Implementation of AdaBoost Face Detection Using Vivado HLS
For the problem that Adaptive Boosting (AdaBoost) face detection algorithm is slowly implemented on the embedded platform by software, this paper adopts the method of the full hardware acceleration. The intellectual property (IP) core of AdaBoost algorithm is designed by Vivado high-level synthesis (HLS), which may reduce the development difficulty and shorten the development cycle. The design adopts the serial–parallel structure to accelerate face detection and uses several methods of optimizing hardware resource. The face detection algorithm is implemented on the Zedboard platform and achieves the purpose of real-time detection.
KeywordsAdaBoost Face detection HLS Real-time detection
- 1.Liang L, Ai H, Zhang B. A survey of human face detection. Chin J Comput. 2002;25(5):449–58.Google Scholar
- 2.Zhu M, Lu X, Lu H. Transplantation and optimization of AdaBoost face detection algorithm on DSP. Comput Eng Appl. 2014;50(20):197–201.Google Scholar
- 3.Zhang Z, Feng Z, Wei S. Implementation of face detection system based on AdaBoost algorithm on embedded system. Inf Technol. 2008;07:167–70.Google Scholar
- 4.Xilinx Inc. High-level-synthesis v17.1 [EB/OL]. URL https://www.xilinx.com/support/documentation/sw_manuals/xilinx2018_1/ug902-vivado-high-level-synthesis.pdf.
- 5.Viola P, Jones M. Rapid object detection using a boosted cascade of simple features. In: Computer society conference on computer vision and pattern recognitionl, vol. 1; 2001. p. I-511–8.Google Scholar
- 6.Acasandrei L, Barriga A. Accelerating Viola-Jones face detection for embedded and SoC environments. In: ACM/IEEE international conference on distributed smart cameras, Ghent; 2011. p. 1–6.Google Scholar