https://scholars.lib.ntu.edu.tw/handle/123456789/428579
標題: | GPU-accelerated high-resolution image stitching with better initial guess | 作者: | Lin, C.-H. Tsai, Y.M. WEICHUNG WANG LIANG-GEE CHEN |
關鍵字: | acceleration; CUDA; Image stitching; image warping; panorama | 公開日期: | 2018 | 卷: | 2018-January | 起(迄)頁: | 1 - 3 | 來源出版物: | 2018 IEEE International Conference on Consumer Electronics, ICCE 2018 | 會議論文: | 2018 IEEE International Conference on Consumer Electronics, ICCE 2018 | 摘要: | High-resolution image processing is crucial for emerging applications in virtual reality. The trade-off between robustness/accuracy and speed pose a challenge to high-resolution image stitching. This paper accelerates the state-of-the-art image stitching algorithm by using the CUDA toolkit. We also use the mesh coordinates as an initial guess for solving warping function for an additional increase in speed. Experimental results show that our implementation achieves comparable quality to the state-of-the-art work, while our implementation is almost 2x faster on high-resolution images (3264×2448). © 2018 IEEE. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/428579 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85048843646&doi=10.1109%2fICCE.2018.8326271&partnerID=40&md5=c90b95d6570c236b379a5abccbee0148 |
DOI: | 10.1109/ICCE.2018.8326271 | SDG/關鍵字: | Acceleration; Economic and social effects; Graphics processing unit; CUDA; Emerging applications; High resolution image; High-resolution image processing; Image stitching; Image warping; panorama; State of the art; Image processing |
顯示於: | 應用數學科學研究所 |
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。