Efficient indexing techniques for model based sensing

1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 1994-06-21 DOI:10.1109/cvpr.1994.323838

A. Wallack, J. Canny

{"title":"Efficient indexing techniques for model based sensing","authors":"A. Wallack, J. Canny","doi":"10.1109/cvpr.1994.323838","DOIUrl":null,"url":null,"abstract":"Indexing is a model-based recognition technique, in which unknown objects are identified using lookup tables. Indexing coordinates are extracted from sensed features, and the indexing coordinates specify a table entry containing the object's identity. Usually, only a small fraction of the possible indexing coordinates correspond to modeled objects, and hash tables are often used to save space. In this paper, we present a new indexing data structure called a tree grid which has two advantages over hash tables. (i) The tree grid preserves spatial ordering, so that nearby indexing entries can be retrieved efficiently (ii) The tree grid compacts the storage size of the table by a factor of as much as two orders of magnitude. k coordinates index an ordering of the interpretations, and 1 coordinate determines the consistent interpretations for objects with k degrees of freedom. We also show that for almost all model sets, 2k+1 indexing coordinates care sufficient to discriminate between two generic models, implying that 2k+1 indexing coordinates specify a unique in interpretation. We have implemented an indexing algorithm for recognizing 3D objects from pairs of image rays using the tree grid technique, and the results are reported.<<ETX>>","PeriodicalId":160667,"journal":{"name":"1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","volume":"19 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1994-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/cvpr.1994.323838","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 8

Abstract

Indexing is a model-based recognition technique, in which unknown objects are identified using lookup tables. Indexing coordinates are extracted from sensed features, and the indexing coordinates specify a table entry containing the object's identity. Usually, only a small fraction of the possible indexing coordinates correspond to modeled objects, and hash tables are often used to save space. In this paper, we present a new indexing data structure called a tree grid which has two advantages over hash tables. (i) The tree grid preserves spatial ordering, so that nearby indexing entries can be retrieved efficiently (ii) The tree grid compacts the storage size of the table by a factor of as much as two orders of magnitude. k coordinates index an ordering of the interpretations, and 1 coordinate determines the consistent interpretations for objects with k degrees of freedom. We also show that for almost all model sets, 2k+1 indexing coordinates care sufficient to discriminate between two generic models, implying that 2k+1 indexing coordinates specify a unique in interpretation. We have implemented an indexing algorithm for recognizing 3D objects from pairs of image rays using the tree grid technique, and the results are reported.<>

查看原文本刊更多论文

基于模型感知的高效索引技术

索引是一种基于模型的识别技术，其中使用查找表识别未知对象。从感知的特征中提取索引坐标，索引坐标指定包含对象标识的表项。通常，只有一小部分可能的索引坐标对应于建模对象，并且通常使用散列表来节省空间。在本文中，我们提出了一种新的索引数据结构，称为树网格，它比哈希表有两个优点。(1)树形网格保持空间顺序，以便可以有效地检索附近的索引条目(2)树形网格将表的存储大小压缩了两个数量级。K个坐标表示解释的顺序，1个坐标决定了对具有K个自由度的物体的一致解释。我们还表明，对于几乎所有的模型集，2k+1索引坐标足以区分两个一般模型，这意味着2k+1索引坐标指定了唯一的解释。我们利用树形网格技术实现了一种从图像射线对中识别三维物体的索引算法，并报道了结果

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition

自引率

0.00%

发文量