基于小波分析法的传感器信息融合的运动损伤检测方法
|
摘要
传统方法针对多组传感器路径中的检测点,在很大程度上会出现若干存在差异的损伤发生概率,导致运动损伤检测不准确。为此,提出一种传感器信息融合的运动损伤检测方法。利用多帧帧间差的累积消除空洞效应,在此基础之上,融合传感器确定出准确的人体运动区域,以此对不同场景人体运动进行监测;采用小波分析法对监测结果的非平稳信号进行分析,得到运动损伤特征。将传感器信息融合和小波神经网络结合在一起,获取所有传感器的小波能量特征向量,按照最大概率密度函数值和特征向量获取融合运动损伤检测结果及损伤种类。实验结果表明,所提方法检测结果准确,实用性强。
In order to solve the problem of inaccurate motion damage detection in the traditional method,a motion damage detection method based on sensor information fusion was proposed. The cavity effect was eliminated by the accumulation of multi-frame interframe difference. On this basis,the sensor was combined to determine the accurate human motion region,and the human motion of different scenes was monitored through the region. The wavelet analysis method was used to monitor the non-stationary results. The signal was analyzed to obtain motion impairment features. The sensor information and the wavelet neural network were combined to obtain the wavelet energy feature vector of all sensors,and the fusion motion damage detection result and damage type were obtained according to the maximum probability density function value and the feature vector. The experimental results show that the proposed method is accurate and practical.
In order to solve the problem of inaccurate motion damage detection in the traditional method,a motion damage detection method based on sensor information fusion was proposed. The cavity effect was eliminated by the accumulation of multi-frame interframe difference. On this basis,the sensor was combined to determine the accurate human motion region,and the human motion of different scenes was monitored through the region. The wavelet analysis method was used to monitor the non-stationary results. The signal was analyzed to obtain motion impairment features. The sensor information and the wavelet neural network were combined to obtain the wavelet energy feature vector of all sensors,and the fusion motion damage detection result and damage type were obtained according to the maximum probability density function value and the feature vector. The experimental results show that the proposed method is accurate and practical.
引文
1夏菽兰,赵力.基于BP神经网络的多传感器信息融合研究[J].计算机测量与控制,2015,23(5):1823-1826Xia Shulan,Zhao Li.Research of multi-sensor information fusion based on BP neural networks[J].Computer Measurement&Control,2015,23(5):1823-1826
2王中立,牛颖.基于多传感器信息融合的机器人障碍物检测[J].中国测试,2017,43(8):80-85Wang Zhongli,Niu Ying.Obstacle detection of robot based on multisensor information fusion[J].China Measurement&Testing Technology,2017,43(8):80-85
3 Pescaru D,Curiac D I.Anchor node localization for wireless sensor networks using video and compass information fusion[J].Sensors,2014,14(3):4211-4224
4杨丹,刘小平,胡凌燕.基于多传感器信息融合的机器人姿态测量系统[J].计算机工程与设计,2016,37(6):1681-1686Yang Dan,Liu Xiaoping,Hu Lingyan.Attitude measurement system for robot based on multi-sensor information fusion[J].Computer Engineering and Design,2016,37(6):1681-1686
5王秀青,侯增广,曾慧,等.基于多传感器信息融合的机器人故障诊断[J].上海交通大学学报,2015,49(6):793-798Wang Xiuqing,Hou Zengguang,Zeng Hui,et al.Fault diagnosis of robots based on multi-sensor information fusion[J].Journal of Shanghai Jiaotong University,2015,49(6):793-798
