基于全局注意力的室内人数统计模型

计算机工程与科学 ›› 2022, Vol. 44 ›› Issue (03): 471-478.

基于全局注意力的室内人数统计模型

李静1,2,何强1,2,张长伦1,2,3,王恒友1,2

(1.北京建筑大学理学院,北京 100044;2.北京建筑大学大数据建模理论与技术研究所,北京 100044;
3.北京建筑大学北京未来城市设计高精尖创新中心,北京 100044)

收稿日期:2021-09-18 修回日期:2021-12-08 接受日期:2022-03-25 出版日期:2022-03-25 发布日期:2022-03-24
基金资助:
国家自然科学基金(62072024，61473111)；北京建筑大学科学研究基金(KYJJ2017017,Y19-19,Y18-11)；住房和城乡建设部科学技术计划北京建筑大学北京未来城市设计高精尖创新中心开放课题（UDC2019033324,UDC201703332)；河北省机器学习与计算智能重点实验室资助课题（2019-2021-A）

An indoor people counting model based on global attention

LI Jing1,2,HE Qiang1,2,ZHANG Chang-lun1,2,3,WANG Heng-you1,2

(1.School of Science,Beijing University of Civil Engineering and Architecture,Beijing 100044;
2.Institute of Big Data Modeling Theory and Technology,
Beijing University of Civil Engineering and Architecture,Beijing 100044;
3.Beijing Advanced Innovation Center for Future Urban Design,
Beijing University of Civil Engineering and Architecture,Beijing 100044,China)

Received:2021-09-18 Revised:2021-12-08 Accepted:2022-03-25 Online:2022-03-25 Published:2022-03-24

摘要/Abstract

摘要： 随着人工智能技术的爆炸式发展，机器学习、深度学习等技术在人脸识别、行人检测和视频跟踪等各个领域得到了广泛的应用，其中利用目标检测进行室内人数统计一直以来是一个热门的研究。室内监控画面存在人群相互遮挡，且目标特征模糊等问题，往往导致检测准确率低，误检率和漏检率高等情况的出现。为了解决此问题，提出了一种基于全局注意力的室内人数统计模型，引入注意力机制，对目标检测算法YOLOv3进行改进，通过提取更多小人头或模糊人头的特征来增强检测能力。实验结果表明，改进后的网络模型具有更高的召回率和平均精度。

关键词: 目标检测, 人数统计, 注意力机制, YOLOv3

Abstract: With the explosive development of artificial intelligence technology, machine learning, deep learning and other technologies have been widely used in face recognition, pedestrian detection, video tracking and other fields. Among them, using target detection for indoor crowd statistics has attracted a lot of attentions. Due to the problems such as mutual occlusion of crowds and blurred target features in the indoor monitoring screen, it often leads to low detection accuracy and high false detection rate and missed detection rate. In order to solve this problem, an indoor people counting model based on global attention is proposed. The model introduces the attention mechanism, optimizes the object detection algorithm YOLOv3, and enhances the detection ability by extracting more features of small or unclear heads. The experimental results show that the improved network model has higher recall and average precision.

Key words: object detection, people counting, global attention, YOLOv3

李静, 何强, 张长伦, 王恒友, . 基于全局注意力的室内人数统计模型[J]. 计算机工程与科学, 2022, 44(03): 471-478.

LI Jing, HE Qiang, ZHANG Chang-lun, WANG Heng-you, . An indoor people counting model based on global attention[J]. Computer Engineering & Science, 2022, 44(03): 471-478.

