https://scholars.lib.ntu.edu.tw/handle/123456789/607243
標題: | CMWMF: Constant Memory Architecture of Weighted Mode/Median Filter for Extremely Large Label Depth Refinement | 作者: | Wu S.-S Chen L.-G. LIANG-GEE CHEN |
關鍵字: | Depth enhancement;Memory efficiency;VLSI architecture design;Weight median filter;Weighted mode filter;Median filters;Memory architecture;Bilateral filters;Constant memory;Hardware architecture;Hardware implementations;Joint histograms;Proposed architectures;Search procedures;Static random access memory;Static random access storage | 公開日期: | 2021 | 卷: | 31 | 期: | 8 | 起(迄)頁: | 2981-2993 | 來源出版物: | IEEE Transactions on Circuits and Systems for Video Technology | 摘要: | In this study, we propose a constant memory hardware architecture that can support weighted mode, median, and joint bilateral filters, which is referred to as CMWMF. This work aims to meet the high memory and computation requirements of processing depth maps with a large number of depth candidates. In the proposed architecture, we leverage the geometry smoothing characteristic of natural images to reduce the static random access memory (SRAM) size for hardware implementation. The architecture preserves a constant number of disparity values instead of depending on the label count and size of the local supporting window. A novel weighted median search procedure is proposed, which assigns a computation to each input cycle, thereby rendering the process hardware friendly. An index-checking technique is proposed to process out-of-order joint histograms. We adopted the above-mentioned techniques in our architecture as they consume a constant SRAM size and supports multiple types of filters. As a result, this architecture reduces the SRAM size by 92.4% with a negligible decrease in performance. According to our analysis on the KITTI, and Middlebury datasets, and with actual depth cameras, the preserved information is sufficient. The proposed architecture is one of the most suitable depth refinement architectures for scenarios having a large number of depth candidates. ? 1991-2012 IEEE. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85112711187&doi=10.1109%2fTCSVT.2020.3035161&partnerID=40&md5=3c460d23b7081fff06b6a6e44cf75fff https://scholars.lib.ntu.edu.tw/handle/123456789/607243 |
ISSN: | 10518215 | DOI: | 10.1109/TCSVT.2020.3035161 |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。