单传感器数据驱动的人体日常短时行为识别方法

苏本跃; 郑丹丹; 汤庆丰; 盛敏

doi:10.3788/IRLA201948.0226003

单传感器数据驱动的人体日常短时行为识别方法

doi: 10.3788/IRLA201948.0226003

1.
安庆师范大学计算机与信息学院,安徽安庆 246011;
2.
安徽省智能感知与计算重点实验室,安徽安庆 246011;
3.
杭州师范大学医学院,浙江杭州 311121

基金项目:

国家自然科学基金（61603003，11471093）;教育部"云数融合科教创新"基金（2017A09116）;安徽省高校优秀拔尖人才培育资助项目（gxbjZD26）

详细信息

作者简介:
苏本跃(1971-),男,教授,博士,主要从事机器学习、图形、图像处理等方面的研究。Email:subenyue@sohu.com

中图分类号: TP181

Human daily short-time activity recognition method driven by single sensor data

1.
School of Computer and Information,Anqing Normal University,Anqing 246011,China;
2.
The Key Laboratory of Intelligent Perception and Computing of Anhui Province,Anqing 246011,China;
3.
Medical College,Hangzhou Normal University,Hangzhou 311121,China

摘要: 在基于惯性传感器的人体行为识别研究中，特征提取是其中的关键环节之一。而离散数据统计特征的稳定性依赖于特征提取的窗口大小。一般来说，训练数据的窗口长度需要大于一个运动周期。因此，针对测试数据远小于一个运动周期的短序列样本识别问题，提出了一种基于模板匹配的新的解决方案。首先，通过适当分割训练数据的长序列样本，构建一个过完备的短时行为模板库，将待测短时样本与模板库中样本进行一致化处理并进行匹配；其次，在匹配算法中，采用样本间的F范数与整体梯度向量的2范数累加作为匹配度量准则，得到相似度直方图；最后，基于相似度直方图，根据投票策略得到最终分类识别结果。实验表明：在使用单传感器识别短时行为的情况下，新算法比传统算法在精度和稳定性上具有更好的性能，并能适应不同窗口下短时行为分类问题。
- 短时行为 /
- 模板匹配 /
- 行为模板库 /
- 相似度直方图 /
- 单传感器
Abstract: In the study of human activity recognition(HAR) based on the inertial sensor, feature extraction was one of the key points. The stability of discrete data statistical features depended on the window size of feature extraction. Generally speaking, the length of window needed to be greater than one motion cycle. Therefore, compared to the traditional behavior recognition, short-time behavior recognition was more difficult. Thus a novel template matching method was proposed for recognizing the test samples whose durations were shorter than one motion cycle. Firstly, by properly dividing the long sequence samples, a complete short-time activity template library was constructed. The short-time samples to be tested and the samples in the template library were processed and matched. Secondly, in the matching algorithm, the similarity histogram was obtained by utilizing the sum of the F norm distance between the samples and the 2 norm distance of the global gradient vector as the matching metric. Finally, based on the similarity histogram, the final classification recognition results were obtained according to the voting strategy. Experiments show that in the case of using a single sensor to identify short-term behavior, the new algorithm had better performance than traditional algorithms in accuracy and stability, and can be adapted to short-term behavior classification problems under different windows.
- short-time activity /
- template matching /
- activity template library /
- similarity histogram /
- single sensor