6肖军,文斌.剧烈运动中身体易损伤部位预测建模仿真[J].计算机仿真,2016,33(12):440-443Xiao Jun,Wen Bin.Vigorous exercise most vulnerable parts of the body damage estimation model simulation[J].Computer Simulation,2016,33(12):440-443
7周文博,刘广瑞,田欣,等.电弧传感器和超声波传感器信息融合在焊接中的应用[J].机床与液压,2016,44(15):19-22Zhou Wenbo,Liu Guangrui,Tian Xin,et al.Application of electric arc sensor and ultrasonic sensor information fusion in welding[J].Machine Tool&Hydraulics,2016,44(15):19-22
8 Tian T,Sun S,Li N.Multi-sensor information fusion estimators for stochastic uncertain systems with correlated noises[J].Information Fusion,2016,27(6):126-137
9樊龙龙,李洪兴,翟晨汐,等.基于模糊信息融合的自平衡机器人姿态角补偿方法[J].科学技术与工程,2014,14(7):34-39Fan Longlong,Li Hongxing,Zhai Chenxi,et al.Attitude angle compensation method for self-balancing robot based on fuzzy information fusion[J].Science Technology and Engineering,2014,14(7):34-39
10刘希亮,陈桂明,李方溪,等.基于改进证据理论的多传感器信息融合故障诊断[J].中国机械工程,2014,25(10):1341-1345Liu Xiliang,Chen Guiming,Li Fangxi,et al.Multi-sensor information fusion fault diagnosis based on improved evidence theory[J].China Mechanical Engineering,2014,25(10):1341-1345
11刘培,李嘉禄,万振凯.三维编织复合材料健康检测的FBG传感器信号的阈值去噪优化[J].科技通报,2015,31(10):262-265Liu Pei,Li Jialu,Wan Zhenkai.FBG sensor signal detection of 3Dbraided composites threshold denoising optimization[J].Bulletin of Science and Technology,2015,31(10):262-265
12陈伟强,陈军,张闯,等.基于智能粒子滤波的多传感器信息融合算法[J].计算机应用,2016,36(12):3358-3362Chen Weiqiang,Chen Jun,Zhang Chuang,et al.Multisensor information fusion algorithm based on intelligent particle filtering[J].Journal of Computer Applications,2016,36(12):3358-3362
13周建伟.基于三维传感跟踪的运动损伤动作细节特征提取[J].现代电子技术,2017,40(20):101-103Zhou Jianwei.Sports injury motion detail feature extraction based on3D sensing tracking[J].Modern Electronics Technique,2017,40(20):101-103
14陈云鹏.激光技术在运动损伤和恢复训练中的运用[J].激光杂志,2017,38(4):164-168Chen Yunpeng.Application of laser technology in sports injury and recovery training[J].Laser Journal,2017,38(4):164-168
15鲍楠,姜博文,李永泽,等.基于Kinect传感器的摔倒检测研究[J].电子设计工程,2017,25(12):149-152Bao Nan,Jiang Bowen,Li Yongze,et al.Fall detection system based on Kinect[J].Electronic Design Engineering,2017,25(12):149-152
16 Tang L,Gong Y,Luo Y,et al.Positioning algorithms by information fusion in wireless sensor networks[J].Wireless Personal Communications,2014,74(2):545-557
17吴昕慧,蔡煊,陶汉卿.基于多传感器的列车里程计定位误差检测及校正方法[J].城市轨道交通研究,2016,19(5):19-25Wu Xinhui,Cai Xuan,Tao Hanqing.Detection and correction method of train odometer positioning error based on multi-sensor system[J].Urban Mass Transit,2016,19(5):19-25
18 Anacleto R,Figueiredo L,Almeida A,et al.Person localization using sensor information fusion[J].Nuclear Medicine Communications,2014,28(9):719-725
19李正周,方朝阳,顾园山,等.基于无线多传感器信息融合的火灾检测系统[J].数据采集与处理,2014,29(5):694-698Li Zhengzhou,Fang Chaoyang,Gu Yuanshan,et al.Fire detection system based on wireless multi-sensor information fusion[J].Journal of Data Acquisition&Processing,2014,29(5):694-698
2王中立,牛颖.基于多传感器信息融合的机器人障碍物检测[J].中国测试,2017,43(8):80-85Wang Zhongli,Niu Ying.Obstacle detection of robot based on multisensor information fusion[J].China Measurement&Testing Technology,2017,43(8):80-85
3 Pescaru D,Curiac D I.Anchor node localization for wireless sensor networks using video and compass information fusion[J].Sensors,2014,14(3):4211-4224
