姿态估计 Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations
来源：互联网 发布：辅助官网源码 编辑：程序博客网 时间：2024/06/11 15:15
Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations
Xianjie Chen and Alan Yuille
Abstract
We present a method for estimating articulated human pose from a single static image based on a graphical model with novel pairwise relations that make adaptive use of local image measurements. More precisely, we specify a graphical model for human pose which exploits the fact the local image measurements can be used both to detect parts (or joints) and also to predict the spatial relationships between them (Image Dependent Pairwise Relations). These spatial relationships are represented by a mixture model. We use Deep Convolutional Neural Networks (DCNNs) to learn conditional probabilities for the presence of parts and their spatial relationships within image patches. Hence our model combines the representational flexibility of graphical models with the efficiency and statistical power of DCNNs. Our method significantly outperforms the state of the art methods on the LSP and FLIC datasets and also performs very well on the Buffy dataset without any training.
Poster
Results & Evaluation Code
Full Code
Trained Model
@InProceedings{Chen_NIPS14, title = {Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations}, author = {Xianjie Chen and Alan Yuille}, booktitle = {Advances in Neural Information Processing Systems (NIPS)}, year = {2014},}Key Ideas
1. Intuition: We can reliably predict the relative positions of a part's neighbors (as well as the presence of the part itself) by only observing the local image patch around it.
2. Deep Convolutional Neural Network is suitable to extract information about pairwise part relations, as well as part presence, from local image patches, which can be used in the unary and pairwise terms of the Graphical Model.
Estimation Examples
Performance
Comparison of PDJ curves of elbows and wrists on the Frames Labeled In Cinema (FLIC) Datasetusing Observer-Centric (OC) annotations. The curves are for Tompson et al., NIPS'14, DeepPose, CVPR'14 and MODEC, CVPR'13.
Figure Data: flic_elbows.fig | flic_wrists.fig
Cross-dataset PDJ curves of elbows and wrists on the Buffy Stickmen Dataset using Observer-Centric (OC) annotations. Note that both our method and DeepPose are trained on the FLIC dataset. Compared with the curves on the FLIC dataset, the margin between our method and DeepPose significantly increases, which implies that our model generalizes better.
Figure Data: cross_dataset_buffy_elbows.fig | cross_dataset_buffy_elbows.fig
Related Pages
Nice Performance Evaluation by Pishchulin et al.
Buffy Stickmen Dataset (Buffy)
Leeds Sports Pose Dataset (LSP)
Extended Leeds Sports Pose Dataset (ex_LSP)
Frames Labeled In Cinema Dataset (FLIC)
from: http://www.stat.ucla.edu/~xianjie.chen/projects/pose_estimation/pose_estimation.html
0 0
- 姿态估计 Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations
- [姿态预测] Advancing Human Pose and Gesture Recognition章节 Pose Estimation with a Deep Heatmap Network
- 人体姿态估计综述（Human Pose Estimation Overview）
- 人体姿态估计数据集整理（Pose Estimation/Keypoint）
- 人体姿态估计数据集整理（Pose Estimation/Keypoint）
- 【姿态估计】Pose estimation algorithm 之 Robust Planar Pose (RPP)algorithm
- 【姿态估计】外参Pose estimation algorithm 之 Robust Planar Pose (RPP)algorithm
- 论文阅读：Pose Machines: Articulated Pose Estimation via Inference Machines
- 在自遮挡下的单目图像3D姿态估计 Monocular Image 3D Human Pose Estimation under Self-Occlusion (ICCV 13)
- 计算机视觉中头部姿态估计的研究综述--Head Pose Estimation in Computer Vision
- 行人姿态估计--Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
- 姿态估计论文思路整理 -- Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
- 手势估计- Hand Pose Estimation
- 手势估计- Hand Pose Estimation
- Head Pose Estimation From a 2D Face Image Using 3D Face Morphing With Depth Parameters [2015]
- 《Towards Viewpoint Invariant 3D Human Pose Estimation》--深度图领域人体姿态估计的CNN算法
- 身体姿势估计 - Human Pose Estimation
- 人体姿态估计（human pose estimate）
- 手把手教你github托管代码
- 将 Qt 5.6 集成至 VS2015
- Controller return view()
- 《Linux4.0设备驱动开发详解》笔记--第十六章：USB主机、设备与Gadget驱动
- c++11标准——泛型算法
- 姿态估计 Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations
- Python内置方法的时间复杂度
- 《Linux4.0设备驱动开发详解》笔记--第十七章：I2C、SPI、USB驱动架构类比
- 条理清晰的搭建SSH环境之添加所需jar包
- opencv中的sift、surf遇到的问题
- 不管在不在arc下，object对象都有强引用、弱引用之分
- 《Linux4.0设备驱动开发详解》笔记--第十八章：ARM Linux设备树
- 环信SDK Demo中的语音通话的流程分析
- Python入门：模拟登录（一）urllib
