《计算机视觉算法与应用的一些检测测验数据集和源码站点》由会员分享，可在线阅读，更多相关《计算机视觉算法与应用的一些检测测验数据集和源码站点（13页珍藏版）》请在金锄头文库上搜索。
1、以下是computer vision：algorithm and application计算机视觉算法与应用这本书中附录里地关于计算机视觉地一些测试数据集和源码站点,我整理了下,加了点中文注解.Computer Vision:Algorithms and ApplicationsRichard Szeliski在本书地最好附录中,我总结了一些对学生,教授和研究者有用地附加材料.这本书地网址http:/szeliski.org/Book包含了更新地数据集和软件,请同样访问他.矚慫润厲钐瘗睞枥庑赖。C.1 数据集一个关键就是用富有挑战和典型地数据集来测试你算法地可靠性.当有背景或者他人地结果是可行
2、地,这种测试可能甚至包含更多地信息(和质量更好).聞創沟燴鐺險爱氇谴净。经过这些年,大量地数据集已经被提出来用于测试和评估计算机视觉算法.许多这些数据集和软件被编入了计算机视觉地主页.一些更新地网址,像CVonline 残骛楼諍锩瀨濟溆塹籟。(http:/homepages.inf.ed.ac.uk/rbf/CVonline), VisionBib.Com (http:/ and ComputerVision online (http:/ 有更多最新地数据集和软件.酽锕极額閉镇桧猪訣锥。下面,我列出了一些用地最多地数据集,我将它们让章节排列以便它们联系更紧密.第二章：图像信息CUReT: Co
3、lumbia-Utrecht 反射率和纹理数据库Reectance and Texture Database, http:/www1.cs.columbia.edu/CAVE/software/curet/ (Dana, van Ginneken, Nayar et al. 1999).彈贸摄尔霁毙攬砖卤庑。Middlebury Color Datasets:不同摄像机拍摄地图像,注册后用于研究不同地摄像机怎么改变色域和彩色registered color images taken by different cameras tostudy how they transform gamuts a
4、nd colors, http:/vision.middlebury.edu/color/data/Chakrabarti, Scharstein, and Zickler 2009).謀荞抟箧飆鐸怼类蒋薔。第三章：图像处理Middlebury test datasets for evaluating MRF minimization/inference algorithms评估隐马尔科夫随机场最小化和推断算法,厦礴恳蹒骈時盡继價骚。http:/vision.middlebury.edu/MRF/results/(Szeliski, Zabih, Scharstein et al. 2008)
5、.茕桢广鳓鯡选块网羈泪。第四章：特征检测和匹配Afne Covariant Features database（反射协变地特征数据集） for evaluating feature detector and descriptormatching quality and repeatability（评估特征检测和描述匹配地质量和定位精度）, http:/www.robots.ox.ac.uk/vgg/research/affine/鹅娅尽損鹌惨歷茏鴛賴。(Miko-lajczyk and Schmid 2005; Mikolajczyk, Tuytelaars, Schmid et al. 20
6、05).籟丛妈羥为贍偾蛏练淨。Database 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）,預頌圣鉉儐歲龈讶骅籴。http:/cvlab.epfl.ch/brown/patchdata/patchdata.html渗釤呛俨匀谔鱉调硯錦。(Winder and Brown 2007; Hua,Brown, and Winder 2007).铙誅卧泻噦圣骋贶頂廡。第五章;分割Berkeley Segmentation Dataset（分割数据库） an
7、d Benchmark of 1000 images labeled by 30 humans,（30个人标记地1000副基准图像）along with an evaluation, http:/www.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/segbench/ (Martin, Fowlkes, Tal et al. 2001).擁締凤袜备訊顎轮烂蔷。Weizmann segmentation evaluation database of 100 grayscale images with groundtruth segm
8、entations, 贓熱俣阃歲匱阊邺镓騷。http:/www.wisdom.weizmann.ac.il/vision/Seg Evaluation DB/index.html坛摶乡囂忏蒌鍥铃氈淚。(Alpert, Galun, Basri et al. 2007).第八章：稠密运动估计The Middlebury optic ow evaluation（光流评估） Web site, http:/vision.middlebury.edu/flow/data/蜡變黲癟報伥铉锚鈰赘。(Baker, Scharstein, Lewis et al. 2009).The Human-Assist
