其实是Overview翻译的。 233
contrib英语简介:地址
AR增强现实模块,可用于黑白板摄像机的校准。 请参阅文章
ar uco : arucoandcharucomarkers—augmentedrealityaruco小型超短裙er and ‘ChARUco ‘小型超短裙ers where ArUco小型超短裙ersembedddeded
背景分割—-静态背景估计与贝叶斯像素级分割相结合,更多背景分割见Opencv分割模块地址
bgse GM : backgroundsegmentationalgorithmcombiningstatisticalbackgroundimageestimationandper-pixelbayesiansegmentation。
生物视觉—-生物启发模型:最小化噪声、亮度变化、瞬间事件分割、高动态范围色调映射
请看高高的、2333、小巧的迷你裙)
bio inspired : biological vision—biologicallyinspiredvisionmodel : minimizenoiseandluminancevariance,transievevevence
自定义标定—-三维重建、摄像机标定、随机模式标定、多摄像机标定
calib : custom calibration—- patterns for3dre construction,omnidirectionalcameracalibration,randompatterncalibrationation
基于33558www.Sina.com—-caffe
CNN _3dobj : deepobjectrecognitionandpose– usescaffedeepneuralnetlibrarytobuild,trainandtestacnmodelofvisualobjectred
CNN物体识别和姿态估计—-便于调试
cvv : computervisiondebugger– simplecodethatyoucanaddtoyourprogramthatpopsupaguiallowingyouteractivelyandvisuallydebuger
弹窗GUI—-用于读取现有CV数据集的代码
datasets : datasets reader—- codeforreadingexistingcomputervisiondatabasesandsamplesofusingthereaderstotrain,testand
数据集Reader—-CNN物体识别,Caffe训练,基于opencv_dnn模块的识别
dnn _ obj detect : objectdetectionusingcnns– implementscompactcnmodelforobjectdetection.trainedusingcaffebutusesopencv
33558 www.Sina.com—-欺骗dnn引起错误识别吗?
DNS _ easily _ fooled : subvertdnns– thiscodecanusetheactivationsinanetworktofoolthenetworksintorecognizingsomethingethingelllllins
DNN物体识别—–著名的行人识别方法
DPM :定义模型–felzenszwalb ‘ scascadewithdeformablepartsobjectrecognitioncode
.
人脸识别—-Eigen,fisher,LBPH方法
face: Face Recognition — Face recognition techniques: Eigen, Fisher and Local Binary Pattern Histograms LBPH methods.
模糊变化—-正逆模糊变化、模糊图片处理
fuzzy: Fuzzy Logic in Vision — Fuzzy logic image transform and inverse; Fuzzy image processing.
FreeType—-利用freetype和harfbuzz在图片上“画”文字
freetype: Drawing text using freetype and harfbuzz.
HDF—-hdf存储
hdf: Hierarchical Data Storage — This module contains I/O routines for Hierarchical Data Format: link. meant to store large amounts of data.
线条描述子—-线条提取和匹配 详情见: 地址
ine_descriptor: Line Segment Extract and Match — Methods of extracting, describing and latching line segments using binary descriptors.
matlab—-顾名思义,233,matlab交互接口
matlab: Matlab Interface — OpenCV Matlab Mex wrapper code generator for certain opencv core modules.
光流optflow—-deepflow、simpleflow、sparsetodenseflow、sihouette flow等方法
optflow: Optical Flow — Algorithms for running and evaluating deepflow, simpleflow, sparsetodenseflow and motion templates silhouette flow).
3D可视化—-利用ORGE 3D引擎来渲染3D数据
ovis: OGRE 3D Visualiser — allows you to render 3D data using the OGRE 3D engine.
绘图—-可以轻松绘制1D2D数据matlab风格) 参考地址
plot: Plotting — The plot module allows you to easily plot data in 1D or 2D.
图像注册—-为了精准拼接
reg: Image Registration — Pixels based image registration for precise alignment. Follows the paper “Image Alignment and Stitching: A Tutorial”, by Richard Szeliski.
RGBD模块—-linemod物体识别、快速法相计算、3D平面寻找、3D测距以及利用kinectFusion的三维重建
rgbd: RGB-Depth Processing module — Linemod 3D object recognition; Fast surface normals and 3D plane finding. 3D visual odometry. 3d reconstruction using KinectFusion.
显著性saliency—-人类看一张图会被什么所吸引?
saliency: Saliency API — Where humans would look in a scene. Has routines for static, motion and “objectness” saliency.
从2D图像进行三维重建—-轻量级的Libmv
sfm: Structure from Motion — This module contains algorithms to perform 3d reconstruction from 2d images. The core of the module is a light version of Libmv.
三维描述子—-不同的描述子用来建立三维配对关系:Census/CS-Census/MCT/BRIEF/MV.
stereo: Stereo Correspondence — Stereo matching done with different descriptors: Census / CS-Census / MCT / BRIEF / MV.
结构光—-如何利用结构光去分析场景的深度
structured_light: Structured Light Use — How to generate and project gray code patterns and use them to find dense depth in a scene.
平面配准—-利用PPF特征进行物体识别和定位
surface_matching: Point Pair Features — Implements 3d object detection and localization using multimodal point pair features.
文字识别—-检测文字,分割词汇,识别文本
text: Visual Text Matching — In a visual scene, detect text, segment words and recognise the text.
目标跟踪—-多种追踪算法 地址
tracking: Vision Based Object Tracking — Use and/or evaluate one of 5 different visual object tracking techniques.
额外的2D特征—-包括一些不免费的,SURF、SIFT、BRIEF、Censure、Rreak、LUCID、朴实的小懒虫、Self-similar
xfeatures2d: Features2D extra — Extra 2D Features Framework containing experimental and non-free 2D feature detector/descriptor algorithms. SURF, SIFT, BRIEF, Censure, Freak, LUCID, 朴实的小懒虫, Self-similar.
扩展图像处理—-结构森林、一堆filterdomain/guided/Adaptive Manifold/Joint Bilateral)、超像素、脊检测filter…
ximgproc: Extended Image Processing — Structured Forests / Domain Transform Filter / Guided Filter / Adaptive Manifold Filter / Joint Bilateral Filter / Superpixels / Ridge Detection Filter.
物体检测—-级联检测器 LBP+_WaldBoost
xobjdetect: Boosted 2D Object Detection — Uses a Waldboost cascade and local binary patterns computed as integral features for 2D object detection.
照片处理—-颜色均衡、降噪、图像修复
xphoto: Extra Computational Photography — Additional photo processing algorithms: Color balance / Denoising / Inpainting.
终于打完了,2333,感觉有好多可以尝试的,开心