期刊文献+

基于Anchor上下文辅助的教室场景人群计数研究 被引量:1

Research on Crowd Counting in Classroom Scene Based on Anchor Context Aid
下载PDF
导出
摘要 通过人脸检测的方式实现人群计数统计,采用了基于Anchor上下文辅助的目标检测算法。针对特定的教室场景收集了大量的课堂图像信息样本,并予以标记,以扩展Wider Face数据集。经多次训练,不断调整参数,最终获得最佳教室人脸检测模型。通过实际教室人数统计实验,检测出教室人脸数,进而得到教室人数状态信息。结果验证了该算法用于教室场景人群计数的可行性和有效性。 Crowd statistics are achieved through face detection,and an Anchor context-assisted target detection algorithm is adopted.Then,a large number of classroom image information samples are collected for specific classroom scenes and labeled to expand the Wider Face data set.Through multiple training and constant adjustment of parameters,the best classroom face detection model is obtained.Through the actual classroom number statistics experiment,the number of faces in the classroom is detected,and then the classroom number status information is obtained.The results show that the algorithm is feasible and effective for classroom scene crowd counting.
作者 雷亮 李小兵 和圆圆 尹衍伟 龚宇 LEI Liang;LI Xiaobing;HE Yuanyuan;YIN Yanwei;GONG Yu(School of Intelligent Technology and Engineering,Chongqing University of Science and Technology,Chongqing 400000,China)
出处 《重庆科技学院学报(自然科学版)》 CAS 2021年第4期84-88,共5页 Journal of Chongqing University of Science and Technology:Natural Sciences Edition
基金 重庆市自然科学基金项目“基于石墨烯和量子点的直读式红外探测机理研究”(CSTC2018JCYJAX0519) 重庆市教学改革重大项目“人工智能移动实验室及交互式案例建设与实践”(201016) 重庆市研究生创新训练项目“基于视觉SLAM的智能轮椅室内自主导航研究”(YKJCX1920805) 重庆科技学院研究生创新训练项目“基于PyramidBox的课堂抬头率研究”(YKJCX1920812),“基于深度学习视觉SLAM的视障人士智能眼镜研究”(YKJCX1920815) 重庆市研究生科研创新项目“具有面部运动控制和视觉SLAM环境感知的智能轮椅研发”(CYS20364)。
关键词 ANCHOR 人群计数 目标检测 数据扩充 anchor crowd counting target detection data expansion
  • 相关文献

参考文献6

二级参考文献59

  • 1Haritaoglu I, Harwood D, Davis L. W4: Real-time Surveillance of People and Their Activities[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2000, 22(8): 809-830.
  • 2Haritaoglu I, Flickner M. Detection and Tracking of Shopping Groups in Stores[C]//Proc. of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Kauai, HI, USA: IEEE Computer Society, 2001.
  • 3Lu Wenmiao, Tan Yap-peng. A Color Histogram Based People Tracking System[C]//Proc. of IEEE International Symposium on Circuits and Systems. Sydney, Australia: [s. n.], 2001.
  • 4Yu S ST Chen X P,Sun W P, et al. A robust method fordetecting and counting people [C] //Proceedings ofInternational Conference on Audio, Language and Image. LosAlamitos: IEEE Computer Society Press,2008: 1545-1549.
  • 5Chan A B, Liang Z S J, Vasconcelos N. Privacy preservingcrowd monitoring: counting people without people models ortracking [C] //Proceedings of IEEE Conference on ComputerVision and Pattern Recognition. Los Alamitos : IEEEComputer Society Press, 2008: 1-7.
  • 6Ge W N, Collins R T. Marked point processes for crowdcounting [C] //Proceedings of IEEE Conference on ComputerVision and Pattern Recognition. Los Alamitos: IEEEComputer Society Press,2009 : 2913-2920.
  • 7Kong D,Gray D,Hai T. A viewpoint invariant approach forcrowd counting [C] //Proceedings of the 18th InternationalConference on Pattern Recognition. Los Alamitos: IEEEComputer Society Press, 2006 : 1187-1190.
  • 8Albiol A, Silla M J, Albiol A, et al. Video analysis usingcorner motion statistics [C] //Proceedings of the IEEEInternational Workshop on Performance Evaluation ofTracking and Surveillance. Los Alamitos: IEEE ComputerSociety Press, 2009 : 31—38.
  • 9Conte D, Foggia P? Percannella G,et al. Counting movingpeople in videos by salient points detection [C] //Proceedingsof the 20th International Conference on Pattern Recognition.Los Alamitos: IEEE Computer Society Press, 2010 : 1743 -1746.
  • 10Tekalp M A. Digital video processing [M]. Upper SaddleRiver: Prentice Hall, 1995.

共引文献61

同被引文献1

引证文献1

二级引证文献2

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部