CN102903096B - 一种基于单目视频的对象深度提取方法 - Google Patents
一种基于单目视频的对象深度提取方法 Download PDFInfo
- Publication number
- CN102903096B CN102903096B CN201210230109.5A CN201210230109A CN102903096B CN 102903096 B CN102903096 B CN 102903096B CN 201210230109 A CN201210230109 A CN 201210230109A CN 102903096 B CN102903096 B CN 102903096B
- Authority
- CN
- China
- Prior art keywords
- depth
- pixel
- value
- depth map
- key frame
- 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
- 238000000605 extraction Methods 0.000 title abstract description 7
- 230000011218 segmentation Effects 0.000 claims abstract description 15
- 238000005457 optimization Methods 0.000 claims abstract description 14
- 238000000034 method Methods 0.000 claims description 32
- 238000012937 correction Methods 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 8
- 238000013519 translation Methods 0.000 claims description 4
- 238000009792 diffusion process Methods 0.000 abstract 1
- 230000006870 function Effects 0.000 description 15
- 230000008878 coupling Effects 0.000 description 7
- 238000010168 coupling process Methods 0.000 description 7
- 238000005859 coupling reaction Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000011084 recovery Methods 0.000 description 4
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000003706 image smoothing Methods 0.000 description 1
- 238000002715 modification method Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
Description
Claims (4)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210230109.5A CN102903096B (zh) | 2012-07-04 | 2012-07-04 | 一种基于单目视频的对象深度提取方法 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210230109.5A CN102903096B (zh) | 2012-07-04 | 2012-07-04 | 一种基于单目视频的对象深度提取方法 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102903096A CN102903096A (zh) | 2013-01-30 |
CN102903096B true CN102903096B (zh) | 2015-06-17 |
Family
ID=47575309
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210230109.5A Active CN102903096B (zh) | 2012-07-04 | 2012-07-04 | 一种基于单目视频的对象深度提取方法 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102903096B (zh) |
Families Citing this family (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2014183787A1 (en) * | 2013-05-14 | 2014-11-20 | Huawei Technologies Co., Ltd. | Method and apparatus for computing a synthesized picture |
CN103581651B (zh) * | 2013-10-28 | 2015-04-29 | 西安交通大学 | 一种用于车载多目摄像机环视系统的虚拟视点合成方法 |
CN103810708B (zh) * | 2014-02-13 | 2016-11-02 | 西安交通大学 | 一种激光散斑图像深度感知方法及装置 |
CN105204609B (zh) * | 2014-06-17 | 2018-01-26 | 立普思股份有限公司 | 深度摄影机系统 |
CN105184784B (zh) * | 2015-08-28 | 2018-01-16 | 西交利物浦大学 | 基于运动信息的单目相机获取深度信息的方法 |
CN107094260A (zh) * | 2016-02-17 | 2017-08-25 | 浙江大学 | 导出视差矢量和运动矢量的方法和装置 |
CN106530409B (zh) * | 2016-11-03 | 2019-08-27 | 浙江大学 | 立体匹配中局部区域一致性对应方法 |
CN107481279B (zh) * | 2017-05-18 | 2020-07-07 | 华中科技大学 | 一种单目视频深度图计算方法 |
CN108986155B (zh) * | 2017-06-05 | 2021-12-07 | 富士通株式会社 | 多视点图像的深度估计方法和深度估计设备 |
CN108780577A (zh) * | 2017-11-30 | 2018-11-09 | 深圳市大疆创新科技有限公司 | 图像处理方法和设备 |
CN108765479A (zh) * | 2018-04-04 | 2018-11-06 | 上海工程技术大学 | 利用深度学习对视频序列中单目视图深度估计优化方法 |
CN108961327B (zh) * | 2018-05-22 | 2021-03-30 | 深圳市商汤科技有限公司 | 一种单目深度估计方法及其装置、设备和存储介质 |
WO2020019175A1 (zh) * | 2018-07-24 | 2020-01-30 | 深圳市大疆创新科技有限公司 | 图像处理方法和设备、摄像装置以及无人机 |
CN109919985A (zh) * | 2019-03-01 | 2019-06-21 | 北京市商汤科技开发有限公司 | 数据处理方法和装置、电子设备和计算机存储介质 |
CN110163246B (zh) * | 2019-04-08 | 2021-03-30 | 杭州电子科技大学 | 基于卷积神经网络的单目光场图像无监督深度估计方法 |
CN110349197B (zh) * | 2019-07-03 | 2021-01-01 | 中山大学 | 一种白内障手术显微镜下单目深度估计方法 |
CN110517309A (zh) * | 2019-07-19 | 2019-11-29 | 沈阳工业大学 | 一种基于卷积神经网络的单目深度信息获取方法 |
CN110517304B (zh) * | 2019-07-26 | 2022-04-22 | 苏州浪潮智能科技有限公司 | 生成深度图的方法、装置、电子设备和存储介质 |
CN111179327B (zh) * | 2019-12-30 | 2023-04-25 | 青岛联合创智科技有限公司 | 一种深度图的计算方法 |
CN111292425B (zh) * | 2020-01-21 | 2022-02-01 | 武汉大学 | 一种基于单双目混合数据集的视图合成方法 |
CN111366917B (zh) * | 2020-03-13 | 2022-07-15 | 北京百度网讯科技有限公司 | 可行驶区域检测方法、装置、设备及计算机可读存储介质 |
CN114283089B (zh) * | 2021-12-24 | 2023-01-31 | 合肥的卢深视科技有限公司 | 基于跳跃加速的深度恢复方法、电子设备及存储介质 |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101945299A (zh) * | 2010-07-09 | 2011-01-12 | 清华大学 | 一种基于拍摄设备阵列的动态场景深度恢复方法 |
CN102074020A (zh) * | 2010-12-31 | 2011-05-25 | 浙江大学 | 对视频进行多体深度恢复和分割的方法 |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6847728B2 (en) * | 2002-12-09 | 2005-01-25 | Sarnoff Corporation | Dynamic depth recovery from multiple synchronized video streams |
