Volumetric Features for Large-Scale Video Processing
用于大规模视频处理的体积特征
基本信息
- 批准号:0534962
- 负责人:
- 金额:--
- 依托单位:
- 依托单位国家:美国
- 项目类别:Continuing Grant
- 财政年份:2005
- 资助国家:美国
- 起止时间:2005-11-01 至 2009-10-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Technical Overview. This project addresses the design of features extracted from video streams to enable detection and classification of visual events. The emphasis of the project is on unsupervised learning of features and classifiers from training data and on the ability to deal efficiently with large volumes of data. Careful design of the features is crucial to ensure that they can handle a large volume of data efficiently while, at the same time, accurately extracting events that are relevant to the applications. This project focuses on the development of spatio-temporal features that can be efficiently and accurately extracted from video streams. This is combined with recent developments in the area of architectures for distributed search based on active storage, which are specifically designed for processing very large databases of images and videos, are ideally suited for making effective use of the video feature detectors. Key objectives of the project include integrating the feature extraction approach with current active storage approaches and evaluating the resulting systems in the context of applications such as video retrieval, surveillance, and forensic video reconstruction.The project addresses the fundamental questions related to the analysis of video streams: (1) What makes a good feature representation and is there a single choice of representation? (2) What spatio-temporal primitives exist in video? (3) How to efficiently detect spatio-temporal primitives? These questions are addressed in the course of the project by (1) developing a novel approach for the automatic segmentation of spatio-temporal regions that are consistent in both appearance and motion; and (2) developing a novel approach for extracting spatio-temporal features based on new "volumetric" operators that operate directly on the spatio-temporal cube and for using these features for event classification. The segmentation algorithm is an extension of the classical mean shift, and the volumetric operators are spatio-temporal extensions of box operators that have been successful in extracting and classifying features in 2D images. These two developments provide the fundamental modules for future video analysis systems. These techniques are important building blocks for efficient object recognition in video. In addition to the fundamental contributions in algorithms and feature design, the scope of the project includes validating the approaches by demonstrating their integration with emerging approaches in distributed search systems that employ active storage to enable efficient processing of 100 terabyte-sized video collections.Broader Impact. The amount of digital video data has grown exponentially in recent years due to the increasing affordability of digital consumer video cameras, large-scale deployment of video surveillance systems, ease of digital content creation, and availability of high-speed networks and high-capacity storage devices. Manual organization and annotation of this content is becoming infeasible. Unfortunately, the technology for searching, indexing and retrieving video content has failed to keep pace. In particular, the processing of very large volumes of video data requires efficient ways of pre-processing the videos to extract features corresponding