首页 > 最新文献

2007 IEEE Conference on Computer Vision and Pattern Recognition最新文献

英文 中文
Two thresholds are better than one 两个门槛胜过一个门槛
Pub Date : 2007-06-17 DOI: 10.1109/CVPR.2007.383500
Zhang Tao, T. Boult, R. C. Johnson
The concept of the Bayesian optimal single threshold is a well established and widely used classification technique. In this paper, we prove that when spatial cohesion is assumed for targets, a better classification result than the "optimal" single threshold classification can be achieved. Under the assumption of spatial cohesion and certain prior knowledge about the target and background, the method can be further simplified as dual threshold classification. In core-dual threshold classification, spatial cohesion within the target core allows "continuation" linking values to fall between the two thresholds to the target core; classical Bayesian classification is employed beyond the dual thresholds. The core-dual threshold algorithm can be built into a Markov random field model (MRF). From this MRF model, the dual thresholds can be obtained and optimal classification can be achieved. In some practical applications, a simple method called symmetric subtraction may be employed to determine effective dual thresholds in real time. Given dual thresholds, the quasi-connected component algorithm is shown to be a deterministic implementation of the MRF core-dual threshold model combining the dual thresholds, extended neighborhoods and efficient connected component computation.
贝叶斯最优单阈值的概念是一种成熟且广泛使用的分类技术。本文证明了在假设目标空间内聚的情况下,可以获得比“最优”单阈值分类更好的分类结果。在空间内聚和目标与背景具有一定先验知识的前提下,该方法可进一步简化为双阈值分类。在核心-双阈值分类中,目标核心内的空间内聚性允许“延续”链接值落在两个阈值之间;在双阈值之外采用经典贝叶斯分类。核心-对偶阈值算法可构建为马尔可夫随机场模型(MRF)。利用该模型可获得双阈值,实现最优分类。在一些实际应用中,可以采用一种称为对称减法的简单方法来实时确定有效的对偶阈值。在给定对偶阈值的情况下,拟连通分量算法是结合对偶阈值、扩展邻域和高效连通分量计算的MRF核心-对偶阈值模型的确定性实现。
{"title":"Two thresholds are better than one","authors":"Zhang Tao, T. Boult, R. C. Johnson","doi":"10.1109/CVPR.2007.383500","DOIUrl":"https://doi.org/10.1109/CVPR.2007.383500","url":null,"abstract":"The concept of the Bayesian optimal single threshold is a well established and widely used classification technique. In this paper, we prove that when spatial cohesion is assumed for targets, a better classification result than the \"optimal\" single threshold classification can be achieved. Under the assumption of spatial cohesion and certain prior knowledge about the target and background, the method can be further simplified as dual threshold classification. In core-dual threshold classification, spatial cohesion within the target core allows \"continuation\" linking values to fall between the two thresholds to the target core; classical Bayesian classification is employed beyond the dual thresholds. The core-dual threshold algorithm can be built into a Markov random field model (MRF). From this MRF model, the dual thresholds can be obtained and optimal classification can be achieved. In some practical applications, a simple method called symmetric subtraction may be employed to determine effective dual thresholds in real time. Given dual thresholds, the quasi-connected component algorithm is shown to be a deterministic implementation of the MRF core-dual threshold model combining the dual thresholds, extended neighborhoods and efficient connected component computation.","PeriodicalId":351008,"journal":{"name":"2007 IEEE Conference on Computer Vision and Pattern Recognition","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123830289","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 6
Detection and segmentation of moving objects in highly dynamic scenes 高动态场景中运动物体的检测与分割
Pub Date : 2007-06-17 DOI: 10.1109/CVPR.2007.383244
Aurélie Bugeau, P. Pérez
Detecting and segmenting moving objects in dynamic scenes is a hard but essential task in a number of applications such as surveillance. Most existing methods only give good results in the case of persistent or slowly changing background, or if both the objects and the background are rigid. In this paper, we propose a new method for direct detection and segmentation of foreground moving objects in the absence of such constraints. First, groups of pixels having similar motion and photometric features are extracted. For this first step only a sub-grid of image pixels is used to reduce computational cost and improve robustness to noise. We introduce the use of p-value to validate optical flow estimates and of automatic bandwidth selection in the mean shift clustering algorithm. In a second stage, segmentation of the object associated to a given cluster is performed in a MAP/MRF framework. Our method is able to handle moving camera and several different motions in the background. Experiments on challenging sequences show the performance of the proposed method and its utility for video analysis in complex scenes.