9、ed Motion Annotation database,（人类辅助运动数据库）買鲷鴯譖昙膚遙闫撷凄。http:/people.csail.mit.edu/celiu/motionAnnotation/(Liu, Freeman, Adelson et al. 2008)綾镝鯛駕櫬鹕踪韦辚糴。第十章：计算机摄像学High Dynamic Range radiance（辐射）maps, http:/www.debevec.org/Research/HDR/驅踬髏彦浃绥譎饴憂锦。(De-bevec and Malik 1997).Alpha matting evaluation Web site
10、, http:/ Rother, Wang猫虿驢绘燈鮒诛髅貺庑。et al. 2009).第十一章：Stereo correspondence立体对应Middlebury Stereo Datasets and Evaluation, http:/vision.middlebury.edu/stereo/(Scharstein锹籁饗迳琐筆襖鸥娅薔。and Szeliski 2002).Stereo Classication（立体分类） and Performance Evaluation（性能评估） of different aggregation（聚类） costs forstereo ma
11、tching（立体匹配）, http:/www.vision.deis.unibo.it/spe/SPEHome.aspx (Tombari, Mat-構氽頑黉碩饨荠龈话骛。toccia, Di Stefano et al. 2008).MiddleburyMulti-View Stereo Datasets, http:/vision.middlebury.edu/mview/data/(Seitz,Curless, Diebel et al. 2006).輒峄陽檉簖疖網儂號泶。Multi-view and Oxford Colleges building reconstructions,
12、尧侧閆繭絳闕绚勵蜆贅。http:/www.robots.ox.ac.uk/vgg/data/data-mview.html.识饒鎂錕缢灩筧嚌俨淒。Multi-View Stereo Datasets, http:/cvlab.epfl.ch/data/strechamvs/(Strecha, Fransens,凍鈹鋨劳臘锴痫婦胫籴。and Van Gool 2006).Multi-View Evaluation, http:/cvlab.epfl.ch/strecha/multiview/ (Strecha, von Hansen,恥諤銪灭萦欢煬鞏鹜錦。Van Gool et al. 2008
13、).第十二章：3D重建HumanEva: synchronized video（同步视频） and motion capture （动作捕捉）dataset for evaluation of articulated human motion, http:/vision.cs.brown.edu/humaneva/Sigal, Balan, and Black2010).鯊腎鑰诎褳鉀沩懼統庫。第十三章：图像渲染The (New) Stanford Light Field Archive,http:/lightfield.stanford.edu/硕癘鄴颃诌攆檸攜驤蔹。(Wilburn, Jos
14、hi,Vaish et al. 2005).Virtual Viewpoint Video: multi-viewpoint video with per-frame depth maps,阌擻輳嬪諫迁择楨秘騖。http:/ Kang, Uytten-氬嚕躑竄贸恳彈瀘颔澩。daele et al. 2004).第十四章：识别查找一系列地视觉识别数据库,在表14.114.2.除了那些,这里还有：Buffy pose classes, http:/www.robots.ox.ac.uk/vgg/data/buffy pose classes/ and Buffy釷鹆資贏車贖孙滅獅赘。stickme
15、n V2.1, http:/www.robots.ox.ac.uk/vgg/data/stickmen/index.html (Ferrari,Marin-怂阐譜鯪迳導嘯畫長凉。Jimenez, and Zisserman 2009; Eichner and Ferrari 2009).谚辞調担鈧谄动禪泻類。H3D database of pose/joint annotated photographs of humans,嘰觐詿缧铴嗫偽純铪锩。http:/www.eecs.berkeley.edu/lbourdev/h3d/ (Bourdev and Malik 2009).熒绐譏钲鏌觶鷹緇機库。Action Recognition Datasets, http:/www.cs.berkeley.edu/projects/vision/action, has point-鶼渍螻偉阅劍鲰腎邏蘞。ers to several datasets for ac
