Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields ∗
来源:互联网 发布:工艺软件有什么 编辑:程序博客网 时间:2024/06/06 00:58
- 只找一个limb,即只考虑a single pair of parts j1 and j2, 此时对应到:带权重二分图的匹配问题,权重就是积分出来的E,目标就是找到累积权重最大的匹配
- When it comes to finding the full body pose of multiple
people, determining Z is a K-dimensional matching problem.
This problem is NP Hard [32] and many relaxations
exist. In this work, we add two relaxations to the optimization,
specialized to our domain. First, we choose a minimal
number of edges to obtain a spanning tree skeleton of human
pose rather than using the complete graph, as shown in
Fig. 6c. Second, we further decompose the matching problem
into a set of bipartite matching subproblems and determine
the matching in adjacent tree nodes independently,
as shown in Fig. 6d. - Our optimization scheme over
the tree structure is orders of magnitude faster than the optimization
over the fully connected graph 效率提高了几个数量级 - PCKh: 各个part落在groundtruth附近,若在head size之内,认为检测出了。PCK的阈值是max(height,width) of body 的0.1 or 0.2倍。同时还可以分析PCKh-0.5等等精度的准确率
- mAP
- OKS: object keypoint similarity: It is calculated from scale of the person and the
distance between predicted points and GT points. - It is noteworthy
that our method has lower accuracy than the top-down
methods on people of smaller scales (APM). The reason is
that our method has to deal with a much larger scale range
spanned by all people in the image in one shot. In contrast,
top-down methods can rescale the patch of each detected
area to a larger size and thus suffer less degradation
at smaller scales. - If we use the GT bounding box and a single
person CPM [31], we can achieve a upper-bound for
the top-down approach using CPM, which is 62.7% AP.
If we use the state-of-the-art object detector, Single Shot
MultiBox Detector (SSD)[16], the performance drops 10%.
This comparison indicates the performance of top-down approaches
rely heavily on the person detector就是说自顶向下的方法每次都处理一个人,需要有个bounding box把人框出来(1. person detection 2. CPM或其他单人姿态检测算法),然后对框出来的单个人图像进行尺度调整,到一个合适的图像大小,再进行处理。当bounding box精度不够时,自顶向下的方法误差会很高。 9.
阅读全文
0 0
- Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields ∗
- Code note: Realtime Multi-person 2D Pose estimation using Part Affinity Fields(2)
- READING NOTE: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
- 行人姿态估计--Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
- caffe openpose/Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields配置
- 姿态估计论文思路整理 -- Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
- 论文阅读-Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
- Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields.md
- 论文阅读:《Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields》CVPR 2017
- Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields 个人解读
- Paper Reading:Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
- 姿态论文整理--02-Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
- Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields ∗ 实时多人人体姿态估计论文原理讲解
- Paper Reading:Regional Multi-person Pose Estimation
- 论文阅读:《RMPE: Regional Multi-Person Pose Estimation》ICCV 2017
- 姿态检查整理--07-RMPE: Regional Multi-Person Pose Estimation
- DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation
- READING NOTE: Towards Accurate Multi-person Pose Estimation in the Wild
- 30 Three.js的相机飞行控件FlyControls
- HDU2614 DFS
- ZOJ
- LintCode-----36.翻转链表 II
- ansible
- Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields ∗
- 前端学习之路-看到的优秀文章
- C++ 观察者模式 (包含模板)
- MAC显示屏的网页图片兼容方案
- SPOJ
- CodeForce 687A 二分图 交叉染色
- ubantu16.04lts 创建python虚拟环境
- iOS UIScrollview 和侧滑手势冲突解决方法
- python库大全