在动态场景中检测和分割运动物体是一项困难但又必不可少的任务,在许多应用中,如监视。大多数现有方法只有在背景持续或缓慢变化的情况下,或者对象和背景都是刚性的情况下,才能给出良好的结果。在本文中,我们提出了一种在没有这些约束的情况下直接检测和分割前景运动目标的新方法。首先,提取具有相似运动和光度特征的像素组。对于第一步,仅使用图像像素的子网格来减少计算成本并提高对噪声的鲁棒性。我们介绍了使用p值来验证光流估计和平均移位聚类算法中的自动带宽选择。在第二阶段,在MAP/MRF框架中执行与给定集群相关的对象的分割。我们的方法能够处理移动的相机和背景中的几个不同的运动。对具有挑战性的视频序列进行了实验,证明了该方法的有效性和对复杂场景视频分析的实用性。
{"title":"Detection and segmentation of moving objects in highly dynamic scenes","authors":"Aurélie Bugeau, P. Pérez","doi":"10.1109/CVPR.2007.383244","DOIUrl":"https://doi.org/10.1109/CVPR.2007.383244","url":null,"abstract":"Detecting and segmenting moving objects in dynamic scenes is a hard but essential task in a number of applications such as surveillance. Most existing methods only give good results in the case of persistent or slowly changing background, or if both the objects and the background are rigid. In this paper, we propose a new method for direct detection and segmentation of foreground moving objects in the absence of such constraints. First, groups of pixels having similar motion and photometric features are extracted. For this first step only a sub-grid of image pixels is used to reduce computational cost and improve robustness to noise. We introduce the use of p-value to validate optical flow estimates and of automatic bandwidth selection in the mean shift clustering algorithm. In a second stage, segmentation of the object associated to a given cluster is performed in a MAP/MRF framework. Our method is able to handle moving camera and several different motions in the background. Experiments on challenging sequences show the performance of the proposed method and its utility for video analysis in complex scenes.","PeriodicalId":351008,"journal":{"name":"2007 IEEE Conference on Computer Vision and Pattern Recognition","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123145775","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 97
Efficient Indexing For Articulation Invariant Shape Matching And Retrieval 关节不变形状匹配与检索的高效索引
Pub Date : 2007-06-17 DOI: 10.1109/CVPR.2007.383227
S. Biswas, G. Aggarwal, R. Chellappa
Most shape matching methods are either fast but too simplistic to give the desired performance or promising as far as performance is concerned but computationally demanding. In this paper, we present a very simple and efficient approach that not only performs almost as good as many state-of-the-art techniques but also scales up to large databases. In the proposed approach, each shape is indexed based on a variety of simple and easily computable features which are invariant to articulations and rigid transformations. The features characterize pairwise geometric relationships between interest points on the shape, thereby providing robustness to the approach. Shapes are retrieved using an efficient scheme which does not involve costly operations like shape-wise alignment or establishing correspondences. Even for a moderate size database of 1000 shapes, the retrieval process is several times faster than most techniques with similar performance. Extensive experimental results are presented to illustrate the advantages of our approach as compared to the best in the field.
