没有合适的资源?快使用搜索试试~ 我知道了~
资源推荐
资源详情
资源评论
基于深度学习的着装表演机器人研究及设计
II
估计出人体的 2D 姿态,然后通过推理,在 2D 姿态的基础上获得 3D
人体骨骼序列。在第一阶段,本文采用自上而下的思路,将服装检测
部分的服装定位信息扩展为人体检测的定位信息。使用空间变换网络
对检测部分进行仿射,使目标人体姿态中心与图像中心重合。然后采
用当前效果最好的单人姿态估计网络 HRnet 识别 2D 人体姿态。在 第
二阶段,采用时域空洞卷积网络从 2D 人体姿态推理出 3D 骨架序列。
为了解决现有 3D 人体姿态数据集不足的问题,本文引入了半监督的
训练方法,实现了高精度、长时间、稳定的 3D 人体骨骼序列提取。
(3)动作模仿和服装模仿在动画表演机器人系统中的验证:该
部分将前两个部分的研究成果相结合应用到表演机器人当中。首先采
用 Marvelous Designer 软件为表演机器人制作服装并将其放入服装库,
然后根据服装检测部分获取的演示者服装类别为表演机器人从服装
库中挑选服装,最后将人体姿态估计部分提取到的 3D 人体骨骼序列
转为表演机器人可读取的欧拉角序列,以一定数据格式传递给机器人,
最终实现了表演机器人的同类别服装更换以及动作模仿。本文通过大
量实验证明了本文方法的有效性,并通过和其他方法对比展示了本文
方法的优越性。
关键词:深度学习,服装检测,3D 姿态估计,表演机器人
万方数据
基于深度学习的着装表演机器人研究及设计
III
RESEARCH AND DESIGN OF PERFORMANCE ROBOT WITH
DRESS BASED ON DEEP LEARNING
ABSTRACT
In recent years, with the huge success of deep learning in many fields, robot researchers tend
to combine deep learning with robot research in order to give robots more capabilities of
perceptions and analysis. More and more robots leave the laboratories and factories to go into
people's daily lives.
Among these robots, the performance robot can "autonomously" perform and interact with
people for serving human. And the quality of performance service depends largely on the quality
of the 3D bone driving sequence. However, the existing acquisition of 3D bone sequences mainly
depends on the 3D human motion capture equipments or motion designers. These methods are
costly, making the research of intelligent performance robots relatively difficult. What’s more,
most of the existing work about performance robots ignore the effects of clothing on robots. In
order to solve the problems above, this thesis researches and designs the dressing categories and
acquisition methods of 3D bone sequence of performing robots based on deep learning. The
research work in this thesis is divided into the following three parts:
(1) Clothing detection and classification for performance robots: This section mainly detects
and classifies the clothing of the presenters in the scene, so that the robot can choose the
corresponding clothing type according to the detection results. And then this thesis’ target tracking
the clothing on presenters in videos, which is helpful for human pose estimation later. This thesis
made a dataset for the clothing detection task, and then improved the target detection network
YOLO v3 according to the application scenario and the characteristics of the dataset. In the later
work, this thesis changed the multi-scale process, introduced down sampling and pruned the net so
that the improved network will be used in this thesis’ task with a better performance.
(2) 3D bone sequence acquisition: This part consists of two stages. The 2D pose of the human
body is estimated from the scene videos, and then the 3D human bone sequence is obtained based
on the 2D pose through inference. In the first stage, this thesis used a top-down approach. First,
expand the clothing positioning information of the clothing detection part into the positioning
information of human body detection. Then, the spatial transformation network is used to affine
万方数据
基于深度学习的着装表演机器人研究及设计
IV
the detection part so that the center of the pose of the target human body coincides with the center
of the image. In addition, HRnet the current best single-person pose estimation network was used
to estimate 2D human poses. In the second stage, this thesis deduced 3D skeleton sequence from
2D human pose by a temporal convolutional network. In order to solve the problem of insufficient
3D human pose dataset, a semi-supervised training method is introduced in this thesis. In a result,
a high-precision, long-term, and stable 3D human skeleton sequence can be extracted.
(3) The verification of action imitation and costume imitation in the robot system of
animation:This section combines the research results of the first two parts and applies these to the
performance robot. First, this thesis use Marvelous Designer to make clothing and put them into
the clothing base for the performance robot. Then, select the clothing for the performing robot
based on the clothing category from the clothing detection section. In addition, 3D human bone
sequence was extracted by the human pose estimation part, and the bone sequence was
transformed into a Euler angle sequence that can be read by the performance robot, and passed to
the robot in a certain data format. Eventually, the same-type clothing replacement and action
simulation of the performing robot were realized. A large number of experiments have proved the
effectiveness of this thesis’ methods, and the superiority of this method is demonstrated by
comparison with other methods.
