Аlgorithm of fast computation of local image histograms on video card1
Abstract
An algorithm of parallel computation of image histograms of different types, including brightness and oriented gradient ones, on video cards of various types is presented. Now local histograms are used for solution of some tasks of image processing and recognition, but their application is restricted due to the long computational time. One of the difficulties appearing during parallel computations of this vector feature is the large number of conflicts of simultaneous access to video memory sells. In the developed version, the number of conflicts of simultaneous access are many times reduced. It accelerated the computations. For instance, 9D vectors of histograms of oriented gradient for all 256×256 windows of a HD image are calculated on the GPU NVIDIA GeForce GTX 1060 within 1,9 msec, whereas the same computations made by the CPU Intel Core i7-6700 take 151 msec.
About the Authors
Ph. S. Trotski
The United Institute of Informatics Problems of the National Academy of Sciences of Belarus, Minsk
Belarus
Junior Researcher
Belarus
Junior Researcher
B. A. Zalesky
The United Institute of Informatics Problems of the National Academy of Sciences of Belarus, Minsk
Belarus
Dr. Sc. (Phys.-Math.), Head of the Laboratory of Image Processing and Recognition
Belarus
Dr. Sc. (Phys.-Math.), Head of the Laboratory of Image Processing and Recognition
References
1. Gonzalez R., Woods R. Cifrovaya obrabotka izobrazhenij [Digital Image Processing]. Moscow, Tehnosfera, 2005, 1070 p.
2. Dalal N., Triggs B. Histograms of oriented gradients for human detection. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’2005). San Diego, 2005,
3. vol. 1, pp. 886–893.
4. Cheon M., Lee W., Hyun C.-H., Park M. Rotation invariant histogram of oriented gradients. International Journal of Fuzzy Logic and Intelligent Systems, 2011, vol. 11, no. 4, pp. 293–298.
5. Marimon D., Ebrahimi T. Orientation histogram-based matching for region tracking. Eighth International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS’07). Santorini, Greece, 2007, p. 8.
6. Ragb H., Asari V. Histogram of oriented phase and gradient (HOPG) descriptor for improved pedestrian detection. IS&T International Conference on Electronic Imaging: Video Surveillance and Transportation Imaging Applications. San Francisco, 2016.
7. Ragb H., Asari V. Histogram of oriented phase (HOP): a new descriptor based on phase congruency. Proceedings SPIE 9869, Mobile Multimedia/Image Processing, Security, and Applications. Bellingham, 2016,
8. vol. 98690. DOI: 10.1117/12.2225159
9. Chen J., Chen Z., Chi Z., Fu H. Facial expression recognition based on facial components detection and HOG features. Scientific Cooperations International Workshops on Electrical and Computer Engineering Subfields, 22–23 August 2014, Istanbul, Turkey. Istanbul, 2014, рр. 64–69.
10. Harris M. Using Shared Memory in CUDA C/C++. Available at: https://devblogs.nvidia.com/usingshared-memory-cuda-cc (accessed 26.09.2018).
11. Zalesky B. A., Trotski Ph. S. Parallelnaya versiya detektora ekstremalnyih osobyih tochek [Parallel version of detector of extremal key points]. Informatika [Informatics], 2018, vol. 15, no. 2, pp. 55–63 (in Russian).
12. Bulashev S. V. Statistika dlya treyderov. Statistics for traders. Moscow, Kompanija Sputnik+, 2003, 245 p. (in Russian).
13. Sanders D., Kendrot E. CUDA by Example: An Introduction to General-Purpose GPU Programming. Boston, Addison-Wesley Professional, 2010, 320 p.
Review
For citations:
Trotski P.S., Zalesky B.A. Аlgorithm of fast computation of local image histograms on video card1. Informatics. 2019;16(1):49-57. (In Russ.)
Views: 980
Email this article 