HPM-TDP: An efficient hierarchical PatchMatch depth estimation approach using tree dynamic programming
文献类型：期刊论文
| 作者 | Tian, Mao3,4; Yang, Bisheng3,4; Chen, Chi3,4; Huang, Ronggang1; Huo, Liang2 |
| 刊名 | ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
 |
| 出版日期 | 2019-09-01 |
| 卷号 | 155页码:37-57 |
| 关键词 | Depth estimation Stereo matching Continuous energy optimization Tree dynamic programming (TDP) |
| ISSN号 | 0924-2716 |
| DOI | 10.1016/j.isprsjprs.2019.06.015 |
| 英文摘要 | Accurate and efficient estimation of the dense depth information from a pair of stereo images is a key step for many applications such as digital surface model production, 3D reconstruction and visualization, autonomous driving, and robotic navigation. Although great progress has been achieved in stereo matching over the past decade, the matching difficulties in poor and repetitive texture regions remain an issue. Aiming at solving the shortcomings of the current methods, this paper proposes HPM-TDP, which is an efficient hierarchical PatchMatch depth estimation approach that integrates a coarse-to-fine image pyramid strategy with a continuous Markov random field (MRF)-based global energy optimization framework, and minimizes the energy function by combining a hierarchical PatchMatch (HPM) framework and local a-expansion based tree dynamic programming (TDP). Firstly, the coarse-to-fine image pyramid strategy is integrated with the PatchMatch filter algorithm to quickly generate the hierarchical disparity plane prior for initializing each pixel's disparity plane of the energy function optimization. Secondly, a multi-resolution cost aggregation strategy is adopted to boost the robustness of the matching cost function in the poor and repetitive texture areas. Finally, the HPM framework and local alpha-expansion based TDP are adopted to solve the non-submodular energy optimization problem, resulting in a globally optimized disparity plane map. Three benchmark datasets the Middlebury 3.0, KITTI 2015, and Vaihingen datasets were used to test the performance of HPM-TDP. The comprehensive experimental results demonstrate that HPM-TDP obtains a good performance on all datasets in terms of the ("Out-Noc", "AvgNoc", "Out-All", "Avg-All") of (15.45%, 4.16px, 24.26%, 12.14px) and (5.46%, 1.20px, 6.55%, 1.54px) for Middlebury 3.0 and KITTI 2015 training datasets, and the ("Out-All", "Avg-All") of (26.32%, 4.04px) for Vaihingen dataset, respectively. |
| 资助项目 | National Science Fund for Distinguished Young Scholars of China[41725005] ; Key Program of the National Natural Science Foundation of China[41531177] ; National Natural Science Foundation of China[41701530] ; National Natural Science Foundation of China[41801398] ; China Postdoctoral Science Found[2018T110802] ; China Postdoctoral Science Found[2017M622553] ; Key Laboratory of Spatial Data Mining & Information Sharing of Ministry of Education, Fuzhou University[2018LSDMIS06] ; LIESMARS Special Research Funding of Ministry of Education, Fuzhou University[2018LSDMIS06] ; [UDC2018031321] |
| WOS研究方向 | Physical Geography ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology |
| 语种 | 英语 |
| WOS记录号 | WOS:000482526600004 |
| 出版者 | ELSEVIER |
| 源URL | [http://202.127.146.157/handle/2RYDP1HH/8612]  |
| 专题 | 中国科学院武汉植物园 |
| 通讯作者 | Yang, Bisheng; Chen, Chi |
| 作者单位 | 1.Chinese Acad Sci, Inst Geodesy & Geophys, State Key Lab Geodesy & Earths Dynam, Wuhan, Hubei, Peoples R China 2.Beijing Univ Civil Engn & Architecture, Beijing Adv Innovat Ctr Future Urban Design, Beijing, Peoples R China 3.Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & R, Wuhan 430079, Hubei, Peoples R China 4.Minist Educ PRC, Engn Res Ctr Space Time Data Capturing & Smart Ap, Wuhan, Hubei, Peoples R China |
| 推荐引用方式 GB/T 7714 | Tian, Mao,Yang, Bisheng,Chen, Chi,et al. HPM-TDP: An efficient hierarchical PatchMatch depth estimation approach using tree dynamic programming[J]. ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING,2019,155:37-57. |
| APA | Tian, Mao,Yang, Bisheng,Chen, Chi,Huang, Ronggang,&Huo, Liang.(2019).HPM-TDP: An efficient hierarchical PatchMatch depth estimation approach using tree dynamic programming.ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING,155,37-57. |
| MLA | Tian, Mao,et al."HPM-TDP: An efficient hierarchical PatchMatch depth estimation approach using tree dynamic programming".ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING 155(2019):37-57. |
入库方式： OAI收割
来源：武汉植物园
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。