现代电子技术2024，Vol.47Issue(15)：40-46,7.DOI:10.16652/j.issn.1004-373x.2024.15.007
一种面向鱼眼图像的行人检测算法
A pedestrian detection algorithm for fisheye images
摘要
Abstract
The nonlinear optical distortion of the fisheye lens leads to low accuracy of pedestrian detection algorithms for fisheye images,and the correction algorithm fails to fully overcome the severe edge deformation of fisheye images.Therefore,a fisheye image correction optical path model is established based on the Faster R-CNN architecture.A fisheye image correction model based on differential equations is proposed to address the distortion of fisheye images,and an improved algorithm is pro-posed for pedestrian detection of fisheye images.A ResNet 50 fusion feature pyramid network structure is constructed to enhance the multi-scale feature extraction ability of the network and improve its localization and recognition ability for pedestrians(small objects).The smooth L1 loss function is optimized to eliminate the imbalance between difficult-to-learn samples with large gra-dients and easy-to-learn samples with small gradients,so as to improve training effectiveness.The experimental results show that the detection accuracy of the proposed algorithm is improved by 39.68%,and its detection accuracy of slight edge distortion and small-scale pedestrians can reach over 90%in comparison with the existing fisheye image pedestrian detection algorithms.There-fore,it is helpful to improve the pedestrian detection performance for fisheye images under extreme conditions.关键词
鱼眼镜头/鱼眼图像/畸变校正/行人检测/Faster R-CNN/ResNet 50Key words
fisheye lens/fisheye image/distortion correction/pedestrian detection/Faster R-CNN/ResNet 50分类
电子信息工程引用本文复制引用
张瑶,刘发炳,黄国勇,钱俊兵,阮爱国,沈忠明..一种面向鱼眼图像的行人检测算法[J].现代电子技术,2024,47(15):40-46,7.基金项目
国家自然科学基金项目(62363018) （62363018）
教育部科技发展中心产学研创新基金资助课题(2021JQR023) （2021JQR023）
教育部产学研合作教育项目基金(220602518-231116) （220602518-231116）
航天科工深圳(集团)有限公司委托项目(KG-CX-FK-20230714002) （集团）
