CN104899921B - 基于多模态自编码模型的单视角视频人体姿态恢复方法 - Google Patents
基于多模态自编码模型的单视角视频人体姿态恢复方法 Download PDFInfo
- Publication number
- CN104899921B CN104899921B CN201510305802.8A CN201510305802A CN104899921B CN 104899921 B CN104899921 B CN 104899921B CN 201510305802 A CN201510305802 A CN 201510305802A CN 104899921 B CN104899921 B CN 104899921B
- Authority
- CN
- China
- Prior art keywords
- image
- dimensional
- matrix
- model
- low
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 239000011159 matrix material Substances 0.000 claims abstract description 62
- 230000000007 visual effect Effects 0.000 claims abstract description 29
- 238000013507 mapping Methods 0.000 claims abstract description 17
- 238000003062 neural network model Methods 0.000 claims abstract description 16
- 238000011084 recovery Methods 0.000 claims abstract description 14
- 230000006870 function Effects 0.000 claims description 39
- 230000008569 process Effects 0.000 claims description 11
- 238000005516 engineering process Methods 0.000 claims description 10
- 238000000354 decomposition reaction Methods 0.000 claims description 8
- 238000005457 optimization Methods 0.000 claims description 6
- 235000009508 confectionery Nutrition 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000000844 transformation Methods 0.000 claims description 3
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 claims description 2
- 230000007935 neutral effect Effects 0.000 abstract 1
- 230000008447 perception Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000002922 simulated annealing Methods 0.000 description 1
- 239000000725 suspension Substances 0.000 description 1
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
Description
Claims (6)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510305802.8A CN104899921B (zh) | 2015-06-04 | 2015-06-04 | 基于多模态自编码模型的单视角视频人体姿态恢复方法 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510305802.8A CN104899921B (zh) | 2015-06-04 | 2015-06-04 | 基于多模态自编码模型的单视角视频人体姿态恢复方法 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104899921A CN104899921A (zh) | 2015-09-09 |
CN104899921B true CN104899921B (zh) | 2017-12-22 |
Family
ID=54032564
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510305802.8A Active CN104899921B (zh) | 2015-06-04 | 2015-06-04 | 基于多模态自编码模型的单视角视频人体姿态恢复方法 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104899921B (zh) |
Families Citing this family (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105740906B (zh) * | 2016-01-29 | 2019-04-02 | 中国科学院重庆绿色智能技术研究院 | 一种基于深度学习的车辆多属性联合分析方法 |
US9971958B2 (en) * | 2016-06-01 | 2018-05-15 | Mitsubishi Electric Research Laboratories, Inc. | Method and system for generating multimodal digital images |
KR102239746B1 (ko) * | 2016-10-10 | 2021-04-12 | 선전 쾅-츠 허종 테크놀로지 엘티디. | 전방 후방 평활 디코딩 방법, 장치 및 시스템 |
CN107808144A (zh) * | 2017-11-10 | 2018-03-16 | 深圳市唯特视科技有限公司 | 一种基于视频时空关系进行自我监督嵌入姿态学习方法 |
CN108846343B (zh) * | 2018-06-05 | 2022-05-13 | 北京邮电大学 | 基于三维视频的多任务协同分析方法 |
CN109166103B (zh) * | 2018-07-27 | 2021-02-05 | 中国科学院自动化研究所 | 基于多层感知网络的激发荧光断层成像方法 |
CN109215780B (zh) * | 2018-08-24 | 2022-05-31 | 齐鲁工业大学 | 高拉普拉斯正则化低秩表示的多模态数据分析方法及*** |
CN112001437B (zh) * | 2020-08-19 | 2022-06-14 | 四川大学 | 面向模态非完全对齐的数据聚类方法 |
CN112446310A (zh) * | 2020-11-19 | 2021-03-05 | 杭州趣链科技有限公司 | 基于区块链的年龄识别***、方法及装置 |
CN112668501A (zh) * | 2020-12-30 | 2021-04-16 | 杭州趣链科技有限公司 | 基于区块链激励的自动编码器特征提取方法与装置 |
CN113129267A (zh) * | 2021-03-22 | 2021-07-16 | 杭州电子科技大学 | 一种基于视网膜分层数据的oct图像检测方法及*** |
CN113408703B (zh) * | 2021-06-29 | 2022-01-28 | 中国科学院自动化研究所 | 基于神经与符号的多模态大数据机器自动学习*** |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004227287A (ja) * | 2003-01-23 | 2004-08-12 | Zumen Soft Inc | 三次元cadデータ作成システム及び三次元cadデータの作成方法 |
CN1567385A (zh) * | 2003-06-19 | 2005-01-19 | 邓兴峰 | 平面图像全景重建立体图像的方法 |
CN1920886A (zh) * | 2006-09-14 | 2007-02-28 | 浙江大学 | 基于视频流的三维动态人脸表情建模方法 |
CN101021900A (zh) * | 2007-03-15 | 2007-08-22 | 上海交通大学 | 利用降维方法进行人脸姿态估计的方法 |
