基于多任务分类的吸烟行为检测

程淑红; 马晓菲; 张仕军; 张丽

doi:10.3969/j.issn.1000-1158.2020.05.05

PDF(1757 KB)

计量学报 ›› 2020, Vol. 41 ›› Issue (5) : 538-543. DOI: 10.3969/j.issn.1000-1158.2020.05.05

光学计量

基于多任务分类的吸烟行为检测

程淑红¹,马晓菲¹,张仕军¹,张丽²

作者信息 +

Smoking Detection Algorithm Based on Multitask Classification

CHENG Shu-hong¹,MA Xiao-fei¹,ZHANG Shi-jun¹,ZHANG Li²

Author information +

文章历史 +

摘要

为了及时检测吸烟行为,准确做出状态判断,提出了一种基于多任务分类的吸烟行为检测算法。该算法融合多任务卷积神经网络、级联回归和残差网络,通过多任务卷积神经网络算法和基于梯度提高学习的回归树方法(RET级联回归)快速定位嘴部感兴趣区域(ROI);在此基础上,采用残差网络对ROI内目标进行检测和状态识别。实验结果表明,该算法可以准确检测到吸烟行为的发生并做出状态判断,准确率可以达到87.5%。

Abstract

In order to detect the smoking behavior in time and accurately judge the state. A smoking behavior detection algorithm based multi-task classification was proposed. The algorithm integrates multi-task convolution neural network, ensemble of regression trees cascade regression and depth residual network, quickly and accurately locates the region of interest through multi-task convolutional neural network algorithm and ERT cascade regression. Based on this, detect targets in the region of interest and identify status using deep residual network. The experimental results showed that the algorithm can accurately detect the occurrence of smoking behavior and make state judgments, the accuracy rate can reach 87.5%.

导出引用

程淑红,马晓菲,张仕军,张丽. 基于多任务分类的吸烟行为检测[J]. 计量学报. 2020, 41(5): 538-543 https://doi.org/10.3969/j.issn.1000-1158.2020.05.05

CHENG Shu-hong,MA Xiao-fei,ZHANG Shi-jun,ZHANG Li. Smoking Detection Algorithm Based on Multitask Classification[J]. Acta Metrologica Sinica. 2020, 41(5): 538-543 https://doi.org/10.3969/j.issn.1000-1158.2020.05.05

中图分类号： TB96 TB973

参考文献

［1］中华人民共和国国家卫生和计划生育委员会. 公共场所控制吸烟条例(送审稿)［J］. 中国实用乡村医生杂志, 2015, (10): 3-5.
National Health and Family Planning Commission of PRC. Public Places Control of Smoking Regulations(Draft for Review) ［J］. Chinese Practical Journal Of Rural, 2015, (10): 3-5.
［2］潘广贞, 元琴, 樊彩霞,等. 基于混合高斯模型和帧差法的吸烟检测算法［J］. 计算机工程与设计, 2015, (5): 1290-1294.
Pan G Z, Yuan Q, Fan C X, et al. Cigarette-smoke detection based on Gaussian mixture model and frame difference［J］. Computer Engineering & Design, 2015, (5): 1290-1294.
［3］王超. 针对吸烟行为的手势识别算法研究［D］. 秦皇岛: 燕山大学, 2013.
［4］Tsai H C, Chuang C H, Tseng S P, et al. The optical flow-based analysis of human behavior-specific system［C］// IEEE. International Conference on Orange Technologies. 2013: 214-218.
［5］Zhang K, Zhang Z, Li Z, et al. Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks［J］. IEEE Signal Processing Letters, 2016, 23(10): 1499-1503.
［6］赵一中, 刘文波. 基于深度信念网络的非限制性人脸识别算法研究［J］. 计量学报, 2017, 38(1): 65-68.
Zhao Y Z, Liu W B. Research on Unconstrained Face Recognition Based on DBNs Network［J］. Acta Metrologica Sinica, 2017, 38(1): 65-68.
［7］程淑红, 刘洁. 基于MWF和GF的复杂光照下人脸识别研究［J］. 计量学报, 2017, 38(1): 60-64.
Cheng S H, Liu J. Face Recognition under Complex Illumination Based on Multi-scale Weberface and Gradientface［J］. Acta Metrologica Sinica, 2017, 38(1): 60-64.
［8］Zhou E, Fan H, Cao Z, et al. Extensive facial landmark localization with coarse-to-fine convolutional network cascade［C］// Proceedings of the IEEE International Conference on Computer Vision Workshops. 2013: 386-391.
［9］He K, Zhang X, Ren S, et al. Deep residual learning for image recognition［C］//Proceedings of the IEEE conference on computer vision and pattern recognition, 2016: 770-778.
［10］Brereton R G, Lloyd G R. Support vector machines for classification and regression［J］. Analyst, 2010, 135(2): 230.
［11］彭明超, 包姣, 叶茂,等. 基于形状参数回归的人脸对齐算法［J］. 模式识别与人工智能, 2016, 29(1): 63-71.
Peng M C, Bao J, Ye M, et al. Face Alignment Algorithm Based on Shape Parameter Regression［J］. Pattern Recognition & Artificial Intelligence, 2016, 29(1): 63-71.
［12］Lin M, Chen Q, Yan S. Network in network［C］//International Conference on Learning Representations. Banff, Canada, 2014.

［13］李彦冬, 郝宗波, 雷航. 卷积神经网络研究综述［J］. 计算机应用, 2016, 36(9): 2508-2515.
Li Y D, Hao Z B, Lei H. Survey of convolutional neural network［J］. Journal of Computer Applications, 2016, 36(9): 2508-2515.
［14］Powers D M W. Evaluation: from precision, recall and f-measure to ROC, informedness, markedness and correlation［J］. Journal of Machine Learning Technologies, 2011, 2(1): 37-63.
［15］王金甲,周雅倩,郝智. 基于注意力模型的多传感器人类活动识别［J］. 计量学报, 2019, 40(6): 958-969.
Wan J J, Zhou Y Q, Hao Z. Multi-sensor Human Activity Recognition Based on Attention Model［J］. Acta Metrologica Sinica, 2019, 40(6): 958-969.