大多数形状匹配方法要么速度快,但过于简单,无法提供所需的性能,要么就性能而言有希望,但计算要求很高。在本文中,我们提出了一种非常简单而有效的方法,它不仅性能几乎与许多最先进的技术一样好,而且还可以扩展到大型数据库。在提出的方法中,每个形状都是基于各种简单且易于计算的特征来索引的,这些特征对关节和刚性变换是不变的。这些特征描述了形状上兴趣点之间的成对几何关系,从而为该方法提供了鲁棒性。使用有效的方案检索形状,该方案不涉及诸如形状对齐或建立对应等昂贵的操作。即使对于包含1000个形状的中等大小的数据库,检索过程也比大多数具有类似性能的技术快几倍。大量的实验结果表明,与该领域的最佳方法相比,我们的方法具有优势。
{"title":"Efficient Indexing For Articulation Invariant Shape Matching And Retrieval","authors":"S. Biswas, G. Aggarwal, R. Chellappa","doi":"10.1109/CVPR.2007.383227","DOIUrl":"https://doi.org/10.1109/CVPR.2007.383227","url":null,"abstract":"Most shape matching methods are either fast but too simplistic to give the desired performance or promising as far as performance is concerned but computationally demanding. In this paper, we present a very simple and efficient approach that not only performs almost as good as many state-of-the-art techniques but also scales up to large databases. In the proposed approach, each shape is indexed based on a variety of simple and easily computable features which are invariant to articulations and rigid transformations. The features characterize pairwise geometric relationships between interest points on the shape, thereby providing robustness to the approach. Shapes are retrieved using an efficient scheme which does not involve costly operations like shape-wise alignment or establishing correspondences. Even for a moderate size database of 1000 shapes, the retrieval process is several times faster than most techniques with similar performance. Extensive experimental results are presented to illustrate the advantages of our approach as compared to the best in the field.","PeriodicalId":351008,"journal":{"name":"2007 IEEE Conference on Computer Vision and Pattern Recognition","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123642540","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 22
Automatic Person Detection and Tracking using Fuzzy Controlled Active Cameras 基于模糊控制主动摄像机的自动人员检测与跟踪
Pub Date : 2007-06-17 DOI: 10.1109/CVPR.2007.383502
Keni Bernardin, F. V. D. Camp, R. Stiefelhagen
This paper presents an automatic system for the monitoring of indoor environments using pan-tilt-zoomable cameras. A combination of Haar-feature classifier-based detection and color histogram filtering is used to achieve reliable initialization of person tracks even in the presence of camera movement. A combination of adaptive color and KLT feature trackers for face and upper body allows for robust tracking and track recovery in the presence of occlusion or interference. The continuous recomputation of camera parameters, coupled with a fuzzy controlling scheme allow for smooth tracking of moving targets as well as acquisition of stable facial close ups, similar to the natural behavior of a human cameraman. The system is tested on a series of natural indoor monitoring scenarios and shows a high degree of naturalness, flexibility and robustness.
本文介绍了一种利用可平移变焦摄像机对室内环境进行自动监测的系统。结合基于haar特征分类器的检测和颜色直方图滤波,即使在存在摄像机运动的情况下也能实现可靠的人轨迹初始化。面部和上身的自适应颜色和KLT特征跟踪器的组合允许在存在遮挡或干扰的情况下进行稳健的跟踪和跟踪恢复。相机参数的连续重新计算,加上模糊控制方案,可以平滑跟踪运动目标,并获得稳定的面部特写,类似于人类摄影师的自然行为。该系统在一系列自然室内监控场景中进行了测试,显示出高度的自然度、灵活性和鲁棒性。
{"title":"Automatic Person Detection and Tracking using Fuzzy Controlled Active Cameras","authors":"Keni Bernardin, F. V. D. Camp, R. Stiefelhagen","doi":"10.1109/CVPR.2007.383502","DOIUrl":"https://doi.org/10.1109/CVPR.2007.383502","url":null,"abstract":"This paper presents an automatic system for the monitoring of indoor environments using pan-tilt-zoomable cameras. A combination of Haar-feature classifier-based detection and color histogram filtering is used to achieve reliable initialization of person tracks even in the presence of camera movement. A combination of adaptive color and KLT feature trackers for face and upper body allows for robust tracking and track recovery in the presence of occlusion or interference. The continuous recomputation of camera parameters, coupled with a fuzzy controlling scheme allow for smooth tracking of moving targets as well as acquisition of stable facial close ups, similar to the natural behavior of a human cameraman. The system is tested on a series of natural indoor monitoring scenarios and shows a high degree of naturalness, flexibility and robustness.","PeriodicalId":351008,"journal":{"name":"2007 IEEE Conference on Computer Vision and Pattern Recognition","volume":"1192 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120878596","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 47
A Linear Programming Approach for Multiple Object Tracking 多目标跟踪的线性规划方法
Pub Date : 2007-06-17 DOI: 10.1109/CVPR.2007.383180
Hao Jiang, S. Fels, J. Little
We propose a linear programming relaxation scheme for the class of multiple object tracking problems where the inter-object interaction metric is convex and the intra-object term quantifying object state continuity may use any metric. The proposed scheme models object tracking as a multi-path searching problem. It explicitly models track interaction, such as object spatial layout consistency or mutual occlusion, and optimizes multiple object tracks simultaneously. The proposed scheme does not rely on track initialization and complex heuristics. It has much less average complexity than previous efficient exhaustive search methods such as extended dynamic programming and is found to be able to find the global optimum with high probability. We have successfully applied the proposed method to multiple object tracking in video streams.
