Pose Estimation/keypoint常用数据集
1. Posetrack:https://posetrack.net/
2. LSP:http://sam.johnson.io/research/lsp.html
3. FLIC:https://bensapp.github.io/flic-dataset.html
4. MPII:http://human-pose.mpi-inf.mpg.de/
5. MSCOCO:http://cocodataset.org/#download
6. AI Challenge:https://challenger.ai/competition/keypoint/subject
2D Pose estimation主要面临的困难:遮挡、复杂背景、光照、真实世界的复杂姿态、人的尺度不一、拍摄角度不固定等。
单人姿态估计
传统方法:基于Pictorial Structures, DPM
▪ 基于深度学习的算法包括直接回归坐标(Deep Pose)和通过热力图回归坐标(CPM, Hourlgass)
目前单人姿态估计,主流算法是基于Hourlgass各种更改结构的算法。
多人姿态估计
二维图像姿态估计基于CNN的多人姿态估计方法,通常有2个思路(Bottom-Up Approaches和Top-Down Approaches):
(1)Top-Down Approaches,即two-step framework,就是先进行行人检测,得到边界框,然后在每一个边界框中检测人体关键点,连接成一个人形,缺点就是受检测框的影响太大,漏检,误检,IOU大小等都会对结果有影响,算法包括RMPE、Mask-RCNN 等。
(2)Bottom-Up Approaches,即part-based framework,就是先对整个图片进行每个人体关键点部件的检测,再将检测到的部件拼接成一个人形,缺点就是会将不同人的不同部位按一个人进行拼接,代表方法就是openpose、DeepCut 、PAFs。
tricks
三、Single PersonPose estimation
2014----Articulated Pose Estimation by a Graphical Model with ImageDependent Pairwise Relations
2014----DeepPose_Human Pose Estimation via Deep Neural Networks
2014----Joint Training of a Convolutional Network and a Graphical Model forHuman Pose Estimation
2014----Learning Human Pose Estimation Features with Convolutional Networks
2014----MoDeep_ A Deep Learning Framework Using Motion Features for HumanPose Estimation
2015----Efficient Object Localization Using Convolutional Networks
2015----Human Pose Estimation with Iterative Error
2015----Pose-based CNN Features for Action Recognition
2016----Advancing Hand Gesture Recognition with High Resolution ElectricalImpedance Tomography
2016----Chained Predictions Using Convolutional Neural Networks
2016----CPM----Convolutional Pose Machines
2016----CVPR-2016----End-to-End Learning of Deformable Mixture of Parts andDeep Convolutional Neural Networks for Human Pose Estimation
2016----Deep Learning of Local RGB-D Patches for 3D Object Detection and 6DPose Estimation
2016----PAFs----Realtime Multi-Person 2D Pose Estimation using PartAffinity Fields
2016----Stacked hourglass----StackedHourglass Networks for Human Pose Estimation
2016----Structured Feature Learning for Pose Estimation
2017----Adversarial PoseNet_ A Structure-aware Convolutional Network forHuman pose estimation
2017----CVPR2017 oral----Realtime Multi-Person 2D Pose Estimation usingPart Affinity Fields
2017----Learning Feature Pyramids for Human Pose Estimation
2017----Multi-Context_Attention_for_Human_Pose_Estimation
2017----Self Adversarial Training for Human Pose Estimation
四、Multi-PersonPose estimation
2016----AssociativeEmbedding_End-to-End Learning for Joint Detection and Grouping
2016----DeepCut----Joint Subset Partition and Labeling for Multi PersonPose Estimation
2016----DeepCut----Joint Subset Partition and Labeling for Multi PersonPose Estimation_poster
2016----DeeperCut----DeeperCut A Deeper, Stronger, and Faster Multi-PersonPose Estimation Model
2017----G-RMI----Towards Accurate Multi-person Pose Estimation in the Wild
2017----RMPE_ Regional Multi-PersonPose Estimation
这篇是上海交大卢策吾教授项目组的论文,基于Top-Down Approaches。
论文的Motivation就是解决定位误差和定位框冗余检测这两个问题。引入Google提出的Spatial
Transformer Networks,可以使得传统的卷积带有了裁剪、平移、缩放、旋转等特性。
论文中一个实验:Upper Bound of Our Framework,就是论文直接使用ground truth的人体边
界框,在验证数据集取得84.2 mAP成绩,说明算法不仅需要提供人体边界框,第二阶段的单人姿态估计性能也需要提高。
脑洞:可以参考MSRA的deformable convolutional network,应该有新的paper。
2017----COCO2017 Keypointswinner----Cascaded Pyramid Network for Multi-Person Pose Estimation
2017----PyraNet----Learning Feature Pyramids for Human Pose Estimation