参考文献［21］

［1］	LeCun Y.Bengio Y.Hinton G.Deep learning［J］.Nature,2015,521:436-444.
［2］	Zhang Rong, Li Wei-ping, Mo Tong. Review of deep learning［J］. Information and Control, 2018, 47(4):385-397. (in Chinese)
［3］	Girshick R,Donahue J,Darrell T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation［C］∥Proc of 2014 IEEE Conference on Computer Vision and Pattern Recognition,2014:580-587.
［4］	Li Lin-hui,Lun Zhi-mei,Lian Jing,et al.Convolution neural network-based vehicle detection method［J］.Journal of Jilin University(Engineering and Technology Edition),2017,47(2):384-391.(in Chinese)
［5］	Xiong Chang-zhen,Shan Yan-mei,Guo Fen-hong.Image retrieval method based on image principal part detection［J］.Optics and Precision Engineering,2017,25(3):792-798.(in Chinese)
［6］	Li Y,Qi H,Dai J,et al.Fully convolutional instane-aware semantic segmentation［C］∥Proc of 2017 IEEE Conference on Computer Vision and Pattern Recognition,2017:4438-4446.
［7］	Hua Xia, Wang Xin-qing, Wang Dong, et al. Multi-objective detection of traffic based on improved SSD［J］. Acta Optica,2018,38(12):221-231. (in Chinese)
［8］	Li Hang, Zhu Ming. A small object detection algorithm based on deep convolutional neural network［J］.Computer Engineering & Science,2020,42(4):649-657.(in Chinese)
［9］	Yi Shi,Li Xin-rong,Wu Zhi-juan,et al.Night hare detection method based on infrared thermal imaging and improved YOLO V3［J］.Transactions of the Chinese Society of Agricultural Engineering,2019,35(19):223-229.(in Chinese)
［10］	Redmon J,Divvala S,Girshick R,et al.You only look once:Unified,real-time object detection［C］∥Proc of 2016 IEEE Conference on Computer Vision and Pattern Recognition,2016:779-788.
［11］	Redmon J. Farhadi A.YOLO9000:Better,faster,stronger［C］∥Proc of 2017 IEEE Conference on Computer Vision and Pattern Recognition,2017:6517-6525.
［12］	Redmon J, Farhadi A.YOLOv3:An incremental improvement［J］.arXiv:1804.02767,2018.
［13］	Liu W,Anguelov D,Erhan D,et al.SSD:single shot multibox detector［C］∥Proc of European Conference on Computer Vision,2016:21-37.
［14］	Girshick R.Fast R-CNN ［C］∥Proc of 2015 IEEE International Conference on Computer Vision,2015:1440-1448.
［15］	He K M,Zhang X Y,Ren S Q.Spatial pyramid pooling in deep convolutional networks for visual recognition［J］.IEEE Transactions on Pattern Analysis & Machine Intelligence,2014,37(9):1904-1916.
［16］	Law H,Deng J.CornerNet:Detecting objects as paired key-points［C］∥Proc of European Conference on Computer Vision,2018:734-750.
［17］	Ren S Q,He K M,Girshick R,et al.Faster R-CNN:Towards real-time object detection with region proposal networks［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
［18］	He K M,Gkioxari G,Dollar P,et al.Mask R-CNN［C］∥Proc of 2017 IEEE International Conference on Computer Vision,2017:2980-2988.
［19］	Qian He-qing,Chen Gang,Shen Rui-min.Population statistics system based on face detection ［J］.Computer Engineering,2012,38(13):188-191.(in Chinese)
［20］	Chen Jiu-hong,Zhang Hai-yu.Design of classroom number counting system based on deep learning［J］.Software Guide,2019,18(10):27-29.(in Chinese)
［21］	Ju Mo-ran, Luo Hai-bo,et al.Improved YOLO V3 algorithm and its application in small target detection［J］.Acta Optica Sinica,2019,39(7):245-252.(in Chinese)
［22］	Hou Q, Zhou D,Feng J.Coordinate attention for efficient mobile network design［J］.arXiv:2103.02907, 2021.
［23］	He K M,Zhang X Y,Ren S Q,et al.Deep residual learning for image recognition［C］∥Proc of 2016 IEEE Conference on Computer Vision and Pattern Recognition,2016:770-778.
［24］	Krizhevsky A.Sutskever I.Hinton G E.ImageNet classification with deep convolutional neural networks［C］∥Proc of the 25th International Conference on Neural Information Processing Systems,2012:1097-1105.
［25］	Hu J,Shen L, Albanie S, et al. Squeeze-and-excitation networks［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020,42(8): 2011-2023.
［26］	Cao Y, Xu J R,Lin S, et al.GCNet:Non-local networks meet squeeze-excitation networks and beyond［J］.arXiv:1904.11492,2019.
	附中文参考文献:
［2］	张荣，李伟平，莫同. 深度学习研究综述［J］.信息与控制，2018, 47(4):385-397.
［4］	李琳辉，伦智梅，连静, 等. 基于卷积神经网络的道路车辆检测方法［J］.吉林大学学报（工学版），2017，47(2):384-391.
［5］	熊昌镇，单艳梅，郭芬红. 结合主体检测的图像检索方法［J］.光学精密工程，2017，25(3):792-798.
［7］	华夏, 王新晴, 王东, 等. 基于改进SSD的交通大场景多目标检测［J］.光学学报,2018, 38(12): 221-231.
［8］	李航，朱明.基于深度卷积神经网络的小目标检测算法［J］.计算机工程与科学,2020，42(4):649-657.
［9］	易诗，李欣荣，吴志娟，等.基于红外热成像与改进YOLO V3的夜间野兔检测方法［J］.农业工程学报，2019，35(19):223-229.
［19］	钱鹤庆,陈刚,申瑞民.基于人脸检测的人数统计系统［J］.计算机工程,2012,38(13):188-191.
［20］	陈久红，张海玉.基于深度学习的教室人数统计系统设计［J］.软件导刊，2019，18(10):27-29.
［21］	鞠默然，罗海波,王仲博，等.改进的YOLO V3算法及其在小目标检测中的应用［J］.光学学报，2019，39(7):245-252.