针对一类多目标跟踪问题,提出了一种线性规划松弛方案,其中目标间交互度量为凸,量化目标状态连续性的目标内项可以使用任意度量。该方案将目标跟踪建模为一个多路径搜索问题。它显式地建模跟踪交互,如对象空间布局一致性或相互遮挡,并同时优化多个对象轨道。该方案不依赖于轨迹初始化和复杂的启发式算法。它的平均复杂度远低于以往的高效穷举搜索方法,如扩展动态规划,并且能够以高概率找到全局最优解。我们已经成功地将该方法应用于视频流中的多目标跟踪。
{"title":"A Linear Programming Approach for Multiple Object Tracking","authors":"Hao Jiang, S. Fels, J. Little","doi":"10.1109/CVPR.2007.383180","DOIUrl":"https://doi.org/10.1109/CVPR.2007.383180","url":null,"abstract":"We propose a linear programming relaxation scheme for the class of multiple object tracking problems where the inter-object interaction metric is convex and the intra-object term quantifying object state continuity may use any metric. The proposed scheme models object tracking as a multi-path searching problem. It explicitly models track interaction, such as object spatial layout consistency or mutual occlusion, and optimizes multiple object tracks simultaneously. The proposed scheme does not rely on track initialization and complex heuristics. It has much less average complexity than previous efficient exhaustive search methods such as extended dynamic programming and is found to be able to find the global optimum with high probability. We have successfully applied the proposed method to multiple object tracking in video streams.","PeriodicalId":351008,"journal":{"name":"2007 IEEE Conference on Computer Vision and Pattern Recognition","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121176023","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 370
Towards Robust Pedestrian Detection in Crowded Image Sequences 拥挤图像序列中鲁棒行人检测研究
Pub Date : 2007-06-17 DOI: 10.1109/CVPR.2007.383300
Edgar Seemann, Mario Fritz, B. Schiele
Object class detection in scenes of realistic complexity remains a challenging task in computer vision. Most recent approaches focus on a single and general model for object class detection. However, in particular in the context of image sequences, it may be advantageous to adapt the general model to a more object-instance specific model in order to detect this particular object reliably within the image sequence. In this work we present a generative object model that is capable to scale from a general object class model to a more specific object-instance model. This allows to detect class instances as well as to distinguish between individual object instances reliably. We experimentally evaluate the performance of the proposed system on both still images and image sequences.
现实复杂场景中的目标分类检测一直是计算机视觉领域的一项具有挑战性的任务。最近的方法主要集中在对象类检测的单一通用模型上。然而,特别是在图像序列的背景下,为了在图像序列中可靠地检测该特定对象,将一般模型适应为更具体的对象实例模型可能是有利的。在这项工作中,我们提出了一个生成对象模型,它能够从一般对象类模型扩展到更具体的对象实例模型。这允许检测类实例以及可靠地区分单个对象实例。我们通过实验评估了该系统在静止图像和图像序列上的性能。
{"title":"Towards Robust Pedestrian Detection in Crowded Image Sequences","authors":"Edgar Seemann, Mario Fritz, B. Schiele","doi":"10.1109/CVPR.2007.383300","DOIUrl":"https://doi.org/10.1109/CVPR.2007.383300","url":null,"abstract":"Object class detection in scenes of realistic complexity remains a challenging task in computer vision. Most recent approaches focus on a single and general model for object class detection. However, in particular in the context of image sequences, it may be advantageous to adapt the general model to a more object-instance specific model in order to detect this particular object reliably within the image sequence. In this work we present a generative object model that is capable to scale from a general object class model to a more specific object-instance model. This allows to detect class instances as well as to distinguish between individual object instances reliably. We experimentally evaluate the performance of the proposed system on both still images and image sequences.","PeriodicalId":351008,"journal":{"name":"2007 IEEE Conference on Computer Vision and Pattern Recognition","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114200809","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 76
Enhanced Level Building Algorithm for the Movement Epenthesis Problem in Sign Language Recognition 手语识别中运动扩展问题的增强层次构建算法
Pub Date : 2007-06-17 DOI: 10.1109/CVPR.2007.383347
Ruiduo Yang, Sudeep Sarkar, B. Loeding
One of the hard problems in automated sign language recognition is the movement epenthesis (me) problem. Movement epenthesis is the gesture movement that bridges two consecutive signs. This effect can be over a long duration and involve variations in hand shape, position, and movement, making it hard to explicitly model these intervening segments. This creates a problem when trying to match individual signs to full sign sentences since for many chunks of the sentence, corresponding to these mes, we do not have models. We present an approach based on version of a dynamic programming framework, called Level Building, to simultaneously segment and match signs to continuous sign language sentences in the presence of movement epenthesis (me). We enhance the classical Level Building framework so that it can accommodate me labels for which we do not have explicit models. This enhanced Level Building algorithm is then coupled with a trigram grammar model to optimally segment and label sign language sentences. We demonstrate the efficiency of the algorithm using a single view video dataset of continuous sign language sentences. We obtain 83% word level recognition rate with the enhanced Level Building approach, as opposed to a 20% recognition rate using a classical Level Building framework on the same dataset. The proposed approach is novel since it does not need explicit models for movement epenthesis.