US9123115B2 (en) * | 2010-11-23 | 2015-09-01 | Qualcomm Incorporated | Depth estimation based on global motion and optical flow |
-
2012
- 2012-07-04 CN CN201210230109.5A patent/CN102903096B/zh active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101945299A (zh) * | 2010-07-09 | 2011-01-12 | 清华大学 | 一种基于拍摄设备阵列的动态场景深度恢复方法 |
CN102074020A (zh) * | 2010-12-31 | 2011-05-25 | 浙江大学 | 对视频进行多体深度恢复和分割的方法 |
Non-Patent Citations (3)
Title |
---|
Extraction of the relative depth information of objects in video sequences;F.X.Martinez等;《1998 International Conference on Image Processing.ICIP 98》;19981007;第948-952页 * |
单目视频中深度图生成算法研究;张鹏;《中国优秀硕士学位论文全文数据库信息科技辑》;20101015(第10期);第21-55页 * |
新的单目立体视觉的视差图的获取方法;徐姝姝等;《计算机应用》;20110228;第31卷(第2期);第341-343、378页 * |
Also Published As
Publication number | Publication date |
---|---|
CN102903096A (zh) | 2013-01-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102903096B (zh) | 一种基于单目视频的对象深度提取方法 | |
CN111325794B (zh) | 一种基于深度卷积自编码器的视觉同时定位与地图构建方法 | |
CN102741884B (zh) | 移动体检测装置及移动体检测方法 | |
CN106920259B (zh) | 一种定位方法及系统 | |
Mehta et al. | Structured adversarial training for unsupervised monocular depth estimation | |
CN103002309B (zh) | 对于多目同步摄像机拍摄的动态场景视频的时空一致性深度恢复的方法 | |
CN101877143B (zh) | 一种二维图像组的三维场景重建方法 | |
CN101496413A (zh) | 用单视场低功率移动装置实时捕获及产生立体图像及视频 | |
CN103996201A (zh) | 一种基于改进梯度和自适应窗口的立体匹配方法 | |
CN103996202A (zh) | 一种基于混合匹配代价和自适应窗口的立体匹配方法 | |
Aleotti et al. | Learning end-to-end scene flow by distilling single tasks knowledge | |
CN110335222B (zh) | 基于神经网络的自修正弱监督双目视差提取方法及装置 | |
CN102074020A (zh) | 对视频进行多体深度恢复和分割的方法 | |
Garg et al. | Look no deeper: Recognizing places from opposing viewpoints under varying scene appearance using single-view depth estimation | |
CN110070574A (zh) | 一种基于改进PSMNet的双目视觉立体匹配算法 | |
KR20140074201A (ko) | 추적 장치 | |
CN103049929A (zh) | 基于联合优化的多摄像机动态场景3d重建方法 | |
KR101125061B1 (ko) | Ldi 기법 깊이맵을 참조한 2d 동영상의 3d 동영상 전환방법 | |
CN113705796B (zh) | 基于epi特征强化的光场深度获取卷积神经网络 | |
Jia et al. | Multi-scale cost volumes cascade network for stereo matching | |
CN102567992B (zh) | 遮挡区域的图像匹配方法 | |
Bhutani et al. | Unsupervised Depth and Confidence Prediction from Monocular Images using Bayesian Inference | |
CN103236057A (zh) | 一种改进的自适应权重视差匹配方法 | |
Ramenahalli et al. | Computing 3D saliency from a 2D image | |
CN109961092A (zh) | 一种基于视差锚点的双目视觉立体匹配方法及系统 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
DD01 | Delivery of document by public notice | ||
DD01 | Delivery of document by public notice |
Addressee: Beijing digital pixel Technology Co., Ltd. Document name: Notification that Application Deemed not to be Proposed |
|
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20180425 Address after: 100081 21 floor 2508-08, 1 building, No. 12 Zhongguancun South Street, Haidian District, Beijing. Patentee after: Beijing digital pixel Technology Co., Ltd. Address before: 100191 Xueyuan Road, Haidian District, Beijing, No. 37 Patentee before: Beihang University |
|
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20190509 Address after: 100193 No. 10 Wangdong Road, Northwest of Haidian District, Beijing, No. 2 Building, No. 3, 302 A5 Patentee after: Rongdian Network (Beijing) S & T, Inc. Address before: 100081 21 floor 2508-08, 1 building, No. 12 Zhongguancun South Street, Haidian District, Beijing. Patentee before: Beijing digital pixel Technology Co., Ltd. |
|
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20190702 Address after: 100081 21 floor 2508-08, 1 building, No. 12 Zhongguancun South Street, Haidian District, Beijing. Patentee after: Beijing digital pixel Technology Co., Ltd. Address before: 100193 No. 10 Wangdong Road, Northwest of Haidian District, Beijing, No. 2 Building, No. 3, 302 A5 Patentee before: Rongdian Network (Beijing) S & T, Inc. |
|
CP03 | Change of name, title or address | ||
CP03 | Change of name, title or address |
Address after: 100193 No. 3, Building No. 2, East Courtyard, No. 10 Wangdong Road, Haidian District, Beijing, 302A4 Patentee after: Beijing Fusion Future Technology Co., Ltd. Address before: 100081 Beijing Haidian District Zhongguancun South Street No. 12 Courtyard 1 Building 21 Floor 2508-08 Patentee before: Beijing digital pixel Technology Co., Ltd. |