关联规则对监控下行人属性识别影响的研究

doi:10.3969/j.issn.1006-2475.2019.04.012

计算机与现代化

关联规则对监控下行人属性识别影响的研究

（1.北京航天长峰科技工业集团有限公司，北京100039；2.中国航天科工二院，北京100039；
3.北京航天长峰股份有限公司，北京100039)

收稿日期:2018-09-26 出版日期:2019-04-26 发布日期:2019-04-30
作者简介:李雪(1993-)，女，陕西西安人，硕士研究生，研究方向：深度学习与图像识别，E-mail: chuncaicai@yeah.net；郭会明(1966-)，男，湖北天门人，研究员，硕士生导师，研究方向：计算机信息系统集成与应用。
基金资助:
国家重点研发计划资助项目（2018YFC0831500）

Research on Affection of Association Rules to Pedestrian #br# Attributes Recognition in Surveillance Video

(1. Changfeng Science Technology Industry Group Co., Ltd., Beijing 100039, China；
2. The Second Institute， China Aerospace Science & Industry Co., Ltd., Beijing 100039, China；
3. Beijing Aerospace Changfeng Co., Ltd., Beijing 100039, China)

Received:2018-09-26 Online:2019-04-26 Published:2019-04-30

摘要/Abstract

摘要： 针对监控视频下的行人多属性识别问题，提出一种结合神经网络与关联规则的多分类方法。首先通过Faster-RCNN检测算法与改进的AlexNet多分类网络得到监控视频下行人各个属性的置信度，再采用关联规则Apriori算法对训练数据进行处理，进而结合神经网络分类的置信度和关联规则的处理结果，提出一种对分类置信度进行优化的算法。最后，统计关联规则优化后的某些行人属性准确率。结果表明，将神经网络与关联规则有效结合后可以提升某些属性识别的准确率。

关键词: 行人属性, 多分类, 神经网络, 关联规则, 优化

Abstract: Aiming at the problem of pedestrian multi-attributes recognition under surveillance video, this paper proposes a multi-classification method combining neural network and association rules. Firstly, the attributes confidence of pedestrian in surveillance video can be obtained through Faster-RCNN detection algorithm and improved AlexNet multi-classification network. Then, it adopts Apriori association rules to deal with the training data. After combining neural network classification confidence and the results of association rules, it proposes an algorithm to optimize classification confidence. Finally, by analyzing the accuracy rate of some pedestrian attributes optimized by association rules, the results show that the effective combination of neural network and association rules can improve the accuracy of some attributes recognition.

Key words: pedestrian attribute, multi-classification, neural network, association rules, optimization

中图分类号:

TP18

李雪1,2，郭会明3. 关联规则对监控下行人属性识别影响的研究[J]. 计算机与现代化, doi: 10.3969/j.issn.1006-2475.2019.04.012.

LI Xue1,2, GUO Hui-ming3. Research on Affection of Association Rules to Pedestrian #br# Attributes Recognition in Surveillance Video[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2019.04.012.

参考文献［23］

［1］	CHEN Q, HUANG J S, FERIS R, et al. Deep domain adaptation for describing people based on fine-grained clothing attributes［C］// IEEE Conference on Computer Vision and Pattern Recognition. 2015:5315-5324.
［2］	RUSSAKOVSKV O, DENG J, SU H, et al. ImageNet large scale visual recognition challenge［J］. International Journal of Computer Vision, 2015,115(3):211-252.
［3］	KUMAR N, BERG A C, BELHUMEUR P N, et al. Describable visual attributes for face verification and image search［J］. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2011,33(10):1962-1977.
［4］	SIDDIQUIE B, FERIS R S, DAVIS L S. Image ranking and retrieval based on multi-attribute queries［C］// IEEE Conference on Computer Vision and Pattern Recognition. 2011:801-808.
［5］	GALLEGUILLOS C, RABINOVICH A, BELONGIE S. Object categorization using co-occurrence, location and appearance［C］// 2008 IEEE Conference on Computer Vision and Pattern Recognition. 2008:1-8.
［6］	ZHU J Q, LIAO S C, LEI Z, et al. Pedestrian attribute classification in surveillance: Database and evaluation［C］// IEEE International Conference on Computer Vision Workshops. 2013:331-338.
［7］	胡诚,陈亮,张勋,等. 基于卷积神经网络的监控场景下行人属性识别［J］. 现代计算机(专业版), 2018(1):22-26.
［8］	JI Z, ZHENG W X, PANG Y W. Deep pedestrian attribute recognition based on LSTM［C］// IEEE International Conference on Image Processing. 2018:151-155.
［9］	LI D W, CHENX T, HUANG K Q. Multi-attribute learning for pedestrian attribute recognition in surveillance scenarios［C］// 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR). 2015:1-5.
［10］	REN S Q， HE K M, GIRSHICK R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks［C］// Proceedings of the 28th International Conference on Neural Information Processing Systems. 2015，1:91-99.
［11］	HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition［C］// 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016:770-778.
［12］	ZEILER M D, FERGUS R. Visualizing and understanding convolutional networks［C］// European Conference on Computer Vision (ECCV). 2014:818-833.
［13］	SIMONYAN K, ZISSERMAN A. Very Deep Convolutional Networks for Large-scale Image Recognition［EB/OL］. (2015-04-10). https://arxiv.org/abs/1409.1556.
［14］	NAIR V, HINTON G E． Rectified linear units improve restricted Boltzmann machines［C］// Proceedings of the 27th 〖JP4〗International Conference on Machine Learning. 2010: 807-814．
［15］	胡鹏程,张超,鲍丙计,等. 基于车载视频的行人预警系统［J］. 计算机与现代化, 2016(11):43-52.
［16］	曾孝文. 关联规则数据挖掘方法的研究［J］. 计算机与现代化, 2006(9):90-92.
［17］	黄秋勇,唐爱龙. 关联规则在图像数据挖掘中的应用［J］. 计算机与现代化, 2009(10):98-100.
［18］	胡佳. 几种典型关联规则算法的分析与比较［J］. 现代计算机(专业版), 2011(17):15-17.
［19］	刘巍,蒋华. 挖掘关联规则中Apriori算法的改进与优化［J］. 计算机与现代化, 2006(11):113-115.
［20］	陆丽娜,陈亚萍,魏恒义,等. 挖掘关联规则中Apriori算法的研究［J］. 小型微型计算机系统, 2000,21(9):940-943.
［21］	SURESH J, RUSHYANTH P. Generating associations rule mining using Apriori and FPGrowth algorithms［J］. International Journal of Computer Trends & Technology, 2013,4(4):887-892
［22］	YU K, LENG B, ZHANG Z, et al. Weakly-supervised learning of mid-level features for pedestrian attribute recognition and localization［J］. Computer Vision and Pattern Recognition, 2016,17(9):4321-4329.
［23］	刘华婷,郭仁祥,姜浩. 关联规则挖掘Apriori算法的研究与改进［J］. 计算机应用与软件, 2009,26(1):146-149.

