首页|基于混合注意力机制与C2f的行人检测算法研究

基于混合注意力机制与C2f的行人检测算法研究

扫码查看
原文链接
  • 国家科技期刊平台
  • NETL
  • NSTL
  • 万方数据
  • 维普
针对行人检测算法对于小目标行人尺度小和密集行人出现漏检、误检等问题,基于YoloX算法提出一种混合注意力机制和C2f模块的行人检测算法.首先,将BAM模块与C2f模块进行融合,有效地增强了行人特征,减少了计算量,提升了检测速度;其次,采用注意力机制引导网络关注行人目标,使行人目标的特征信息得到进一步加强.在Crowd Human数据集上进行了实验分析,当IoU阈值设置为0.5时,小尺度行人检测精度为21.1%,中尺度行人检测精度为47.3%,大尺度行人检测精度为64.7%,全部的行人目标检测精度为73.2%,检测速度为24.3帧/s.实验结果表明,所提出的行人检测算法有效地提高了行人目标检测精度和检测速度,具有较好的检测性能.
Research on Pedestrian Detection Algorithm Based on Mixed Attention Mechanism and C2f
Aiming at the problems of missing detection and false detection of small target pedestrians with small scale and dense pedestrians,this paper proposes a pedestrian detection algorithm with mixed attention mechanism and C2f module based on YoloX algorithm.In this algo-rithm,firstly,the BAM module and the C2f module are fused to effectively enhance the characteristics of pedestrians,reduce the amount of calculation,and improve the detection speed.Secondly,the attention mechanism is used to guide the network to pay attention to pedestrian tar-gets,and the characteristic information of pedestrian targets has been further strengthened.Finally,experimental analysis is carried out on the Crowd Human dataset,when the IoU threshold is set to 0.5,the small-scale pedestrian detection accuracy is 21.1%,the mesoscale pedestrian detection accuracy is 47.3%,the large-scale pedestrian detection accuracy is 64.7%,the total pedestrian target detection accuracy is 73.2%,and the detection speed is 24.3 frames per second.Experimental results show that the pedestrian detection algorithm in this paper effectively improves the detection accuracy and detection speed of pedestrian targets,and has good detection performance for pedestrian targets.

pedestrian detectionfeature enhancementYoloXdeep learningattention mechanisms

王志新、王如刚、王媛媛、周锋、郭乃宏

展开 >

盐城工学院 信息工程学院,江苏 盐城 224051

盐城雄鹰精密机械有限公司,江苏 盐城 224006

行人检测 特征增强 YoloX 深度学习 注意力机制

国家自然科学基金江苏省研究生实践创新计划江苏省研究生实践创新计划江苏省高等学校自然科学研究重大项目江苏省高等学校自然科学研究面上项目江苏省高等学校自然科学研究面上项目江苏省自然科学基金

61673108SJCX22_1685SJCX21_151719KJA11000218KJD51001019KJB510061BK20181050

2024

10.11907/rjdk.231683

软件导刊
湖北省信息学会

软件导刊

影响因子：0.524
ISSN：1672-7800
年,卷(期)：2024.23(1)
  • 10