pedestrain_detection:比较使用Faster RCNN和RPN + BF进行的脚步检测-源码

Comparing the differences between Faster RCNN and RPN+BF in pedestrain detection By zyq&cyq Introduction 行人检测具有极其广泛的应用：智能辅助驾驶，智能监控，行人分析以及智能机器人等领域。随着深度学习的性能的优越性，将深度学习的方法应用到行人中以提高检测准确率。本工程分别采用Faster R-CNN和RPN+BF网络，对Caltech数据集进行训练和测试，并比较两者的结果。 This code has been tested on Ubuntu 16.04 with MATLAB 2014b and CUDA 7.5. Citing RPN+BF @article{zhang2016faster, title={Is Faster R-CNN Doing Well for Pedes