https://scholars.lib.ntu.edu.tw/handle/123456789/338033
標題: | Video super-resolution by integrating SAD and NCC matching criterion for multiple moving objects | 作者: | Chi-Nan Hsieh Huang, Y.-P. Chen, Y.-Y. Fuh, C.-S. Ho, W.-J. CHIOU-SHANN FUH |
關鍵字: | Block matching; Image enlargement; K-means clustering; Motion estimation; Super-resolution | 公開日期: | 2008 | 起(迄)頁: | 172-177 | 來源出版物: | 10th IASTED International Conference on Computer Graphics and Imaging | 摘要: | Traditionally, image enlargement is magnified from a single image. Due to the one and only one image, the quality of the reconstructed image is thus constrained. Super-resolution is proposed to use multiple frames as additional information to estimate the high-resolution image. If we have enough low-resolution images with observed subpixels, the high-resolution image can be reconstructed. In this paper, a complete super-resolution model based on k-means motion clustering is proposed for image enlargement with multiple moving objects. Motion masks are first produced for useful image selection and then blocks matching are used to do motion estimation. Two complementary features, sum of absolute difference (SAD) and normalized cross-correlation (NCC), are adopted as the matching criterion. Objects are assumed to move slightly between two consecutive images. Thus, erroneous motion vectors could be corrected by the center of motion clusters. The proposed method achieves better magnification quality than the traditional ones and some previous super resolution works. From the experimental results, both the visual and quantitative improvements, especially in the high frequency, are significant. |
URI: | http://www.scopus.com/inward/record.url?eid=2-s2.0-62949094099&partnerID=MN8TOARS http://scholars.lib.ntu.edu.tw/handle/123456789/338033 |
SDG/關鍵字: | Block matching; Complementary features; Consecutive images; High frequencies; High-resolution images; Image enlargement; Image selections; K-Means; K-means clustering; Low-resolution images; Matching criterions; Motion vectors; Multiple frames; Multiple moving objects; Normalized cross correlations; Reconstructed images; Single images; Sub-pixels; Sum of absolute differences; Super-resolution; Super-resolution models; Video super resolutions; Color image processing; Computer graphics; Estimation; Face recognition; Motion compensation; Optical resolving power; Water supply systems; Motion estimation |
顯示於: | 資訊工程學系 |
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。