Action Snippets V1.0
====================
Code written by Konrad Schindler, using components provided by Peter Kovesi and Anton Schweighofer.
Research by Konrad Schindler and L. van Gool.
Quick start
-----------
1) uncompress the archive with TAR or WINZIP.
2) change to directory snippets/code
3) open MATLAB
4) run the feature extraction, using the provided data ad control file:
> features('../data/weizmann.txt'); This takes a while. Features are written to file, so you need not do this again, unless you change the parameters of feature extraction.
5) run the feature pooling:
> pooling('../data/weizmann.txt'); Again, the pooled features are written to file, so unless you change the pooling size, you need not do this again.
6) test the classification:
> crossvalidation('../data/weizmann.txt'); This takes a LONG while, because the PCA-basis is recomputed for each fold. The PCA-bases are written to file, so that you can later load them from file, as long as you are using the same snippet length - change the variable <Globals.features_tofile>.
Overview
--------
Welcome to this software release, which implements the functionality reported in [1]:
- extracting features from action videos
- training a classifier for the actions
- testing the classifier with crossvalidation
The release includes the complete Matlab source code. It is recommend to use the code only with Matlab 8 or higher. In addition to the code, this release also includes the cropped frames of the WEIZMANN dataset [2]. The crops were generated automatically, using the author's silhouette annotations.
Parameter Settings
------------------
All parameters are set directly in the top-level files.
Look for variables names <Globals.XXX>. Variable names and code comments should be self-explanatory, if you read the paper [1].
Using your dataset
------------------
To use other data than the provided Weizmann frames:
- split the video into single files; all frames must be the same size, and all clips must have the same number of frames. The frames from one clip must follow the naming convention <name.3-digit-framenumber.extension>.
- prepare a control file, using the template <weizmann.txt>. Class labels are integer numbers starting from 1.
- run the three steps of the program with your controlfile.
Support
-------
For any query/suggestion/complaint or simply to say you like/use this software, just drop me an email:
[email protected]
I wish you a good time using this software,
Konrad
References
----------
[1] K. Schindler and L. van Gool. Action snippets: how many frames does human action recognition require? CVPR 2009.
[2] L. Gorelick, M. Blank, E. Shechtman, M. Irani and R. Basri. Actions as space-time shapes. ICCV 2005.
没有合适的资源?快使用搜索试试~ 我知道了~
特征描述子surf,hog,光流
共2688个文件
png:2532个
m:69个
jpg:11个
5星 · 超过95%的资源 需积分: 9 62 下载量 138 浏览量
2013-06-30
19:54:47
上传
评论 3
收藏 24.26MB RAR 举报
温馨提示
特征描述部分的代码,有surf,hog,光流,三种下面又有多种应用代码实现,如图像拼接,匹配,动作识别等等。还有相应实验结果分析。拿来和大家分享
资源推荐
资源详情
资源评论
收起资源包目录
特征描述子surf,hog,光流 (2688个子文件)
Lucas_Kanade.asv 6KB
HS.asv 3KB
anna_phog.asv 2KB
Untitled.asv 717B
Derivative.asv 525B
anna_phog_demo.asv 515B
optical_flow_demo.bsc 2.02MB
surfmatch.c 6KB
mexutils.c 2KB
cvsurf.cpp 21KB
optical_flow_demo.cpp 12KB
surfpoints.cpp 10KB
demo.cpp 3KB
Thumbs.db 29KB
optical_flow_demo.dep 93B
surfWINDLL.dll 52KB
实验总结.doc 226KB
实验分析.doc 103KB
实验总结.doc 28KB
实验分析.doc 20KB
实验分析.doc 20KB
匹配.doc 11KB
optical_flow_demo.dsp 4KB
demo.dsp 3KB
optical_flow_demo.dsw 559B
demo.dsw 516B
demo.exe 336KB
optical_flow_demo.exe 204KB
surflib.h 4KB
surf.h 3KB
fasthessian.h 3KB
image.h 3KB
ipoint.h 2KB
surfWINDLL.h 821B
cvsurf.h 728B
vc60.idb 337KB
vc60.idb 153KB
demo.ilk 467KB
optical_flow_demo.ilk 228KB
SAM_1750.JPG 3.87MB
changjing.jpg 409KB
outabcde.jpg 122KB
b.jpg 122KB
1.jpg 122KB
d.jpg 122KB
2.jpg 119KB
a.jpg 118KB
c.jpg 116KB
e.jpg 116KB
3.jpg 107KB
surfWINDLL.lib 14KB
svmtrain.m 21KB
crossvalidation.m 10KB
gaborconvolve.m 7KB
Lucas_Kanade.m 6KB
svm.m 5KB
panorama.m 5KB
anna_phog_demo.m 4KB
estimate_projective_ransac.m 4KB
flowmap_withties.m 3KB
features.m 3KB
svmkernel.m 3KB
HS.m 3KB
extract_flowfeatures.m 3KB
ecoctrain.m 3KB
consist.m 3KB
flowmap.m 2KB
surfpoints.m 2KB
svmfwd.m 2KB
ecocfwd.m 2KB
anna_phog.m 2KB
Estimate.m 2KB
short_example.m 2KB
ecoc.m 2KB
EstimateMotion.m 1KB
plotFlow.m 1KB
surfoptions.m 1KB
pooling.m 1KB
anna_binMatrix.m 1KB
max_pooling.m 1KB
anna_phogDescriptor.m 1KB
surfmatch.m 1KB
distance.m 1KB
gaussFilter.m 1KB
learn_pca_representation.m 1KB
estimate_projective_nonlinear.m 1021B
surfmatch_matlab.m 1007B
smoothImg.m 944B
learn_pca.m 944B
frame2vec.m 864B
learn_classification_npairs.m 795B
Untitled.m 771B
computeDerivatives.m 759B
read_exp.m 753B
imgshift.m 705B
surfplot.m 690B
extract_pca_descriptors.m 646B
majority_vote.m 636B
learn_classification_ova.m 633B
estimate_projective4point.m 620B
共 2688 条
- 1
- 2
- 3
- 4
- 5
- 6
- 27
囧神柴囧
- 粉丝: 14
- 资源: 18
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
最新资源
- Picasso_v3.1 2.ipa
- chromedriver-mac-arm64.zip
- 蓝zapro.apk
- chromedriver-linux64.zip
- UCAS研一深度学习实验-MNIST手写数字识别python源码+详细注释(高分项目)
- 基于Python和PyTorch框架完成的一个手写数字识别实验源码(带MINIST手写数字数据集)+详细注释(高分项目)
- 基于Matlab在MNIST数据集上利用CNN完成手写体数字识别任务,并实现单层CNN反向传播算法+源代码+文档说明(高分项目)
- NVIDIA驱动、CUDA和Pytorch及其依赖
- 基于SVM多特征融合的微表情识别python源码+项目说明+详细注释(高分课程设计)
- html动态爱心代码一(附源码)
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功
- 1
- 2
前往页