[1]	王宏杰, 徐胜超, 杨波, 毛明扬, 蒋金陵. 基于SRv6技术的云网安全服务链自动编排方法[J]. 计算机与现代化, 2024, 0(01): 1-5.
[2]	陈琦, 李晶晶. D2D网络中基于多目标优化的计算卸载策略[J]. 计算机与现代化, 2024, 0(01): 21-28.
[3]	欧基发, 蔡茂国, 洪广杰, 詹楷杰. 基于PWLCM和秃鹰俯冲机制改进的野狗优化算法[J]. 计算机与现代化, 2024, 0(01): 109-116.
[4]	宋涛涛, 李艳萍, 李洪港, 韩春雪. 基于改进变结构趋近律的机械臂滑模控制系统[J]. 计算机与现代化, 2023, 0(12): 14-18.
[5]	周成诚, 曾庆军, 杨康, 胡家铭, 韩春伟. 基于高效通道注意力模块的运动想象脑电识别[J]. 计算机与现代化, 2023, 0(12): 19-23.
[6]	王宇航, 董宝良, 公超, 尚真真, 姚康宁. 基于意图识别的空中群目标动态威胁评估[J]. 计算机与现代化, 2023, 0(12): 100-104.
[7]	王凯翔, 杨静, 杨文, 米红菊, 甘飞. 基于改进GSA算法的多能源移动电源车优化配置[J]. 计算机与现代化, 2023, 0(12): 105-111.
[8]	杨博, 庄毅. 基于AOA-MSVM的控制集群故障检测方法[J]. 计算机与现代化, 2023, 0(12): 112-116.
[9]	陈晨, 庄毅, 高增. QoE驱动的SDN网络高可用传输框架[J]. 计算机与现代化, 2023, 0(11): 62-68.
[10]	谷明轩, 范冰冰. 基于多模态特征融合的抑郁症识别[J]. 计算机与现代化, 2023, 0(10): 17-22.
[11]	陈俊义. 基于图节点动静态特征的健康事件预测模型[J]. 计算机与现代化, 2023, 0(10): 39-44.
[12]	黎世达, 项剑文. 一种提高图像识别模型鲁棒性的弱化强化方法[J]. 计算机与现代化, 2023, 0(10): 70-76.
[13]	陈子健, 段春红. 面向在线学习情境的认知情绪面部表情识别[J]. 计算机与现代化, 2023, 0(10): 92-98.
[14]	刘付琪, 张达, 宋建华, 王海东. 基于CNN-BiLSTM的液压系统故障诊断[J]. 计算机与现代化, 2023, 0(09): 10-19.
[15]	冀心成, 汪衍凯, 张迎, 许彦杰. 贝叶斯优化梯度提升树的室内日光照度分布预测[J]. 计算机与现代化, 2023, 0(09): 44-50.

关联规则对监控下行人属性识别影响的研究

Research on Affection of Association Rules to Pedestrian #br# Attributes Recognition in Surveillance Video

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献［23］

相关文章 15

编辑推荐

Metrics

本文评价

关联规则对监控下行人属性识别影响的研究

Research on Affection of Association Rules to Pedestrian #br# Attributes Recognition in Surveillance Video

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献 ［23］

相关文章 15

编辑推荐

Metrics

本文评价

参考文献［23］