自动手语识别的难点之一是动作扩展问题。动作延伸是连接两个连续手势的手势动作。这种影响可能持续很长时间,并且涉及手的形状、位置和运动的变化,因此很难明确地对这些中间部分进行建模。当试图将单个符号与完整的符号句子相匹配时,这就产生了一个问题,因为对于与这些mes相对应的句子的许多块,我们没有模型。我们提出了一种基于动态规划框架版本的方法,称为水平构建,在存在运动扩展(me)的情况下,将符号与连续的手语句子同时分割和匹配。我们增强了经典的关卡构建框架,这样它就可以容纳我们没有明确模型的标签。然后将这种增强的关卡构建算法与三重语法模型相结合,以最佳地分割和标记手语句子。我们使用连续手语句子的单视图视频数据集证明了该算法的有效性。使用增强的level Building方法,我们获得了83%的单词级别识别率,而在相同的数据集上使用经典的level Building框架,识别率为20%。所提出的方法是新颖的,因为它不需要明确的运动扩展模型。
{"title":"Enhanced Level Building Algorithm for the Movement Epenthesis Problem in Sign Language Recognition","authors":"Ruiduo Yang, Sudeep Sarkar, B. Loeding","doi":"10.1109/CVPR.2007.383347","DOIUrl":"https://doi.org/10.1109/CVPR.2007.383347","url":null,"abstract":"One of the hard problems in automated sign language recognition is the movement epenthesis (me) problem. Movement epenthesis is the gesture movement that bridges two consecutive signs. This effect can be over a long duration and involve variations in hand shape, position, and movement, making it hard to explicitly model these intervening segments. This creates a problem when trying to match individual signs to full sign sentences since for many chunks of the sentence, corresponding to these mes, we do not have models. We present an approach based on version of a dynamic programming framework, called Level Building, to simultaneously segment and match signs to continuous sign language sentences in the presence of movement epenthesis (me). We enhance the classical Level Building framework so that it can accommodate me labels for which we do not have explicit models. This enhanced Level Building algorithm is then coupled with a trigram grammar model to optimally segment and label sign language sentences. We demonstrate the efficiency of the algorithm using a single view video dataset of continuous sign language sentences. We obtain 83% word level recognition rate with the enhanced Level Building approach, as opposed to a 20% recognition rate using a classical Level Building framework on the same dataset. The proposed approach is novel since it does not need explicit models for movement epenthesis.","PeriodicalId":351008,"journal":{"name":"2007 IEEE Conference on Computer Vision and Pattern Recognition","volume":" 9","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113949543","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 62
Linear and Quadratic Subsets for Template-Based Tracking 基于模板的跟踪的线性和二次子集
Pub Date : 2007-06-17 DOI: 10.1109/CVPR.2007.383179
Selim Benhimane, A. Ladikos, V. Lepetit, Nassir Navab
We propose a method that dramatically improves the performance of template-based matching in terms of size of convergence region and computation time. This is done by selecting a subset of the template that verifies the assumption (made during optimization) of linearity or quadraticity with respect to the motion parameters. We call these subsets linear or quadratic subsets. While subset selection approaches have already been proposed, they generally do not attempt to provide linear or quadratic subsets and rely on heuristics such as textured-ness. Because a naive search for the optimal subset would result in a combinatorial explosion for large templates, we propose a simple algorithm that does not aim for the optimal subset but provides a very good linear or quadratic subset at low cost, even for large templates. Simulation results and experiments with real sequences show the superiority of the proposed method compared to existing subset selection approaches.
