基于级联网络的行人检测方法  

Pedestrian detection method based on cascade networks

作　　者：陈光喜[1] 王佳鑫 黄勇[2] 詹益俊 詹宝莹 CHEN Guangxi;WANG Jiaxin;HUANG Yong;ZHAN Yijun;ZHAN Baoying(Guangxi Key Laboratory of Intelligent Processing of Computer Images and Graphics (Guilin University of Electronic Technology),Guilin Guangxi 541004,China;Guangdong Engineering Technology Research Center for Mathematical Educational Software (Guangzhou University),Guangzhou Guangdong 510006,China)

机构地区：[1]广西图像图形智能处理重点实验室(桂林电子科技大学),广西桂林541004 [2]广东省数学教育软件工程技术研究中心(广州大学),广州510006

出　　处：《计算机应用》2019年第1期186-191,共6页journal of Computer Applications

基　　金：国家自然科学基金资助项目(61462018);广东省数学教育软件工程技术研究中心开放基金资助项目(LD16124X);桂林电子科技大学研究生教育创新项目(2016XWYJ09)~~

摘　　要：针对复杂环境下行人检测不能同时满足高召回率与高效率检测的问题,提出一种基于卷积神经网络(CNN)的行人检测方法。首先,采用CNN中的单步检测升级版网络YOLOv2初步检测行人;然后,设计一个网络与YOLOv2网络级联。设计的网络具有目标分类和边界框回归的功能,对YOLOv2初步检测出的行人位置进行再分类与回归,以此降低误检,提高召回率;最后,采用非极大值抑制(NMS)处理的方法去除冗余的边界框。实验结果显示,在数据集INRIA和Caltech上,所提方法与原始YOLOv2相比,召回率提高3. 3个百分点,准确率提高5. 1个百分点,同时速度上达到了11. 6帧/s,实现了实时检测。与现有的流行的行人检测方法相比,所提方法具有更好的整体性能。In complex environment, existing pedestrian detection methods can not be very good to achieve high recall rate and efficient detection. To solve this problem, a pedestrian detection method based on Convolutional Neural Network( CNN)was proposed. Firstly, pedestrian locations in input images were initially detected with single step detection upgrade network( YOLOv2) derived from CNN. Secondly, a network with target classification and bounding box regression was designed to cascade with YOLOv2 network, which made reclassification and regression of pedestrian location initially detected by YOLOv2, to reduce error detections and increase recall rate. Finally, a Non-Maximum Suppression( NMS) method was used to remove redundant bounding boxes. The experimental results show that, in INRIA and Caltech dataset, the proposed method increases recall rate by 3. 3 percentage points, and the accuracy is increased by 5. 1 percentage points compared with original YOLOv2. It also reached a speed of 11. 6FPS( Frames Per Second) to realize real-time detection. Compared with the existing six popular pedestrian detection methods, the proposed method has better overall performance.

关 键 词：行人检测 卷积神经网络 级联网络 分类回归 实时检测 

分 类 号：TP391.413[自动化与计算机技术—计算机应用技术] TP18[自动化与计算机技术—计算机科学与技术]