利用双级随机森林分类器的行人快速检测方法  

A fast pedestrian detection method using two-level random forest classifier

作　　者：山笑珂 张炳林[2] SHAN Xiaoke;ZHANG Binglin(School of Cultural Heritage,Zhengzhou University of Technology,Zhengzhou 450054,China;School of Education,Henan University,Kaifeng 475004,China)

机构地区：[1]郑州工程技术学院文化遗产学院,河南郑州450044 [2]河南大学教育科学学院,河南开封475004

出　　处：《光学技术》2020年第6期741-749,共9页Optical Technique

基　　金：河南省科技厅科技攻关计划项目(182102210229);2018年度河南省教师教育课程改革项目(2018-JSJYYB-008);2019年度中原工学院信息商务学院科研项目(ky1915);2019年度重点科研项目(jg1903)。

摘　　要：近年来,深度学习算法发展迅速,并广泛应用于目标检测的任务。然而,在内存和计算能力等条件受限制的设备上,无法进行实时性的目标检测。针对这一问题,提出了一种在内存和处理单元受限的监视系统中检测行人的快速方法。针对一般行人检测中提取高维度行人特征导致检测效率低的问题,将改进的方向梯度直方图(HOG)和Sobel边缘图像局部二元模式算法(Sobel-LBP)进行融合作为特征,提出基于教师-学生框架的模型压缩技术,将其应用于随机森林(RF)分类器,不使用深度网络,因为经过压缩的深度网络仍然需要大量的内存用于处理参数乘法运算。通过使用教师随机森林(T-RF)输出的soft target来训练学生浅层随机森林(S-RF),也称再生随机森林(BARF),让其模仿T-RF的表现;通过BARF分类器进行行人检测,最后使用滑动窗口法检测出行人。实验证明,与T-RF相比,提出方法的速度提高了2.05倍,压缩率提高了5.39倍,并且其检测性能也较为理想。In recent years, deep learning algorithm develops rapidly and is widely used in the task of target detection. However, real-time target detection cannot be carried out on devices with limited memory and computing power. To solve this problem, a fast pedestrian detection method is proposed in the surveillance system with limited memory and processing unit. Firstly, aiming at the problem of low detection efficiency caused by extracting high-dimensional pedestrian features in general pedestrian detection, an improved directional gradient histogram(HOG) and Sobel edge local binary pattern(Sobel LBP) are fused as features. Secondly, a model compression technique based on teacher-student framework is proposed, which is applied to random forest(RF) classifier without deep network, because the compressed deep network still needs a lot of memory to process parameter multiplication. Students’ random forest(S-RF)(born again random forest, BARF) is trained to imitate the performance of teachers’ random forest by using the soft target of teachers’ random forest output. Then the pedestrian detection is carried out by BARF classifier, and finally the pedestrian detection is carried out by sliding window method. In experiments, the proposed method achieved up to a 2.05 times faster speed and a 5.39 times higher compression rate than T-RF and its detection performance is also ideal.

关 键 词：信息光学 行人检测 视频监视 师生框架 模型压缩 双级随机森林 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]