计算机工程与应用2019，Vol.55Issue(22)：91-98,162,9.DOI:10.3778/j.issn.1002-8331.1902-0004
基于候选区域和并行卷积神经网络的行人检测
Pedestrian Detection Based on Candidate Regions and Parallel Convolutional Neural Network
摘要
Abstract
Aiming at the problems that the percentage of pedestrians in some natural scenes is small(hereinafter referred to as small target), the extracted features are easily lost, and the detection accuracy is low, a pedestrian detection method based on candidate regions and Parallel Convolutional Neural Network(PCNN)is proposed. First, for the candidate region extraction section, selective search is improved to make it more suitable for pedestrians in this category of candidate region extraction. Then, Edge Boxes are used to filter a large number of pre-candidate regions extracted by selective search. Finally, a small number of high-quality candidate regions are obtained. When using Convolutional Neural Network(CNN)to extract features, deeper convolutional neural networks can extract richer and more abstract high-level features, but at the same time, the small objects can easily cause feature loss, adding shallow convolutional neural network to build a parallel con-volutional neural network to extract deep and shallow feature outputs. Finally, the proposed method is applied to pedestrian detection. The experimental results show that the proposed method can improve the detection accuracy of small target.关键词
卷积神经网络(CNN)/行人检测/选择性搜索/Edge Boxes/特征提取Key words
Convolutional Neural Network(CNN)/pedestrian detection/selective search/Edge Boxes/feature extraction分类
信息技术与安全科学引用本文复制引用
徐喆,王玉辉..基于候选区域和并行卷积神经网络的行人检测[J].计算机工程与应用,2019,55(22):91-98,162,9.基金项目
科学技术部国家重点研发计划(No.2018YFC1900801,No.11041001201801) （No.2018YFC1900801,No.11041001201801）
国家自然科学基金(No.61873009) （No.61873009）
北京市自然科学基金(No.4192009). （No.4192009）
