Use of similarity metrics in template-based detection of objects in images

被引：0
作者：
Rubel O. [1 ]
Abramov S. [1 ]
Abramova V. [1 ]
Lukin V. [1 ]
机构：
[1] National Aerospace University, Kharkiv Aviation Institute, 17 Chkalov St., Kharkiv
来源：
Telecommunications and Radio Engineering (English translation of Elektrosvyaz and Radiotekhnika) | 2019年 / 78卷 / 14期
关键词：
Noise; Similarity metrics; Template-based detection;
D O I：
10.1615/TelecomRadEng.v78.i14.30
中图分类号：
学科分类号：
摘要：
A task of template-based detection of similar objects or blocks in images is considered. As a measure of similarity, different similarity metrics (distances) are studied under assumption that noise is present in images or video frames. It is shown that there are metrics that are able to perform sufficiently better than standard Euclidean norm in both spatial or transform domain, especially if noise is intensive and/or has certain degree of spatial correlation. Analysis is carried out for five test images and a wide set of noise variance values. Traditional and unconventional criteria of detection are applied. ©2019 by Begell House, Inc.
引用
收藏
页码：1249 / 1261
页数：12
相关论文
共 24 条
[1]  
Elad M., Sparse and redundant representations, From Theory to Applications in Signal and Image Processing, (2010)
[2]  
Buades A., Coll A., Morel J.M., A non-local algorithm for image denoising, Computer Vision and Pattern Recognition (CVPR) IEEE Computer Society Conference, 2, pp. 60-65, (2005)
[3]  
Lebrun M., Colom M., Buades A., Morel J.M., Secrets of image denoising cuisine, Acta Numerica, 21, pp. 475-576, (2012)
[4]  
Richardson I., H.264 and MPEG-4 Video Compression: Video Coding for Next-Generation Multimedia, (2003)
[5]  
Zhou W., Wang C., Xiao B., Zhang Z., SLD: A novel robust descriptor for image matching, IEEE Signal Processing Letters, 21, pp. 339-342, (2014)
[6]  
Song J., Liu L., Huang W., Li Y., Chen X., Zhang Z., Target detection via HSV color model and edge gradient information in infrared and visible image sequences under complicated background, Optical and 331 Quantum Electronics, 50, pp. 171-175, (2018)
[7]  
Li C., Hua T., Human action recognition based on template matching, Procedia Engineering, 15, pp. 2824-2830, (2011)
[8]  
Choi H., Park J.-M., Choi W.-S., Oh S.Y., Vision-based fusion of robust lane tracking and forward vehicle detection in a real driving environment, International Journal of Automotive Technology, 13, pp. 653-669, (2012)
[9]  
Dabov K., Image and Video Restoration with Nonlocal Transform-Domain Filtering: Thesis for the, (2010)
[10]  
Lukin V., Ponomarenko N., Egiazarian K., Astola J., Adaptive DCT-based filtering of images corrupted by spatially correlated noise, Proceedings of SPIE Image Processing: Algorithms and Systems VI, SPIE, 6812, (2008)
123