The correlation coefficient calculation is implemented not with built-in function corr or corr2 but with conv2. Function corr is relatively slow for template matching purpose and it is also required extra considerations on controlling the boundary and selecting region of interest on the frame image. However, by using conv2, the template matching speed has been accelerated and run-time has reduced to a reasonable value.
引用
Yue Wu (2024). Template Matching using Correlation Coefficients (https://www.mathworks.com/matlabcentral/fileexchange/28590-template-matching-using-correlation-coefficients), MATLAB Central File Exchange. 取得済み .
MATLAB リリースの互換性
作成:
R2009b
すべてのリリースと互換性あり
プラットフォームの互換性
Windows macOS Linuxカテゴリ
- Image Processing and Computer Vision > Computer Vision Toolbox > Tracking and Motion Estimation > Template Matching >
- Image Processing and Computer Vision > Image Processing Toolbox > Image Filtering and Enhancement > ROI-Based Processing >
Help Center および MATLAB Answers で Template Matching についてさらに検索
タグ
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!