删除或更新信息,请邮件至freekaoyan#163.com(#换成@)

基于手机多源传感器的室内火灾行人行为识别

本站小编 Free考研考试/2022-02-13

DOI: 10.11908/j.issn.0253-374x.2019.03.016

作者:

作者单位: 国土环境与灾害监测国家测绘地理信息局重点实验室


作者简介:


通讯作者:

中图分类号: P228.9


基金项目: 国家重点研发计划(2016YFB0502105);国家自然科学基金项目(41371423);江苏省自然科学基金(bk20161181);江苏高校品牌专业建设工程资助项目(PPZY2015B144) 。




Method of Pedestrian’s Behavior Recognition Based on Builtin Sensor of Smartphone in Compartment Fires
Author:

Affiliation:


Fund Project:




摘要
| 图/表
| 访问统计
| 参考文献
|相似文献
| 引证文献
| 资源附件

摘要:针对室内火灾情境下人员安全的有效监控问题,提出了一种基于手机多源传感器的室内火灾行人细粒度行为识别与匹配方法.借助手机内置多源传感器完成对行人当前表征行为特征的数据采集,在异常子序列探测后提取行为特征向量,利用基于关键点序列的动态时间规整(KeyDTW)算法或者相应训练成型的分类模型分别对特征各异的行为进行匹配、理解;并对不同传感器组合方式和不同设备位置的识别能力进行比较;最后,综合识别结果进而分析行人当前生理、心理、位置状态,为室内应急救援工作提供决策信息.经模拟试验验证,该方法不仅能够对行人应激性细粒度行为有较高的识别准确率,对于持久性的动作也有着很高的匹配精确性和效率.



Abstract:When a compartment fire, it is impossible to monitor the safety of pedestrian effectively, a method of pedestrian’s finegrained behavior recognition based on builtin sensors of smartphone was proposed. In this method, the multisensors of mobile phone were used to collect the data of the pedestrian’s characterization. After detecting the abnormal subsequence, the feature vectors were extracted. Then, the algorithm of KeyDTW and the models of classifying were respectively used to recognize and understand the pedestrian’s activities. Next, comparing the ability of classifying in different position of device and in various combination of smartphone sensor. Finally, analyzing the pedestrian’s current status of physiological, psychological and positional. The method will provide much valuable information for the rescue operation. The results of experiments showed that the method has higher accuracies and efficiencies of activity recognition.





PDF全文下载地址:

点我下载PDF
相关话题/传感器 文献 火灾 序列 江苏