A flexible, high performance hardware implementation of the simplified histogram of oriented gradients descriptor

• Autorzy: Kraft M. , Olejniczak M. , Fularz M.
• Języki publikacji: EN

Abstrakty

EN

In this paper, a high performance, configurable, compact hardware architecture for computing the histogram of oriented gradients (HoG) descriptors is presented. The descriptor computation algorithm is simplified w.r.t. to the original solution, enabling hardware resource cost reduction with only a small accuracy penalty. The proposed architecture can be accommodated to different block sizes and different block grid configurations, enabling its use in a wide range of object detection and recognition tasks with varying region of interest sizes. The resulting architecture is systolic and massively parallel, enabling high throughput processing.

Słowa kluczowe

EN

HoG; FPGA; image processing

• Wydawca: Wydawnictwo PAK
• Czasopismo: Measurement Automation Monitoring
• Rocznik: 2017
• Tom: Vol. 63, No. 5
• Strony: 177--179
• Opis fizyczny: Bibliogr. 6 poz., rys., tab.

Twórcy

autor

Kraft M.

• Poznan University of Technology, Faculty of Electrical Engineering, Institute of Control and Information Engineering 3a Piotrowo St., 60-965 Poznan, Poland

autor

Olejniczak M.

• Poznan University of Technology, Faculty of Electrical Engineering, Institute of Control and Information Engineering 3a Piotrowo St., 60-965 Poznan, Poland

autor

Fularz M.

• Poznan University of Technology, Faculty of Electrical Engineering, Institute of Control and Information Engineering 3a Piotrowo St., 60-965 Poznan, Poland

Bibliografia

• [1] Dalal N., & Triggs B.: Histograms of oriented gradients for human detection. In Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on (Vol. 1, pp. 886-893). IEEE, June 2005.
• [2] Komorkiewicz M., Kluczewski M., & Gorgon M.: Floating point HOG implementation for real-time multiple object detection. In Field Programmable Logic and Applications (FPL), 2012, Aug., 22nd International Conference on (pp. 711-714). IEEE.
• [3] Chen P. Y., Huang C. C., Lien C. Y., & Tsai Y. H.: An efficient hardware implementation of HOG feature extraction for human detection. IEEE Transactions on Intelligent Transportation Systems, 15(2), 656-662, 2014.
• [4] Suleiman A., & Sze V.: An Energy-Efficient Hardware Implementation of HOG-Based Object Detection at 1080HD 60 fps with Multi-Scale Support. Journal of Signal Processing Systems, 84(3), 325-337, 2016.
• [5] Gajski Daniel D.: Principles of digital design. Prentice Hall (1997).
• [6] Kim, S., & Cho, K.: Fast Calculation of Histogram of Oriented Gradient Feature by Removing Redundancy in Overlapping Block. J. Inf. Sci. Eng., 2014, 30(6), 1719-1731.

Uwagi

PL

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę (zadania 2017).