to interesting temporal events. The project addresses this need directly by providing new technology that will enable the development of large-scale video analysis tools. The products of project have potential impact on all virtually all applications of video analysis. The project focuses on a few broad classes of applications with substantial societal impact in the areas of improved access to information and security. In particular, the project contributes to video retrieval (e.g., for education), video surveillance (e.g., for homeland security), forensic video reconstruction (e.g., for law enforcement) and smart environments (e.g., for business and homes). In order to assist in the application of the technology to these areas, the project includes a plan for transfer through an external partner whose role is to provide data sets (e.g., the IRP speaker video dataset), scenarios, computing resources, software and guidance for the evaluation of the algorithms, as well as access to state of the art active storage technology. This collaboration will enable the integration our the video processing elements with new developments in active storage technology, and to demonstrate the applicability of our approach to large-scale distributed video analysis systems.URL: http://www.cs.cmu.edu/~hebert/vol3d.html
技术概述。该项目旨在设计从视频流中提取的特征,以实现视觉事件的检测和分类。该项目的重点是对训练数据中的特征和分类器进行无监督学习,以及有效处理大量数据的能力。仔细设计这些功能对于确保它们能够有效地处理大量数据,同时准确地提取与应用程序相关的事件至关重要。该项目的重点是开发时空特征,可以有效地和准确地从视频流中提取。这与最近的发展相结合,在该地区的架构的分布式搜索的基础上,主动存储,这是专门设计用于处理非常大的数据库的图像和视频,非常适合有效地利用视频特征检测器。该项目的主要目标包括将特征提取方法与当前的主动存储方法相结合,并在视频检索、监控和法医视频重建等应用背景下评估所产生的系统,该项目解决了与视频流分析相关的基本问题:(1)什么是好的特征表示,是否存在单一的表示选择?(2)视频中存在哪些时空原语?(3)如何有效地检测时空基元?这些问题是解决的过程中的项目(1)开发一种新的方法,自动分割的时空区域是一致的外观和运动;和(2)开发一种新的方法提取时空特征的基础上新的“体积”运营商直接操作的时空立方体和使用这些功能的事件分类。分割算法是经典均值漂移的扩展,体积算子是在2D图像中成功提取和分类特征的盒算子的时空扩展。这两个发展为未来的视频分析系统提供了基本的模块。这些技术是视频中有效对象识别的重要组成部分。除了在算法和功能设计方面的基本贡献外,该项目的范围还包括通过展示这些方法与分布式搜索系统中的新兴方法的集成来验证这些方法,这些分布式搜索系统采用主动存储,能够有效处理100 TB大小的视频集合。近年来,数字视频数据量呈指数级增长,这是由于数字消费者摄像机的可负担性不断提高、视频监控系统的大规模部署、数字内容创建的便利性以及高速网络和大容量存储设备的可用性。手动组织和注释这些内容变得不可行。不幸的是,搜索、索引和检索视频内容的技术未能跟上步伐。特别地,非常大量的视频数据的处理需要预处理视频以提取对应于感兴趣的时间事件的特征的有效方式。该项目通过提供能够开发大规模视频分析工具的新技术,直接满足了这一需求。该项目的产品对视频分析的几乎所有应用都有潜在的影响。该项目侧重于在改善信息获取和安全领域具有重大社会影响的几大类应用程序。特别是,该项目有助于视频检索(例如,用于教育),视频监视(例如,用于国土安全),法医视频重建(例如,用于执法)和智能环境(例如,对于企业和家庭)。为了协助将技术应用于这些领域,该项目包括一项通过外部伙伴进行转让的计划,该伙伴的作用是提供数据集(例如,IRP演讲者视频数据集)、场景、计算资源、软件和算法评估指南,以及访问最先进的主动存储技术。这种合作将使我们的视频处理元件与主动存储技术的新发展相结合,并证明我们的方法适用于大规模分布式视频分析系统。URL:http://www.cs.cmu.edu/~hebert/vol3d.html
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Martial Hebert其他文献
Evolution of a Prototype Lunar Rover: Addition of Laser-Based Hazard Detection, and Results from Field Trials in Lunar Analog Terrain
- DOI:
10.1023/a:1008926000060 - 发表时间:
1999-09-01 - 期刊:
- 影响因子:4.300
- 作者:
Eric Krotkov;Martial Hebert;Lars Henriksen;Paul Levin;Mark Maimone;Reid Simmons;James Teza - 通讯作者:
James Teza
Stereo perception and dead reckoning for a prototype lunar rover
- DOI:
10.1007/bf00710797 - 发表时间:
1995-01-01 - 期刊:
- 影响因子:4.300
- 作者:
Eric Krotkov;Martial Hebert;Reid Simmons - 通讯作者:
Reid Simmons
Intelligent Unmanned Ground Vehicles: Autonomous Navigation Research at Carnegie Mellon
- DOI:
- 发表时间:
1997 - 期刊:
- 影响因子:0
- 作者:
Martial Hebert - 通讯作者:
Martial Hebert
Learning Compositional Representations for Few-Shot Recognition Supplementary Material
学习少镜头识别的组合表示补充材料
- DOI:
- 发表时间:
2019 - 期刊:
- 影响因子:0
- 作者:
P. Tokmakov;Yu;Martial Hebert - 通讯作者:
Martial Hebert
Martial Hebert的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('Martial Hebert', 18)}}的其他基金