[1]	Poppe R. A survey on vision-based human action recognition[J]. Image Vision Computing, 2010, 28(6):976-990.
[2]	Wang J, Liu Z, Wu Y, et al. Learning actionlet ensemble for 3D human action recognition[J]. IEEE Transactions on Pattern Analysis Mchine Intelligence, 2014, 36(5):914-927.
[3]	Bulling A, Blanke U, Schiele B. A tutorial on human activity recognition using body-worn inertial sensors[J]. Acm Computing Surveys, 2014, 46(3):1-33.
[4]	Lara O D, Labrador M A. A survey on human activity recognition using wearable sensors[J]. IEEE Communications Surveys Tutorials, 2013, 15(3):1192-1209.
[5]	Yang J, Wang S, Chen N, et al. Wearable accelerometer based extendable activity recognition system[C]//IEEE International Conference on Robotics and Automation. Piscataway, 2010:3641-3647.
[6]	Davis K, Owusu E, Bastani V, et al. Activity recognition based on inertial sensors for ambient assisted living[C]//International Conference on Information Fusion, 2016:371-378.
[7]	Su B, Tang Q F, Jiang J, et al, A novel method for short-time human activity recognition based on improved template matching technique[C]//ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry, 2016:233-242.
[8]	Li L J, Su H, Lim Y, et al. Object bank:An object-level image representation for high-level visual recognition[J]. International Journal of Computer Vision, 2014, 107(1):20-39.
[9]	Sadanand S, Corso J J. Action bank:A high-level representation of activity in video[C]//Computer Vision and Pattern Recognition(CVPR), 2012:1234-1241.
[10]	Liu Z J, Lin W, Geng Y L, et al. Intent pattern recognition of lower-limb motion based on mechanical sensors[J]. Journal of Automatica Sinica, 2017, 4(4):651-660.
[11]	Young A J, Simon A M, Hargrove L J. A training method for locomotion mode prediction using powered lower limb prostheses[J]. IEEE Transactions on Neural Systems Rehabilitation Engineering, 2014, 22(3):671-677.
[12]	Young A J, Simon A M, Fey N P, et al. Intent recognition in a powered lower limb prosthesis using time history information[J]. Annals of Biomedical Engineering, 2014, 42(3):631-641.
[13]	Yuan K B, Wang Q N, Wang L. Fuzzy-logic-based terrain identification with multisensor fusion for transtibial amputees[J]. IEEE/ASME Transactions on Mechatronics, 2015, 20(2):618-630
[14]	Zheng E H, Wang Q N. Noncontact capacitive sensing-based locomotion transition recognition for amputees with robotic transtibial prostheses[J]. IEEE Transactions on Neural Systems Rehabilitation Engineering, 2016, 25(2):161-170.
[15]	Yang A Y, Jafari R, Sastry S S, et al. Distributed recognition of human actions using wearable motion sensor networks[J]. Journal of Ambient Intelligence Smart Environments, 2009, 1(2):103-115.
[16]	Su B, Tang Q, Wang G, et al. Transactions on Edutainment XⅡ:The Recognition of Human Daily Actions With Wearable Motion Sensor System[M]. Germany:Springer, 2016:68-77.
[17]	He W, Guo Y, Gao C, et al. Recognition of human activities with wearable sensors[J]. Eurasip Journal on Advances in Signal Processing, 2012, 2012(1):1-13.
[18]	Xiao L. Li R F, Luo J. Recognition on human activity based on compressed sensing in body sensor networks[J]. Journal of Electronics Information Technology, 2013, 35(1):119-125.
[19]	Li F, Pan J K. Human motion recognition based on triaxial accelerometer[J]. Journal of Computer Research and Development, 2016, 53(3):621-631.
[20]	Sheng M, Jiang J, Su B, et al. Short-time activity recognition with wearable sensors using convolutional neural network[C]//Proceedings of the 15th ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry, 2016:413-416.

[1]	雷鸿毅, 张家洪, 张元英, 王新宇, 陈志炎. 铌酸锂晶体结构对电场传感器灵敏度影响分析 . 红外与激光工程, 2023, 52(2): 20220370-1-20220370-8. doi: 10.3788/IRLA20220370
[2]	王向军, 朱慧. 利用国产FPGA的高帧率目标跟踪方法 . 红外与激光工程, 2023, 52(9): 20220905-1-20220905-12. doi: 10.3788/IRLA20220905
[3]	乌日娜, 宋云鹤, 卢佳琦, 高芮, 李业秋, 岱钦. 光子晶体光纤载体中液晶随机激光辐射行为 . 红外与激光工程, 2021, 50(4): 20200171-1-20200171-6. doi: 10.3788/IRLA20200171
[4]	彭进, 王星星, 许红巧, 杨嘉佳, 张芙蓉. 熔滴填充位置对激光焊接熔池动态行为的影响 . 红外与激光工程, 2020, 49(6): 20200025-1-20200025-8. doi: 10.3788/IRLA20200025
[5]	裴晓敏, 范慧杰, 唐延东. 多通道时空融合网络双人交互行为识别 . 红外与激光工程, 2020, 49(5): 20190552-20190552-6. doi: 10.3788/IRLA20190552
[6]	苏李, 张晓彤, 吕沛桐, 孙铭阳, 王成虎, 陈晨, 张天瑜. 大量程高灵敏度的光纤光栅低频振动传感器研究 . 红外与激光工程, 2020, 49(S2): 20200340-20200340. doi: 10.3788/IRLA20200340
[7]	刘舒扬, 张晨, 赵安娜, 李奇峰, 贾晓东. 基于光谱特性的高判别准确度激光近场探测传感器研究 . 红外与激光工程, 2020, 49(4): 0403009-0403009-5. doi: 10.3788/IRLA202049.0403009
[8]	王向军, 郭志翼. 算力限制平台下的长时目标跟踪 . 红外与激光工程, 2020, 49(1): 0126003-0126003(6). doi: 10.3788/IRLA202049.0126003
[9]	卢瑞涛, 任世杰, 申璐榕, 杨小冈. 基于稀疏表示多子模板的鲁棒目标跟踪算法 . 红外与激光工程, 2019, 48(3): 326003-0326003(8). doi: 10.3788/IRLA201948.0326003
[10]	裴晓敏, 范慧杰, 唐延东. 时空特征融合深度学习网络人体行为识别方法 . 红外与激光工程, 2018, 47(2): 203007-0203007(6). doi: 10.3788/IRLA201847.0203007
[11]	安佳, 王永杰, 李芳, 刘元辉, 彭丹丹. 采用聚酰胺酸层的高灵敏度长周期光纤光栅温度传感器 . 红外与激光工程, 2018, 47(8): 822002-0822002(7). doi: 10.3788/IRLA201847.0822002
[12]	张法业, 姜明顺, 隋青美, 张雷, 曹玉强, 马国文, 魏钧涛. 基于柔性铰链结构的高灵敏度低频光纤光栅加速度传感器 . 红外与激光工程, 2017, 46(3): 317004-0317004(8). doi: 10.3788/IRLA201746.0317004
[13]	朱南南, 张骏. 表面粗糙度激光散射检测的多波长光纤传感器 . 红外与激光工程, 2016, 45(5): 522003-0522003(6). doi: 10.3788/IRLA201645.0522003
[14]	王鹏, 娄淑琴, 梁生, 张颜. 选择性平均的φ-OTDR分布式光纤扰动传感系统阈值算法 . 红外与激光工程, 2016, 45(3): 322003-0322003(6). doi: 10.3788/IRLA201645.0322003
[15]	李志军, 刘松林, 牛照东, 陈曾平. 基于梯度相位和显著性约束的Hausdorff 距离模板匹配方法 . 红外与激光工程, 2015, 44(2): 775-780.
[16]	何帆, 白剑, 侯西云. 基于模板匹配的莫尔条纹倾角计算 . 红外与激光工程, 2015, 44(9): 2825-2830.
[17]	戴士杰, 邵猛, 吴佳宁, 葛圣强. 使用12像素对称模板的棋盘格内角点检测 . 红外与激光工程, 2014, 43(4): 1306-1311.
[18]	郭敬明, 何昕, 杨杰, 魏仲慧, 龚俊亮. 模板自适应的Mean Shift红外目标跟踪 . 红外与激光工程, 2014, 43(4): 1087-1093.
[19]	汪鲁才, 易锡年, 陈小天, 刘鑫. 自适应连续多级分区与初始阈值估计的快速模板匹配方法 . 红外与激光工程, 2013, 42(4): 1106-1111.
[20]	吴晓. LED芯片粗精定位系统 . 红外与激光工程, 2013, 42(9): 2478-2484.