[1]	马思远, 焦佳辉, 任晟岐, 宋伟. 基于注意力机制的城市多元空气质量数据缺失值填充[J]. 计算机工程与科学, 2023, 45(08): 1354-1364.
[2]	尹春勇, 冯梦雪. 基于注意力机制的半监督日志异常检测方法[J]. 计算机工程与科学, 2023, 45(08): 1405-1415.
[3]	余子丞, 凌捷. 基于Transformer和多特征融合的DGA域名检测方法[J]. 计算机工程与科学, 2023, 45(08): 1416-1423.
[4]	唐剑, 车文刚, 高盛祥. 融入注意力机制的多尺度卷积图像去雾方法[J]. 计算机工程与科学, 2023, 45(08): 1453-1462.
[5]	吴栋梁, 刘知贵, . 基于轻量化YOLOX的电子元器件缺陷检测方法研究[J]. 计算机工程与科学, 2023, 45(08): 1463-1471.
[6]	刘浩翰, 孙铖, 贺怀清, 惠康华. 基于改进YOLOv3的金属表面缺陷检测[J]. 计算机工程与科学, 2023, 45(07): 1226-1235.
[7]	白杉, 冯秀芳. 基于注意力增强的中心差分自适应图卷积的骨架行为识别[J]. 计算机工程与科学, 2023, 45(07): 1263-1273.
[8]	王剑, 姜林, 王琳钦, 余正涛, 张松, 高盛祥, . 基于BiLSTM的低资源老挝语文本正则化任务[J]. 计算机工程与科学, 2023, 45(07): 1292-1299.
[9]	田秀霞, 刘正, 刘秋旭, 李浩然. 一种改进Faster R-CNN的图像篡改检测模型[J]. 计算机工程与科学, 2023, 45(06): 1030-1039.
[10]	李校林, 王复港, 张鹏飞, 张琳玉, . 基于多尺度特征提取的YOLOv5s算法优化[J]. 计算机工程与科学, 2023, 45(06): 1054-1062.
[11]	杨慧剑, 孟亮. 基于改进的YOLOv5的航拍图像中小目标检测算法[J]. 计算机工程与科学, 2023, 45(06): 1063-1070.
[12]	刘晓航, 姜晶菲, 许金伟. 基于脉动阵列的层融合注意力模型加速器结构[J]. 计算机工程与科学, 2023, 45(05): 802-809.
[13]	霍爱清, 张书涵, 杨玉艳, 胥静蓉, 王泽文. 密集交通场景中改进YOLOv3目标检测优化算法[J]. 计算机工程与科学, 2023, 45(05): 878-884.
[14]	排日旦·阿布都热依木, 吐尔地·托合提, 艾斯卡尔·艾木都拉, . 基于深度学习的实体关系抽取方法研究[J]. 计算机工程与科学, 2023, 45(05): 895-902.
[15]	赵乐乐, 张丽萍, 赵凤荣. 基于注意力机制的Tree2Seq代码注释自动生成[J]. 计算机工程与科学, 2023, 45(04): 638-645.