转载“现在Computer Vision基本要用的几个图像特征和方法”
来源:互联网 发布:昆山seo外包公司 编辑:程序博客网 时间:2024/06/11 03:04
转载自:http://www.zhizhihu.com/html/y2010/2431.html
一直在关注Action Classification,VOC2010结果发布之后,大体看了一下,基本上就那些图像特征的使用(dense SIFT+Spatial Pyramid),然后就是乱七八糟的融合了,归结都低就是Multiple Kernel Learning以及一些近似的算法。
下面看看VOC2010关于ActionClassification部分的结果:
Average Precision (AP %)
instrument
bike
horse
photo
computer
各种方法的描述后面也有。
首先看看UCLEAR_SVM_DOSP_MULTFEATS的方法:
Multiple chi squared kernels are computed: spatial pyramid (SP) w/ dense SIFT, dense overlapping SP w/ HOG, texture filter, LAB values (bag-of-words w/ the above features) and edge dir hists. They are computed on full images, person bounding boxes (BB) and BB of the lower part (simple stretch-scale of person BB) expected to contain horse, bike etc. They are combined with class specific binary weights based on their perf on val set. Finally, class specific SVMs trained on train+val.
是不是感觉方法很简单?
再看看SURREY_MK_KDA的方法:
Kernel-level fusion with Spatial Pyramid Grids, Soft Assignment and Kernel Discriminant Analysis using spectral regression. 18 kernels have been generated from 18 variants of SIFT. 融合吧。
CVC_SEL的方法:
Enhanced CVC submission built upon CVC-BASE for action recognition. Standard BoW model over multiple features from CVC-BASE plus contextual object descriptors. Cross-validation procedure for action-specific feature and kernel selection. Foreground/background/neighborhood modeled separately, spatial pyramid over several features for foreground representation. Object detection based on deformable part-based detector incorporated. Late fusion of feature-specific SVM outputs for final action score.
综上所述:Spatial Pyramid w/(dense SIFT | overlap HOG)这是最好用的描述模板的方法,一起用就用Multiple Kernel融合起来,学个融合的参数,其实效果真的很好很好,不骗你。
所以说,对于一些类似这样的问题,除非你是非得自己发明一些描述子,不然用这些就能够达到一些实验的目标,当然实用也是未尝不可的。
- 转载“现在Computer Vision基本要用的几个图像特征和方法”
- 现在Computer Vision基本要用的几个图像特征和方法
- 【computer vision】目标检测的图像特征提取之——LBP特征
- 【computer vision】目标检测的图像特征提取之——HOG特征
- Computer Vision -- 特征点提取
- 搜集的computer vision网址和算法
- 【转载】Computer vision research groups
- Python Computer Vision Programming学习笔记(二)——基本的图像操作与处理
- Computer Vision中一些常用的图像数据库
- Computer Vision的尴尬
- Computer Vision的尴尬
- computer vision的前景
- Computer Vision的尴尬
- Computer Vision的尴尬
- computer vision的前景
- 入门经典的computer vision
- 图像处理和计算机视觉中的Gabor滤波:Gabor filter for image processing and computer vision
- Computer Vision
- 天易17----spring定时器配置与实现(很好用)
- RFID电子标签的七大特点
- org.hibernate.exception.SQLGrammarException: Cannot open connection解决
- git 创建远程仓库
- ie6对postion:fixed的完美解决方案
- 转载“现在Computer Vision基本要用的几个图像特征和方法”
- 通过wifi调试android程序(本文为转载)
- cocos2d-x引擎的核心类-沈大海cocos2d-x教程7
- opencv中facedetect例子浅析
- 在Visual Studio 2010中配置VC++目录
- 纯代码布局
- C#网络编程系列九:类似QQ的即时通信程序
- Variable Modifiers [变量调节器]
- Hibernate学习第一天 配置环境和helloworld