点击查看大图

计量

文章访问数: 512
HTML全文浏览量: 71
PDF下载量: 61
被引次数: 0

姓名
邮箱
手机号码
标题
留言内容
验证码

留言板

单传感器数据驱动的人体日常短时行为识别方法

doi: 10.3788/IRLA201948.0226003

作者简介:
苏本跃(1971-),男,教授,博士,主要从事机器学习、图形、图像处理等方面的研究。Email:subenyue@sohu.com

Human daily short-time activity recognition method driven by single sensor data

计量

单传感器数据驱动的人体日常短时行为识别方法

doi: 10.3788/IRLA201948.0226003

1. 安庆师范大学计算机与信息学院,安徽安庆 246011;

2. 安徽省智能感知与计算重点实验室,安徽安庆 246011;

3. 杭州师范大学医学院,浙江杭州 311121

作者简介:
苏本跃(1971-),男,教授,博士,主要从事机器学习、图形、图像处理等方面的研究。Email:subenyue@sohu.com

English Abstract

Human daily short-time activity recognition method driven by single sensor data

1. School of Computer and Information,Anqing Normal University,Anqing 246011,China;

2. The Key Laboratory of Intelligent Perception and Computing of Anhui Province,Anqing 246011,China;

3. Medical College,Hangzhou Normal University,Hangzhou 311121,China

全文HTML

目录

留言板

单传感器数据驱动的人体日常短时行为识别方法

doi: 10.3788/IRLA201948.0226003

作者简介: 苏本跃(1971-),男,教授,博士,主要从事机器学习、图形、图像处理等方面的研究。Email:subenyue@sohu.com

Human daily short-time activity recognition method driven by single sensor data

计量

出版历程

单传感器数据驱动的人体日常短时行为识别方法

doi: 10.3788/IRLA201948.0226003

1. 安庆师范大学 计算机与信息学院,安徽 安庆 246011; 2. 安徽省智能感知与计算重点实验室,安徽 安庆 246011; 3. 杭州师范大学 医学院,浙江 杭州 311121

作者简介: 苏本跃(1971-),男,教授,博士,主要从事机器学习、图形、图像处理等方面的研究。Email:subenyue@sohu.com

English Abstract

Human daily short-time activity recognition method driven by single sensor data

1. School of Computer and Information,Anqing Normal University,Anqing 246011,China; 2. The Key Laboratory of Intelligent Perception and Computing of Anhui Province,Anqing 246011,China; 3. Medical College,Hangzhou Normal University,Hangzhou 311121,China

全文HTML

目录

作者简介:
苏本跃(1971-),男,教授,博士,主要从事机器学习、图形、图像处理等方面的研究。Email:subenyue@sohu.com

1. 安庆师范大学计算机与信息学院,安徽安庆 246011;

2. 安徽省智能感知与计算重点实验室,安徽安庆 246011;

3. 杭州师范大学医学院,浙江杭州 311121

作者简介:
苏本跃(1971-),男,教授,博士,主要从事机器学习、图形、图像处理等方面的研究。Email:subenyue@sohu.com

1. School of Computer and Information,Anqing Normal University,Anqing 246011,China;

2. The Key Laboratory of Intelligent Perception and Computing of Anhui Province,Anqing 246011,China;

3. Medical College,Hangzhou Normal University,Hangzhou 311121,China