A Heterogeneous System for Real-Time Detection with AdaBoost
Zheng Xu, Runbin Shi, Zhihao Sun, Yaqi Li, Yuanjia Zhao, Chenjian Wu · 2016
AdaBoost algorithm based on Haar-like features can achieves high accuracy (above 95%) in object detection. Meanwhile massive computing power is needed to implement the cascaded classifiers involved in AdaBoost detection. To solve this problem, several dedicated hardware solutions have been proposed for real-time applications. In this work, a novel heterogeneous architecture of an AdaBoost detector is presented. This architecture achieves higher performance while consuming fewer hardware resources. By combining an integrated ARM Cortex-A9 processor with a dedicated accelerator, this architecture can be configured to realize various objects detection by simply loading different parameters. 2-D parallelism is involved in accelerator unit combination which brings more flexibility. This scheme is implemented on Xilinx ZC702 platform, the experiment result shows that 40 QVGA frames per second can be achieved for real-time face detection. The accelerator achieves more than 13 times improvement over the OpenCV implementation on a standalone Cortex-A9 w.r.t execution speed. Meanwhile, the accelerator consumes 40% less FPGA hardware resources than the prior-art implementation.