我们提出了一种在收敛区域大小和计算时间方面显著提高基于模板的匹配性能的方法。这是通过选择模板的一个子集来完成的,该子集验证了关于运动参数的线性或二次性的假设(在优化期间进行的)。我们称这些子集为线性子集或二次子集。虽然已经提出了子集选择方法,但它们通常不试图提供线性或二次子集,而是依赖于纹理性等启发式方法。由于对最优子集的简单搜索会导致大型模板的组合爆炸,因此我们提出了一种简单的算法,它不以最优子集为目标,而是以低成本提供非常好的线性或二次子集,即使对于大型模板也是如此。仿真和真实序列的实验结果表明,该方法与现有的子集选择方法相比具有优越性。
{"title":"Linear and Quadratic Subsets for Template-Based Tracking","authors":"Selim Benhimane, A. Ladikos, V. Lepetit, Nassir Navab","doi":"10.1109/CVPR.2007.383179","DOIUrl":"https://doi.org/10.1109/CVPR.2007.383179","url":null,"abstract":"We propose a method that dramatically improves the performance of template-based matching in terms of size of convergence region and computation time. This is done by selecting a subset of the template that verifies the assumption (made during optimization) of linearity or quadraticity with respect to the motion parameters. We call these subsets linear or quadratic subsets. While subset selection approaches have already been proposed, they generally do not attempt to provide linear or quadratic subsets and rely on heuristics such as textured-ness. Because a naive search for the optimal subset would result in a combinatorial explosion for large templates, we propose a simple algorithm that does not aim for the optimal subset but provides a very good linear or quadratic subset at low cost, even for large templates. Simulation results and experiments with real sequences show the superiority of the proposed method compared to existing subset selection approaches.","PeriodicalId":351008,"journal":{"name":"2007 IEEE Conference on Computer Vision and Pattern Recognition","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126363470","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 30
Real-time Object Classification in Video Surveillance Based on Appearance Learning 基于外观学习的视频监控实时目标分类
Pub Date : 2007-06-17 DOI: 10.1109/CVPR.2007.383503
Lun Zhang, S. Li, Xiao-Tong Yuan, Shiming Xiang
Classifying moving objects to semantically meaningful categories is important for automatic visual surveillance. However, this is a challenging problem due to the factors related to the limited object size, large intra-class variations of objects in a same class owing to different viewing angles and lighting, and real-time performance requirement in real-world applications. This paper describes an appearance-based method to achieve real-time and robust objects classification in diverse camera viewing angles. A new descriptor, i.e., the multi-block local binary pattern (MB-LBP), is proposed to capture the large-scale structures in object appearances. Based on MB-LBP features, an adaBoost algorithm is introduced to select a subset of discriminative features as well as construct the strong two-class classifier. To deal with the non-metric feature value of MB-LBP features, a multi-branch regression tree is developed as the weak classifiers of the boosting. Finally, the error correcting output code (ECOC) is introduced to achieve robust multi-class classification performance. Experimental results show that our approach can achieve real-time and robust object classification in diverse scenes.