2015 National Robotics Initiative PI Meeting
2015年国家机器人计划PI会议
- 批准号:
1540080 - 财政年份:2015
- 资助金额:
-- - 项目类别:
Standard Grant
NRI-Large: Collaborative Research: Purposeful Prediction: Co-robot Interaction via Understanding Intent and Goals
NRI-Large:协作研究:有目的的预测:通过理解意图和目标进行协作机器人交互
- 批准号:
1227495 - 财政年份:2012
- 资助金额:
-- - 项目类别:
Continuing Grant
RI: Medium: Collaborative Research: Physically Grounded Object Recognition
RI:媒介:协作研究:物理接地物体识别
- 批准号:
0905402 - 财政年份:2009
- 资助金额:
-- - 项目类别:
Standard Grant
Exploratory Research in Scene Analysis and Object Recognition
场景分析与物体识别的探索性研究
- 批准号:
0745636 - 财政年份:2007
- 资助金额:
-- - 项目类别:
Standard Grant
RI: Detecting Boundaries for Segmentation and Recognition
RI:检测分割和识别的边界
- 批准号:
0713406 - 财政年份:2007
- 资助金额:
-- - 项目类别:
Continuing Grant
Fast Capture and Understanding of Dynamic 3-D Shapes
快速捕捉和理解动态 3D 形状
- 批准号:
0102272 - 财政年份:2001
- 资助金额:
-- - 项目类别:
Continuing Grant
Time and Space-Efficient Template Based Indexing
基于时间和空间高效模板的索引
- 批准号:
9907142 - 财政年份:1999
- 资助金额:
-- - 项目类别:
Continuing Grant
Point-Based Surface Representation for Shape Similarity and Object Recognition
用于形状相似性和对象识别的基于点的表面表示
- 批准号:
9711853 - 财政年份:1997
- 资助金额:
-- - 项目类别:
Continuing Grant
Workshop on Object Representation in Computer Vision
计算机视觉中的对象表示研讨会
- 批准号:
9407040 - 财政年份:1994
- 资助金额:
-- - 项目类别:
Standard Grant
Modeling and Recognizing Three-Dimensional Curved Objects
三维弯曲物体的建模和识别
- 批准号:
9224521 - 财政年份:1993
- 资助金额:
-- - 项目类别:
Continuing Grant
相似海外基金
Integrative approach to identify genomic features that shape the immune landscape and predict immunotherapy response in diffuse large B cell lymphoma
识别塑造免疫景观并预测弥漫性大 B 细胞淋巴瘤免疫治疗反应的基因组特征的综合方法
- 批准号:
10660739 - 财政年份:2023
- 资助金额:
-- - 项目类别:
Appropriate Incorporation of Groundwater Flow Features and Processes in Small- to Large-Scale Hydrologic Models
在小型到大型水文模型中适当纳入地下水流特征和过程
- 批准号:
571298-2021 - 财政年份:2022
- 资助金额:
-- - 项目类别:
Alliance Grants
Investigating architectural features of large-scale brain networks using white matter lesions
利用白质病变研究大规模脑网络的结构特征
- 批准号:
547546-2020 - 财政年份:2022
- 资助金额:
-- - 项目类别:
Alexander Graham Bell Canada Graduate Scholarships - Doctoral
Applying machine learning techniques to detect and classify faint tidal features with samples from upcoming large-scale surveys.
应用机器学习技术,利用即将进行的大规模调查的样本来检测和分类微弱的潮汐特征。
- 批准号:
2782601 - 财政年份:2022
- 资助金额:
-- - 项目类别:
Studentship
Defining the genomic and microenvironmental features of diffuse large B cell lymphoma in HIV + patients (Biospecimens/Biocohort)
定义 HIV 患者弥漫性大 B 细胞淋巴瘤的基因组和微环境特征(生物样本/生物队列)
- 批准号:
10619709 - 财政年份:2022
- 资助金额:
-- - 项目类别:
Investigating architectural features of large-scale brain networks using white matter lesions
利用白质病变研究大规模脑网络的结构特征
- 批准号:
547546-2020 - 财政年份:2021
- 资助金额:
-- - 项目类别:
Alexander Graham Bell Canada Graduate Scholarships - Doctoral
Hidden features and information diffusion in large social networks
大型社交网络中的隐藏特征和信息传播
- 批准号:
RGPIN-2017-05112 - 财政年份:2021
- 资助金额:
-- - 项目类别:
Discovery Grants Program - Individual
Investigating architectural features of large-scale brain networks using white matter lesions
利用白质病变研究大规模脑网络的结构特征
- 批准号:
547546-2020 - 财政年份:2020
- 资助金额:
-- - 项目类别:
Alexander Graham Bell Canada Graduate Scholarships - Doctoral
Hidden features and information diffusion in large social networks
大型社交网络中的隐藏特征和信息传播
- 批准号:
RGPIN-2017-05112 - 财政年份:2020
- 资助金额:
-- - 项目类别:
Discovery Grants Program - Individual
Hidden features and information diffusion in large social networks
大型社交网络中的隐藏特征和信息传播
- 批准号:
RGPIN-2017-05112 - 财政年份:2019
- 资助金额:
-- - 项目类别:
Discovery Grants Program - Individual