Affine Covariant Features databa（反射协变的特征数据集） for evaluating feature detector and descriptor matching quality and repeatability（评估特征检测和描述匹配的质量和定位精度）, (Miko-lajczyk and Schmid 2005; Mikolajczyk, Tuytelaars, Schmid et al. 2005).
Databa of matched image patches for learning （图像斑块匹配学习数据库）and feature descriptor evaluation（特征描述评估数据库）,
cvlab.epfl.ch/~brown/patchdata/patchdata.html
tercel(Winder and Brown 2007; Hua,Brown, and Winder 2007).
第五章;分割
Berkeley Segmentation Datat（分割数据库） and Benchmark of 1000 images labeled by 30 humans,（30个人标记的1000副基准图像）along with an evaluation, (Martin, Fowlkes, Tal et al. 2001).
Weizmann gmentation evaluation databa of 100 grayscale images with ground truth gmentations,
www.wisdom.weizmann.ac.il/~vision/Seg Evaluation DB/index.html
(Alpert, Galun, Basri et al. 2007).
第八章：稠密运动估计
The Middlebury optic flow evaluation（光流评估） Web site, vision.middlebury.edu/flow/data/
卷积编码
(Baker, Scharstein, Lewis et al. 2009).
品质管理流程The Human-Assisted Motion Annotation databa,（人类辅助运动数据库）
people.csail.mit.edu/celiu/motionAnnotation/ (Liu, Freeman, Adelson et al. 2008)
第十章：计算机摄像学
High Dynamic Range radiance（辐射）maps, www.debevec/Rearch/HDR/
(De-bevec and Malik 1997).
Alpha matting evaluation Web site, (Rhemann, Rother, Wang
et al. 2009).
第十一章：Stereo correspondence立体对应
Middlebury Stereo Datats and Evaluation, vision.middlebury.edu/stereo/ (Scharstein
常用短语and Szeliski 2002).
Stereo Classification（立体分类） and Performance Evaluation（性能评估） of different aggregation（聚类） costs for stereo matching（立体匹配）, www.vision.deis.unibo.it/spe/SPEHome.aspx翻译图片在线识别 (Tombari, Mat-
toccia, Di Stefano et al. 2008).
Middlebury Multi-View Stereo Datats,
vision.middlebury.edu/mview/data/ (Seitz,Curless, Diebel et al. 2006).
Multi-view and Oxford Colleges building reconstructions,
ac.uk/~vgg/data/data-mview.html .
Multi-View Stereo Datats, cvlab.epfl.ch/data/strechamvs/ (Strecha, Franns,
and Van Gool 2006).
Multi-View Evaluation, cvlab.epfl.ch/~strecha/multiview/ (Strecha, von Hann,
Van Gool et al. 2008).
营业费用包括第十二章：3D重建
HumanEva: synchronized video（同步视频） and motion capture （动作捕捉）datat for evaluation of articulated human motion, vision.cs.brown.edu/humaneva/ Sigal, Balan, and Black 2010).
第十三章：图像渲染
The (New) Stanford Light Field Archive, lightfield.stanford.edu/
(Wilburn, Joshi,Vaish et al. 2005).
Virtual Viewpoint Video: multi-viewpoint video with per-frame depth maps,
/en-us/um/redmond/groups/ivm/vvv/ (Zitnick, Kang, Uytten-
daele et al. 2004).
第十四章：识别
查找一系列的视觉识别数据库，在表14.1–14.2.除了那些，这里还有：
Buffy po class, buffy po class/ and Buffy
stickmen V2.1, (Ferrari,Marin-
Jimenez, and Zisrman 2009; Eichner and Ferrari 2009).
H3D databa of po/joint annotated photographs of humans,
(Bourdev and Malik 2009).
Action Recognition Datats, www.cs.berkeley.edu/projects/vision/action, has point-
ers to veral datats for action and activity recognition, as well as some papers.（有一些关于人活动和运动的数据库和论文） The human action databa at www.nada.kt
h./cvap/actions/ 包含更多的行动序列。
