目标检测、跟踪和图像检索 数据库

目标检测、跟踪、识别标准测试视频集和图像数据库

一个网友收集的运动目标检测，阴影检测的标准测试视频

http://blog.csdn.net/sunbaigui/article/details/6363390

Ground truth data for tracking of (almost) planar objects

http://cmp.felk.cvut.cz/demos/Tracking/linTrack/data/index.html

    

很权威的change detection检测视频集，里面有将近20种主流算法在这个测试集上的运行结果和ROC,PRA曲线

http://changedetection.net/

 

VIVID Tracking Evaluation Web Site

http://vision.cse.psu.edu/data/vividEval/datasets/datasets.html

 

cvpapers的数据集，包括人脸检测，人脸识别，猫脸检测，行人检测，显著性检测等测试图集，以及目标分割，目标跟踪，前背景分离算法的测试视频 

http://www.cvpapers.com/datasets.html

 

cv数据库大全

http://datasets.visionbib.com/

 http://clickdamage.com/sourcecode/cv_datasets.php

九洲大学数据库

http://limu.ait.kyushu-u.ac.jp/dataset/en/index.html

 

Florida大学数据库，内有一些目标检测的开源代码

http://vision.eecs.ucf.edu/projects/Turbulence/

 

Wallflower数据库

http://research.microsoft.com/en-us/um/people/jckrumm/wallflower/testimages.htm

1. PETS2001的测试视频
http://www.filewatcher.com/b/ftp/ftp.cs.rdg.ac.uk/pub/PETS2001.0.0.html
内容如下，可以得到如下所示5个DATASET，有训练和测试视频：

ftp://ftp.cs.rdg.ac.uk/pub/PETS2001/direct 532 B 2001-07-25welcome.msg5 mirrors 6 B 2006-10-24WWW2 mirrors 532 B 2001-07-25PETS2001_README2 mirrors 0 2001-12-11DoNotDownLoadThisFile2 mirrors [DIR]DATASET5/direct2 twin directories [DIR]DATASET4/direct2 twin directories [DIR]DATASET3/direct6 twin directories [DIR]DATASET2/direct6 twin directories [DIR]DATASET1/direct6 twin directories 0 2001-06-23.chunkdesc2 mirrors 0 2001-06-23.bufferloc2 mirrors

2. 阴影检测（Shadow Detection）测试视频及CVPR-ATON 阴影检测相关论文
http://cvrr.ucsd.edu/aton/shadow/
在下面原始movie可以下载到：Highway、Campus、Laboratory、Intelligent Room，这些视频。

Technical Papers A. Prati, I. Mikic, M. Trivedi, R. Cucchiara, "Detecting Moving Shadows: Formulation, Algorithms and Evaluation" (Under Review June 2001) - Survey I. Mikic, P. Cosman, G.. Kogut, M. Trivedi, "Moving Shadow and Object Detection in Traffic Scenes", International Conference on Pattern Recognition, September 2000, pp. 321-324 vol. 1 R. Cucchiara, C. Grana, M. Piccardi, A. Prati, "Detecting objects, shadows and ghosts in video streams by exploiting color and motion information", Appearing in Proceedings of 11th International Conference on Image Analysis and Processing (ICIAP 2001), September 2001. M. Trivedi, I. Mikic, G. Kogut, "Distributed Video Networks for Incident Detection and Management", IEEE Conference on Intelligent Transportation Systems, Dearborn, Michigan, October 2000. Testbed Data Comparative Movies (Highway I,Intelligent Room - AVIs) Raw Movies (Highway I,Highway II, Campus, Laboratory, Intelligent Room - AVIs) Manually Segmented Images (Ground Truth - Zipped BMPs)

3. IBM人类视觉研究中心监视系统性能评价提供的视频
http://www.research.ibm.com/peoplevision/performanceevaluation.html
这个你看了一定欣喜若狂，一大票的视频，任你选择，不用再发愁找不到视频了！

Performance Evaluation of Surveillance Systems Effectively evaluating the performance of moving object detection and tracking algorithms is in an important step towards attaining robust digital video surveillance systems with sufficient accuracy for practical applications. As systems become more complex and achieve greater robustness, the ability to quantitatively assess performance is needed in order to continuously improve performance. To this end, we are providing video sequences and ground truth annotations for performance evaluation. Ground Truth sequences have extension .pvann and are xml files. An explanation of the ground truth procedure can be found in the paper [1] . Performance metrics and an evaluation of the IBM Smart Surveillance System can also be found in this publication. 1. Outdoor Sequences ( 4 videos from PET2001 with ground truth ) PetsD1TeC1.avi PetsD1TeC1.pvannPetsD1TeC2.avi PetsD1TeC2.pvannPetsD2TeC1.avi PetsD2TeC1.pvannPetsD2TeC2.avi PetsD2TeC2.pvann 2. Indoor Sequences (11 videoswith ground truth) IndoorGTTest1.avi IndoorGTTest1.pvann IndoorGTTest2.avi IndoorGTTest2.pvann ThreePerson_Circles_Comp_0_Quad0.avi ThreePerson_Circles_Comp_0_Quad0.pvann ThreePerson_Circles_Comp_0_Quad2.avi ThreePerson_Circles_Comp_0_Quad2.pvann ThreePerson_Circles_Comp_0_Quad3.avi ThreePerson_Circles_Comp_0_Quad3.pvann ThreePerson_Together_Split_Comp_0_Quad0.avi ThreePerson_Together_Split_Comp_0_Quad0.pvann ThreePerson_Together_Split_Comp_0_Quad2.avi ThreePerson_Together_Split_Comp_0_Quad2.pvann ThreePerson_Together_Split_Comp_0_Quad3.avi ThreePerson_Together_Split_Comp_0_Quad3.pvann TwoPerson_Line_Circle_Comp_0_Quad0.avi TwoPerson_Line_Circle_Comp_0_Quad0.pvann TwoPerson_Line_Circle_Comp_0_Quad2.avi TwoPerson_Line_Circle_Comp_0_Quad2.pvann TwoPerson_Line_Circle_Comp_0_Quad3.avi TwoPerson_Line_Circle_Comp_0_Quad3.pvann [1] Performance Evaluation of Surveillance Systems Under Varying Conditions Lisa M. Brown, Andrew W. Senior, Ying-li Tian, Jonathan Connell, Arun Hampapur, Chiao-fe Shu, Hans Merkl, and Max Lu IEEE Int'l Workshop on Performance Evaluation of Tracking and Surveillance, Colorado Jan., 2005 . PDF Other Research Areas: Robust Background Subtraction Salient Motion Detection Object Classification 2D Tracking 3D Multi-Person Tracking Articulated Human Body Tracking Active Head Tracking Coarse Head Pose Estimation Position Independent Absolute Head Pose Estimation Face Cataloger Video Privacy Multi-scale Tracking & Index Browser Real Time Alerts Middleware for Large Scale Surveillance (MILS)

图像检索数据库：

1.http://www.vision.caltech.edu/Image_Datasets/Caltech101/    

加利福尼亚理工学院101类图像数据库