CVPR2017两篇基于骨架的动作识别
来源:互联网 发布:最火淘宝店铺 编辑:程序博客网 时间:2024/06/05 05:40
标签(空格分隔): 文章阅读
一、ST-NBNN:
没上神经网络
Each 3D action instance is represented by a collection of temporal stages composed by 3D poses, and each pose in stages is presented by a collection of spatial joints.
1. Introduction
learning-based classifiers,基于学习的骨架分类方法[5, 24, 35, 21, 14, 13] 已经取得了很多进展
non-parametric classifiers 不需要学习,训练参数 的分类方法还没有被很好的探索
- 动机有二
1:
2:骨架信息并不像图片,有成千上万个像素,只有上十个joints,因此不需要端到端的复杂模型,非参数模型也能搞定 方法
1:通过使用stage-to-class distance and bilinear classifier,该模型结合了参数模型和非参数模型的长处
2:通过关键帧和关键的骨架节点(key temporal stages and spatial joints),模型能提取出必要的时空模型spatio-temporal patterns结果
仅用线性分类器就能超过很多端到端的模型
2. Related Work
各种基于骨架的spatial/temporal/spacial-temporal 模型
- spatial
把骨架分成几部分,用神经网络找这几部分之间的关系
jopints,算joints之间的angle之类的 - temporal
好几种,不怎么理解 - spacial-temporal:
LSTM分析时空域骨架信息
NBNN
3.Proposed Method
(1)stage-descriptor
We first introduce a set of stage-descriptors to represent a 3D
sequence (Sec. 3.1).
描述子内容:pose 和velocity
1video=N*stage=N*(l frames)(2)NBNN来对descriptor分类
Then NBNN [2] is used as a basic framework to classify actions (Sec. 3.2).- (3)学习时域和空域上的权重
Finally, the learning of spatial and temporal weights is introduced to discover
key poses and spatial joints for action recognition (Sec. 3.3)
二、基于李群的网络用来做动作识别
Deep Learning on Lie Groups for Skeleton-based Action Recognition
Lie group representations for action recognition
文章视频
提出了一个新的神经网络LieNet,学习基于李群的3D骨架特征来进行动作识别
- 1.将李群结构和神经网络结合起来,相比于传统的神经网络结构,网络结构为了适应李群做了相应的调整,添加了RotMap Layer、RotPooling Layer、. LogMap Layer
- 2.在这个结构中,为了使用反向传播算法,随机梯度下降法也做了相应探索
视频中列举的两个demo
realtime huaman pose recognition in parts from a single depth image
作者的LieNet 在NTU-RGBD dataset ( A Shahroudy et al CVPR2016)上展示
三、骨架相关的数据集
MSR-Action3D
Finally, the MSR Action3D [45] represents one of the most used datasets for HAR. It includes 20 activities performed by 10 subjects, 2 or 3 times. In total, 567 sequences of depth (320 × 240) and skeleton frames are provided, but 10 of them have to be discarded because the skeletons are either missing or affected by too many errors. The following activities are included in the dataset: high arm wave, horizontal arm wave,hammer, hand catch, forward punch, high throw, draw X, draw tick, draw circle, hand clap, two-hand wave, side boxing, bend, forward kick, side kick, jogging, tennis swing, tennis serve, golf swing, and pickup and throw. The dataset has been collected using a structured-light depth camera at 15 fps; RGB data are not available.
UTKinect
http://cvrc.ece.utexas.edu/KinectDatasets/HOJ3D.html
Berkeley MHAD
HMDB05
NTU RGBD CVPR2016
- RGB videos
- depth map sequences
- 3D skeletal data
- infrared videos
将3D骨架信息映射到视频中去
- CVPR2017两篇基于骨架的动作识别
- 基于密集轨迹的动作识别
- 基于OpenCV的简易四肢位置识别与动作识别
- 基于zhang 的骨架提取
- 关于基于WiFi动作识别的一些简单看法
- 基于3D关节点的人体动作识别综述
- 动作识别的笔记
- cvpr2017-branchout——基于CNN的在线集成跟踪
- 基于视频动作识别研究--求交流
- “非手动的个人电脑控制” 基于眼球动作识别的鼠标光标控制
- 基于单幅深度图像的实时人体部位动作识别(摘要+概述)
- 基于kinect的人体动作识别系统(算法和代码都放出)
- kinect+ogre骨架追踪及手势识别(基于微软kinectSDK)
- 基于express框架的应用程序骨架生成器介绍
- 基于SDF的抽骨架之散点图(Projected points)
- 基于轮廓的三维骨架重建方法和核心代码
- 基于距离变换的中轴线道路骨架提取算法
- 基于html5的多文件上传核心骨架文件
- 指数型母函数
- LeetCode 204. Count Primes
- Practical OCA Java SE 8 Programmer I Certification Guide (Java Basics).azw3
- 170917 软件安装教程汇总
- LeetCode 64. Minimum Path Sum
- CVPR2017两篇基于骨架的动作识别
- JDBC连接数据库,数据库访问层
- python 与 3D 可视化----(1)
- API认证方式
- Coursera machine learning week 6(一)
- 3章 文件I/O
- 简单排序
- 航院 6213 Chinese Zodiac
- 增加测试函数计算排序函数运行时间