CN101246602A (zh) * | 2008-02-04 | 2008-08-20 | 东华大学 | 基于几何骨架的人体姿态重建方法 |
CN101714262A (zh) * | 2009-12-10 | 2010-05-26 | 北京大学 | 单幅图像的三维场景重建方法 |
CN102054291A (zh) * | 2009-11-04 | 2011-05-11 | 厦门市美亚柏科信息股份有限公司 | 一种基于单幅人脸图像实现三维人脸重建的方法及其装置 |
-
2015
- 2015-06-04 CN CN201510305802.8A patent/CN104899921B/zh active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004227287A (ja) * | 2003-01-23 | 2004-08-12 | Zumen Soft Inc | 三次元cadデータ作成システム及び三次元cadデータの作成方法 |
CN1567385A (zh) * | 2003-06-19 | 2005-01-19 | 邓兴峰 | 平面图像全景重建立体图像的方法 |
CN1920886A (zh) * | 2006-09-14 | 2007-02-28 | 浙江大学 | 基于视频流的三维动态人脸表情建模方法 |
CN101021900A (zh) * | 2007-03-15 | 2007-08-22 | 上海交通大学 | 利用降维方法进行人脸姿态估计的方法 |
CN101246602A (zh) * | 2008-02-04 | 2008-08-20 | 东华大学 | 基于几何骨架的人体姿态重建方法 |
CN102054291A (zh) * | 2009-11-04 | 2011-05-11 | 厦门市美亚柏科信息股份有限公司 | 一种基于单幅人脸图像实现三维人脸重建的方法及其装置 |
CN101714262A (zh) * | 2009-12-10 | 2010-05-26 | 北京大学 | 单幅图像的三维场景重建方法 |
Also Published As
Publication number | Publication date |
---|---|
CN104899921A (zh) | 2015-09-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104899921B (zh) | 基于多模态自编码模型的单视角视频人体姿态恢复方法 | |
CN108921893B (zh) | 一种基于在线深度学习slam的图像云计算方法及*** | |
CN111080511B (zh) | 一种端到端的高分辨率多特征提取的人脸交换方法 | |
CN111275518B (zh) | 一种基于混合光流的视频虚拟试穿方法及装置 | |
CN110728219B (zh) | 基于多列多尺度图卷积神经网络的3d人脸生成方法 | |
WO2017163759A1 (en) | System and computer-implemented method for semantic segmentation of image, and non-transitory computer-readable medium | |
CN111814719A (zh) | 一种基于3d时空图卷积的骨架行为识别方法 | |
CN110503680A (zh) | 一种基于非监督的卷积神经网络单目场景深度估计方法 | |
CN108710906B (zh) | 基于轻量级网络LightPointNet的实时点云模型分类方法 | |
CN111783582A (zh) | 一种基于深度学习的无监督单目深度估计算法 | |
Jiang et al. | Learning a referenceless stereopair quality engine with deep nonnegativity constrained sparse autoencoder | |
CN114581560A (zh) | 基于注意力机制的多尺度神经网络红外图像彩色化方法 | |
CN108171279A (zh) | 一种多视角视频自适应乘积Grassmann流形子空间聚类方法 | |
CN110059593B (zh) | 一种基于反馈卷积神经网络的面部表情识别方法 | |
CN112686830B (zh) | 基于图像分解的单一深度图的超分辨率方法 | |
CN113128424A (zh) | 基于注意力机制的图卷积神经网络动作识别方法 | |
CN112101262A (zh) | 一种多特征融合手语识别方法及网络模型 | |
CN111125403A (zh) | 一种基于人工智能的辅助设计绘图方法及*** | |
CN115936992A (zh) | 一种轻量级Transformer的垃圾图像超分辨方法及*** | |
CN116524121A (zh) | 一种单目视频三维人体重建方法、***、设备及介质 | |
CN116309774A (zh) | 一种基于事件相机的密集三维重建方法 | |
CN113192186B (zh) | 基于单帧图像的3d人体姿态估计模型建立方法及其应用 | |
CN115049739A (zh) | 一种基于边缘检测的双目视觉立体匹配方法 | |
Basak et al. | Monocular depth estimation using encoder-decoder architecture and transfer learning from single RGB image | |
CN111027433A (zh) | 一种基于卷积神经网络的多重风格人脸特征点检测方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right |
Effective date of registration: 20191016 Address after: 310000 23 / F, Shimao center, 857 Xincheng Road, Binjiang District, Hangzhou City, Zhejiang Province Patentee after: Hangzhou Yuanchuan New Technology Co.,Ltd. Address before: Hangzhou City, Zhejiang province 310018 Xiasha Higher Education Park No. 2 street Patentee before: HANGZHOU DIANZI University |
|
TR01 | Transfer of patent right | ||
CP03 | Change of name, title or address |
Address after: Room 23011, Yuejiang commercial center, No. 857, Xincheng Road, Puyan street, Binjiang District, Hangzhou, Zhejiang 311611 Patentee after: Hangzhou Yuanchuan Xinye Technology Co.,Ltd. Address before: 310000 floor 23, Shimao center, No. 857, Xincheng Road, Binjiang District, Hangzhou City, Zhejiang Province Patentee before: Hangzhou Yuanchuan New Technology Co.,Ltd. |
|
CP03 | Change of name, title or address | ||
PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A Method for Human Posture Restoration in Single View Video Based on Multimodal Self coding Model Effective date of registration: 20230509 Granted publication date: 20171222 Pledgee: China Everbright Bank Limited by Share Ltd. Hangzhou branch Pledgor: Hangzhou Yuanchuan Xinye Technology Co.,Ltd. Registration number: Y2023980040155 |
|
PE01 | Entry into force of the registration of the contract for pledge of patent right |