文献类型：期刊文献

中文题名：迭代Faster R-CNN的密集行人检测

英文题名：Dense Pedestrian Detection with Iterative Faster R-CNN

作者：贺宇哲[1];徐光美[2];何宁[2];于海港[1];张人[1];晏康[2]

第一作者：贺宇哲

机构：[1]北京联合大学北京市信息服务工程重点实验室,北京100101;[2]北京联合大学智慧城市学院,北京100101

第一机构：北京联合大学北京市信息服务工程重点实验室

年份：2023

卷号：59

期号：21

起止页码：214-221

中文期刊名：计算机工程与应用

外文期刊名：Computer Engineering and Applications

收录：CSTPCD;;EI(收录号：20241215791459);北大核心:【北大核心2020】；CSCD:【CSCD_E2023_2024】；

基金：国家自然科学基金(61872042,62172045);北京市教委科技计划重点项目(KZ201911417048);北京联合大学人才强校优选计划(BPHR2020AZ01,BPHR2020EZ01);国家重点研发计划(2018AAA0100804)。

语种：中文

中文关键词：行人检测;密集场景;遮挡问题;Faster R-CNN;迭代方案

外文关键词：pedestrian detection;dense scenes;occlusion problem;Faster R-CNN;iterative scheme

摘要：行人检测是利用计算机视觉技术判断图像或者视频序列中是否存在行人并给予精确定位。针对行人检测在密集场景下普遍存在的行人间遮挡问题,提出基于迭代Faster R-CNN的密集行人检测模型,利用一种IterDet迭代方案对Faster R-CNN进行改进,有效解决非极大值抑制(NMS)算法及其改进在选择精确度和召回率之间平衡点的难题。同时利用递归金字塔结构(RFP)进一步增强模型提取特征能力。在具有挑战性的WiderPerson和CrowdHuman数据集上进行训练和验证,实验结果表明,该模型相比Faster R-CNN在精度和召回率显著提升的同时,漏检率也明显降低。尤其在WiderPerson数据集上召回率、精度、漏检率等性能指标分别达到了97.65%、91.29%、40.43%的SOTA结果。
Pedestrian detection uses computer vision technology to determine whether there are pedestrians in the image or video sequence and give accurate positioning.In this paper,a dense pedestrian detection model based on iterative Faster R-CNN is proposed to solve the common pedestrian occlusion problem in dense scenes.An IterDet iteration scheme is used to improve Faster R-CNN,which effectively solves the problem of choosing a balance between precision and recall for the NMS and its improvement.At the same time,the recursive pyramid structure is used to further enhance the feature extraction ability of the model.This paper trains and validates on the challenging WiderPerson and Crowd-Human datasets.The experimental results show that compared with Faster R-CNN,the model in this paper significantly improves the precision and recall,but also significantly reduces the mMR.Especially on the WiderPerson dataset,the recall,precision,and mMR has reached SOTA results of 97.65%,91.29%,and 40.43%,respectively.