对运动物体进行语义分类是自动视觉监控的重要内容。然而,这是一个具有挑战性的问题,因为与有限的对象尺寸有关的因素,由于不同的视角和照明,同一类中对象的类内变化很大,以及在实际应用中的实时性能要求。本文提出了一种基于外观的方法,在不同摄像机视角下实现实时、鲁棒的目标分类。提出了一种新的描述符,即多块局部二进制模式(MB-LBP),用于捕获物体外观中的大规模结构。基于MB-LBP特征,引入adaBoost算法选择判别特征子集,构造强两类分类器。为了处理MB-LBP特征的非度量特征值,提出了一种多分支回归树作为boosting的弱分类器。最后,引入纠错输出码(ECOC)来实现鲁棒的多类分类性能。实验结果表明,该方法可以在多种场景下实现实时、鲁棒的目标分类。
{"title":"Real-time Object Classification in Video Surveillance Based on Appearance Learning","authors":"Lun Zhang, S. Li, Xiao-Tong Yuan, Shiming Xiang","doi":"10.1109/CVPR.2007.383503","DOIUrl":"https://doi.org/10.1109/CVPR.2007.383503","url":null,"abstract":"Classifying moving objects to semantically meaningful categories is important for automatic visual surveillance. However, this is a challenging problem due to the factors related to the limited object size, large intra-class variations of objects in a same class owing to different viewing angles and lighting, and real-time performance requirement in real-world applications. This paper describes an appearance-based method to achieve real-time and robust objects classification in diverse camera viewing angles. A new descriptor, i.e., the multi-block local binary pattern (MB-LBP), is proposed to capture the large-scale structures in object appearances. Based on MB-LBP features, an adaBoost algorithm is introduced to select a subset of discriminative features as well as construct the strong two-class classifier. To deal with the non-metric feature value of MB-LBP features, a multi-branch regression tree is developed as the weak classifiers of the boosting. Finally, the error correcting output code (ECOC) is introduced to achieve robust multi-class classification performance. Experimental results show that our approach can achieve real-time and robust object classification in diverse scenes.","PeriodicalId":351008,"journal":{"name":"2007 IEEE Conference on Computer Vision and Pattern Recognition","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128130862","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 108
Closed-Loop Tracking and Change Detection in Multi-Activity Sequences 多活动序列的闭环跟踪与变化检测
Pub Date : 2007-06-17 DOI: 10.1109/CVPR.2007.383243
Bi Song, Namrata Vaswani, A. Roy-Chowdhury
We present a novel framework for tracking of a long sequence of human activities, including the time instances of change from one activity to the next, using a closed-loop, non-linear dynamical feedback system. A composite feature vector describing the shape, color and motion of the objects, and a non-linear, piecewise stationary, stochastic dynamical model describing its spatio-temporal evolution, are used for tracking. The tracking error or expected log likelihood, which serves as a feedback signal, is used to automatically detect changes and switch between activities happening one after another in a long video sequence. Whenever a change is detected, the tracker is re initialized automatically by comparing the input image with learned models of the activities. Unlike some other approaches that can track a sequence of activities, we do not need to know the transition probabilities between the activities, which can be difficult to estimate in many application scenarios. We demonstrate the effectiveness of the method on multiple indoor and outdoor real-life videos and analyze its performance.
我们提出了一种新的框架,用于跟踪人类活动的长序列,包括从一个活动到下一个活动的变化时间实例,使用闭环,非线性动态反馈系统。使用描述物体形状、颜色和运动的复合特征向量和描述其时空演变的非线性、分段平稳、随机动态模型进行跟踪。跟踪误差或期望对数似然作为反馈信号,用于自动检测长视频序列中一个接一个发生的活动的变化和切换。每当检测到变化时,通过将输入图像与已学习的活动模型进行比较,自动重新初始化跟踪器。与其他一些可以跟踪活动序列的方法不同,我们不需要知道活动之间的转移概率,这在许多应用程序场景中很难估计。我们在多个室内和室外真实视频上验证了该方法的有效性,并分析了其性能。
{"title":"Closed-Loop Tracking and Change Detection in Multi-Activity Sequences","authors":"Bi Song, Namrata Vaswani, A. Roy-Chowdhury","doi":"10.1109/CVPR.2007.383243","DOIUrl":"https://doi.org/10.1109/CVPR.2007.383243","url":null,"abstract":"We present a novel framework for tracking of a long sequence of human activities, including the time instances of change from one activity to the next, using a closed-loop, non-linear dynamical feedback system. A composite feature vector describing the shape, color and motion of the objects, and a non-linear, piecewise stationary, stochastic dynamical model describing its spatio-temporal evolution, are used for tracking. The tracking error or expected log likelihood, which serves as a feedback signal, is used to automatically detect changes and switch between activities happening one after another in a long video sequence. Whenever a change is detected, the tracker is re initialized automatically by comparing the input image with learned models of the activities. Unlike some other approaches that can track a sequence of activities, we do not need to know the transition probabilities between the activities, which can be difficult to estimate in many application scenarios. We demonstrate the effectiveness of the method on multiple indoor and outdoor real-life videos and analyze its performance.","PeriodicalId":351008,"journal":{"name":"2007 IEEE Conference on Computer Vision and Pattern Recognition","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134535112","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 11
期刊
2007 IEEE Conference on Computer Vision and Pattern Recognition
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1