulations Neuronal correlate Dendritic spines Cortical-neurons Firing rates Term-memory FIRING RATE Attractor Neural network Computer based modeling cell activity ignition sequence Network Dendritic Spines realistic simulation Visual Cortex

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：