Recent work in computervision has demonstrated positive results in reasoning about possible object function based on analysis of only the object shape. While shape properties are important, verification of actual fun...
详细信息
ISBN:
(纸本)0818658258
Recent work in computervision has demonstrated positive results in reasoning about possible object function based on analysis of only the object shape. While shape properties are important, verification of actual functionality generally requires consideration of properties beyond pure static shape. In particular, dynamic physical properties such as the degree of deformation or rigidity under applied force are essential to the function of many objects. The work described in this paper combines reasoning about object shape with reasoning about deformation under applied forces for recognizing (categorizing) an object according to its function. Initial reasoning about the static 3-D object shape provides a function verification plan. This plan is a sequence of interactions that lead to confirming or rejecting the suggested object function. The interactions involve applying test forces to elements of the object structure as identified in the reasoning about static 3-D shape.
A multiscale extension to the medial axis transform(MAT) or skeleton can be obtained by combining information derived from a scale-space hierarchy of boundary representations with region information provided by the MA...
详细信息
ISBN:
(纸本)0818658258
A multiscale extension to the medial axis transform(MAT) or skeleton can be obtained by combining information derived from a scale-space hierarchy of boundary representations with region information provided by the MAT. The skeleton-space is constructed by attributing each skeleton component with a hierarchically ordered sequence of residual values, each expressing the saliency of the component at a distinct resolution level. Since our method amounts to a rather symbolic than iconic computation of a multiscale MAT, it does not introduce the correspondence problem between distinct levels of detail, in contrast to other commonly proposed techniques. Our multiscale MAT is capable of describing complex shapes characterized by significantly jagged boundaries. Furthermore, tracking the evolution of prominent loci of the MAT such as nodes across scales permits to assess the most significant skeleton constituents and to automatically determine pruning parameters. A salient subset of the MAT (first order skeleton) can be extracted without the need of manual threshold adjustment.
Range data offer a direct way to produce shape descriptions of surfaces. Typically single range images have the form of a graph surface z = g(x,y) and thus suffer from occlusion. One can reduce this problem by taking ...
详细信息
ISBN:
(纸本)0818658258
Range data offer a direct way to produce shape descriptions of surfaces. Typically single range images have the form of a graph surface z = g(x,y) and thus suffer from occlusion. One can reduce this problem by taking several images from different locations and merging them together. The result is a real 3-D description of the object's surface. In this paper we address several problems that result from the 2 1/2 -D to 3-D transition. We present an algorithm which is able to merge depth images of an arbitrary shaped object using a highly local approach. An explicit sensor error model is used to support the merging. A key feature of our algorithm is the ability to update its result by an additional new view. Thus, it is possible to gradually improve the surface description in regions of high noise.
The (iterative) relaxation algorithms, used in the framework of Markov Random Field-based image analysis may quickly lead to prohibitive computation times on workstations when sophisticated models and real-time applic...
详细信息
ISBN:
(纸本)0818658258
The (iterative) relaxation algorithms, used in the framework of Markov Random Field-based image analysis may quickly lead to prohibitive computation times on workstations when sophisticated models and real-time applications have to be handled. Stochastic relaxation algorithms are drastically time consuming while deterministic schemes often get 'stuck' in local minima of the energy function. Besides, it is known that multigrid methods can improve significantly the convergence rate of iterative relaxation schemes. On the other hand, the computations involved by these different algorithms are regular and local, and lead naturally to massive data parallelism which is well suited for parallel processing on array processor architectures. In this paper, we present a new algorithmic framework which enables making a full use of the large potential of data parallelism available on 2D processor arrays for the implementation of non-linear multigrid relaxation methods. This framework leads to fast convergence towards quasi-optimal solutions. It is demonstrated on two different low-level vision applications.
We introduce a spatial representation, s-map, for an indoor navigation robot. The s-map represents the locations of obstacles in a planar domain, where obstacles are defined as any objects that can block movement of t...
详细信息
ISBN:
(纸本)0818658258
We introduce a spatial representation, s-map, for an indoor navigation robot. The s-map represents the locations of obstacles in a planar domain, where obstacles are defined as any objects that can block movement of the robot. In building the s-map, the viewing triangle constraint and the stability constraint are introduced for efficient verification of vertical surfaces. These verified vertical surfaces and 3-D segments of obstacles smaller than a robot, are mapped to the s-map by simply dropping height information. Thus, the s-map is made directly form 3-D segments with simple verification, and represents obstacles in a planar domain so that it becomes a navigable map for the robot without further processing. In addition to efficient map building, the s-map represents the environment more realistically and completely. Furthermore, the s-map converts many navigation problems in 3-D, such as map fusion and path planning, into 2-D ones. We present the analysis of the s-map in terms of complexity and reliability, and discuss its pros and cons. Moreover, we show the results of the s-maps for indoor environments.
Three different statistical models of colour data for use in segmentation or tracking algorithms are proposed. Results of a performance comparison of a tracking algorithm, applied to two separate applications, using e...
详细信息
ISBN:
(纸本)0780342364
Three different statistical models of colour data for use in segmentation or tracking algorithms are proposed. Results of a performance comparison of a tracking algorithm, applied to two separate applications, using each of the three different types of underlying model of the data are presented. From these a comparison of the performance of the statistical colour models themselves is obtained.
We propose a new method for view synthesis from real images using stereo vision. The method does not explicitly model scene geometry, and enables fast and exact generation of synthetic views. We also reevaluate the re...
详细信息
ISBN:
(纸本)0818672587
We propose a new method for view synthesis from real images using stereo vision. The method does not explicitly model scene geometry, and enables fast and exact generation of synthetic views. We also reevaluate the requirements on stereo algorithms for the application of view synthesis and discuss ways of dealing with partially occluded regions of unknown depth and with completely occluded regions of unknown texture. Our experiments demonstrate that it is possible to efficiently synthesize realistic new views even from inaccurate and incomplete depth information.
We present a new, efficient stereo algorithm addressing robust disparity estimation in the presence of occlusions. The algorithm is an adaptive, multi-window scheme using left-right consistency to compute disparity an...
详细信息
ISBN:
(纸本)0780342364
We present a new, efficient stereo algorithm addressing robust disparity estimation in the presence of occlusions. The algorithm is an adaptive, multi-window scheme using left-right consistency to compute disparity and its associated uncertainty. We demonstrate and discuss performances with both synthetic and real stereo pairs, and show how our results improve an those of closely related techniques for both robustness and efficiency.
暂无评论