Liu Ruyue(Control science and Engineering)
Supervised by Wang Zhijie
KEY WORDS: deep learning, clothing detection, 3D pose estimation, performance robot
万方数据
基于深度学习的着装表演机器人研究及设计
V
目录
摘 要.............................................................................................................................. I
ABSTRACT ................................................................................................................. III
第 1 章 绪论 .............................................................................................................. 1
1.1 表演机器人的研究背景和意义....................................................................... 1
1.2 表演机器人的国内外研究现状....................................................................... 2
1.2.1 国外研究现状......................................................................................... 2
1.2.2 国内研究现状......................................................................................... 3
1.3 论文主要内容................................................................................................... 4
1.4 论文结构安排................................................................................................... 5
第 2 章 表演机器人的功能要求分析 ...................................................................... 7
2.1 系统功能要求分析........................................................................................... 7
2.2 表演机器人系统设计中的关键技术............................................................... 8
2.3 本章小结......................................................................................................... 10
第 3 章 基于 YOLO V3 的服装检测 ...................................................................... 11
3.1 引言................................................................................................................ 11
3.2 YOLO v3 实现原理 ....................................................................................... 12
3.3 YOLO v3 网络改进 ....................................................................................... 17
3.3.1 基于 K-means 的先验框优化 ............................................................. 18
3.3.2 多尺度优化.......................................................................................... 19
3.3.3 基于下采样的并行网络优化.............................................................. 20
3.3.4 模型剪枝.............................................................................................. 21
3.4 实验结果及分析............................................................................................ 23
3.4.1 实验平台.............................................................................................. 23
3.4.2 实验数据集.......................................................................................... 23
3.4.3 数据预处理.......................................................................................... 23
3.4.4 评价指标.............................................................................................. 24
3.4.5 结果分析.............................................................................................. 25
3.5 本章小结........................................................................................................ 27
第 4 章 人体姿态估计 ............................................................................................ 28
4.1 引言................................................................................................................ 28
4.2 2D 人体姿态估计 ........................................................................................... 30
4.2.1 AlphaPose 实现原理 ............................................................................ 32
4.2.2 基于 AlphaPose 框架的 2D 人体姿态估计 ....................................... 32
4.2.3 实验及结果分析.................................................................................. 34
4.3 3D 骨骼序列获取 ........................................................................................... 41
4.3.1 时域空洞卷积实现原理...................................................................... 42
4.3.2 基于时域空洞卷积的 3D 骨骼序列获取 ........................................... 44
4.4 本章小结........................................................................................................ 47
第 5 章 着装表演机器人关键技术的验证 ............................................................ 48
万方数据
基于深度学习的着装表演机器人研究及设计
VI
5.1 引言................................................................................................................ 48
5.2 表演机器人服装库制作与动作数据转换.................................................... 48
5.2.1 表演机器人服装库制作...................................................................... 48
5.2.2 表演机器人动作数据转换.................................................................. 50
5.3 表演机器人关键技术验证............................................................................ 51
5.4 本章小结........................................................................................................ 55
第 6 章 总结与展望 ................................................................................................ 56
6.1 总结................................................................................................................ 56
6.2 展望................................................................................................................ 57
参考文献...................................................................................................................... 58
攻读学位期间的研究成果目录.................................................................................. 64
致谢.............................................................................................................................. 65
万方数据
剩余66页未读,继续阅读
资源评论
programhh
- 粉丝: 8
- 资源: 3742
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
- nyakumi-lewd-snack-3-4k_720p.7z.002
- 现在微信小程序能用的mqtt.min.js
- 基于MPC的非线性摆锤系统轨迹跟踪控制matlab仿真,包括程序中文注释,仿真操作步骤
- 基于MATLAB的ITS信道模型数值模拟仿真,包括程序中文注释,仿真操作步骤
- 基于Java、JavaScript、CSS的电子产品商城设计与实现源码
- 基于Vue 2的zjc项目设计源码,适用于赶项目需求
- 基于跨语言统一的C++头文件设计源码开发方案
- 基于MindSpore 1.3的T-GCNTemporal Graph Convolutional Network设计源码
- 基于Java的贝塞尔曲线绘制酷炫轮廓背景设计源码
- 基于Vue框架的Oracle数据库实训大作业设计与实现源码
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