摘要
针对无人驾驶场景下行人多尺度、小尺度造成漏检率升高,检测精度下降的问题,本文提出一种融合深浅层特征和级联动态选择机制的行人检测方法。首先,在YOLO v3-tiny的基础上基于密集连接的卷积神经网络改进特征提取部分,融合行人的深层特征和浅层特征加强网络对行人的识别能力;其次,在改进的主干网络上级联具有动态选择机制的注意力模块,使检测网络更加适应动态的行人尺度变化;最后,本文选择BDD 100K数据集和Caltech加州理工学院行人数据集进行实验,在保证实时性的前提下(25 ms/张),本文模型在BDD 100K数据集行人漏检率降低11.4%,平均检测精度提高11.7%,在Caltech行人漏检率降低10.1%,平均检测精度提高6.7%,适用于无人驾驶行人检测领域。
Aiming at the problem that the multi-scale and small-scale of pedestrians in unmanned scenario causes the increase of missed detection rate and the decrease of detection accuracy,this paper proposes a pedestrian detection method that fuses deep and shallow layer features and cascade dynamic selection mechanism.Firstly,on the basis of YOLO v3-tiny,we improve the feature extraction part based on the densely connected convolutional neural network,and fuse the deep and shallow features of pedestrians to enhance the network’s ability to recognize pedestrians.Secondly,we cascade the attention module with dynamic selection mechanism on the improved backbone network to make the detection network more adaptable to dynamic pedestrian scale changes.Finally,we choose the BDD 100K dataset and the Caltech pedestrian dataset to conduct experiments.Under the premise of real-time performance(25 ms/sheet),the missed detection rate of pedestrian is reduced by 11.4%and the average detection accuracy is improved by 11.7%in the BDD 100K dataset,and the missed detection rate of pedestrian is reduced by 10.1%and the average detection accuracy is improved by 6.7%in the Caltech dataset,which is suitable for unmanned pedestrian detection.
作者
沙梦洲
沈韬
曾凯
马倩
曾文健
SHA Mengzhou;SHEN Tao;ZENG Kai;MA Qian;ZENG Wenjian(Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650500,China;Yunnan Key Laboratory of Computer Technologies Application,Kunming University of Science and Technology,Kunming 650500,China)
出处
《数据采集与处理》
CSCD
北大核心
2023年第1期162-173,共12页
Journal of Data Acquisition and Processing
基金
国家自然科学基金(61971208)
云南省中青年学术技术带头人后备人才基金(沈韬,2019HB005)
云南省万人计划青年拔尖人才基金(沈韬,朱艳,云南省人社厅201873)
云南省重大科技专项基金(202002AB080001-8)。
关键词
无人驾驶
小尺度
行人检测
密集连接
动态选择机制
driverless
small scale
pedestrian detection
dense connectivity
dynamic selection mechanisms