4杨丹,刘小平,胡凌燕.基于多传感器信息融合的机器人姿态测量系统[J].计算机工程与设计,2016,37(6):1681-1686Yang Dan,Liu Xiaoping,Hu Lingyan.Attitude measurement system for robot based on multi-sensor information fusion[J].Computer Engineering and Design,2016,37(6):1681-1686
5王秀青,侯增广,曾慧,等.基于多传感器信息融合的机器人故障诊断[J].上海交通大学学报,2015,49(6):793-798Wang Xiuqing,Hou Zengguang,Zeng Hui,et al.Fault diagnosis of robots based on multi-sensor information fusion[J].Journal of Shanghai Jiaotong University,2015,49(6):793-798
6肖军,文斌.剧烈运动中身体易损伤部位预测建模仿真[J].计算机仿真,2016,33(12):440-443Xiao Jun,Wen Bin.Vigorous exercise most vulnerable parts of the body damage estimation model simulation[J].Computer Simulation,2016,33(12):440-443
7周文博,刘广瑞,田欣,等.电弧传感器和超声波传感器信息融合在焊接中的应用[J].机床与液压,2016,44(15):19-22Zhou Wenbo,Liu Guangrui,Tian Xin,et al.Application of electric arc sensor and ultrasonic sensor information fusion in welding[J].Machine Tool&Hydraulics,2016,44(15):19-22
8 Tian T,Sun S,Li N.Multi-sensor information fusion estimators for stochastic uncertain systems with correlated noises[J].Information Fusion,2016,27(6):126-137
9樊龙龙,李洪兴,翟晨汐,等.基于模糊信息融合的自平衡机器人姿态角补偿方法[J].科学技术与工程,2014,14(7):34-39Fan Longlong,Li Hongxing,Zhai Chenxi,et al.Attitude angle compensation method for self-balancing robot based on fuzzy information fusion[J].Science Technology and Engineering,2014,14(7):34-39
10刘希亮,陈桂明,李方溪,等.基于改进证据理论的多传感器信息融合故障诊断[J].中国机械工程,2014,25(10):1341-1345Liu Xiliang,Chen Guiming,Li Fangxi,et al.Multi-sensor information fusion fault diagnosis based on improved evidence theory[J].China Mechanical Engineering,2014,25(10):1341-1345
11刘培,李嘉禄,万振凯.三维编织复合材料健康检测的FBG传感器信号的阈值去噪优化[J].科技通报,2015,31(10):262-265Liu Pei,Li Jialu,Wan Zhenkai.FBG sensor signal detection of 3Dbraided composites threshold denoising optimization[J].Bulletin of Science and Technology,2015,31(10):262-265
12陈伟强,陈军,张闯,等.基于智能粒子滤波的多传感器信息融合算法[J].计算机应用,2016,36(12):3358-3362Chen Weiqiang,Chen Jun,Zhang Chuang,et al.Multisensor information fusion algorithm based on intelligent particle filtering[J].Journal of Computer Applications,2016,36(12):3358-3362
13周建伟.基于三维传感跟踪的运动损伤动作细节特征提取[J].现代电子技术,2017,40(20):101-103Zhou Jianwei.Sports injury motion detail feature extraction based on3D sensing tracking[J].Modern Electronics Technique,2017,40(20):101-103
14陈云鹏.激光技术在运动损伤和恢复训练中的运用[J].激光杂志,2017,38(4):164-168Chen Yunpeng.Application of laser technology in sports injury and recovery training[J].Laser Journal,2017,38(4):164-168
15鲍楠,姜博文,李永泽,等.基于Kinect传感器的摔倒检测研究[J].电子设计工程,2017,25(12):149-152Bao Nan,Jiang Bowen,Li Yongze,et al.Fall detection system based on Kinect[J].Electronic Design Engineering,2017,25(12):149-152
16 Tang L,Gong Y,Luo Y,et al.Positioning algorithms by information fusion in wireless sensor networks[J].Wireless Personal Communications,2014,74(2):545-557
17吴昕慧,蔡煊,陶汉卿.基于多传感器的列车里程计定位误差检测及校正方法[J].城市轨道交通研究,2016,19(5):19-25Wu Xinhui,Cai Xuan,Tao Hanqing.Detection and correction method of train odometer positioning error based on multi-sensor system[J].Urban Mass Transit,2016,19(5):19-25
18 Anacleto R,Figueiredo L,Almeida A,et al.Person localization using sensor information fusion[J].Nuclear Medicine Communications,2014,28(9):719-725
19李正周,方朝阳,顾园山,等.基于无线多传感器信息融合的火灾检测系统[J].数据采集与处理,2014,29(5):694-698Li Zhengzhou,Fang Chaoyang,Gu Yuanshan,et al.Fire detection system based on wireless multi-sensor information fusion[J].Journal of Data Acquisition&Processing,2014,29(5):694-698