Research On Earthquake Emergency Response Modes Of Individuals Based On Social Surveillance Video

Seismic disaster risk is an interdisciplinary subject,which involves not only the seismic hazard,but also the seismic vulnerability of buildings,as well as the population exposure.Therefore,reducing the seismic disaster risk is a system engineering,which needs the joint efforts of many disciplines.After earthquake,the correct and efficient earthquake emergency response behaviors of individuals are very important to reduce casualties and the seismic disaster risk.Compared with the fire,hurricane and other disasters,there are few studies on the pedestrians’ earthquake emergency response behaviors.Based on the collected social surveillance videos and the actual response of individuals recorded in the surveillance videos,this paper has analyzed the pedestrians’ earthquake emergency response behaviors qualitatively and quantitatively,extracts the data of the pedestrians’ earthquake emergency response behaviors in the video,and conducts the analysis and research:First,the video analysis technology is used to extract the pedestrians’ typical earthquake emergency response behaviors.In this paper,the process of individuals’ earthquake emergency response can be divided into four stages: pre-earthquake phase,first response behaviors after earthquake,first protective behaviors after earthquake,and subsequent behaviors.According to the different characteristics of the four stages,the pedestrians’ typical earthquake emergency response behaviors have been extracted by using the transana analysis technology.The pedestrians’ typical earthquake emergency response behaviors are the foundation of developing an extensive database for evacuation models,constructing the earthquake emergency response decision tree and studying the pedestrians’ evacuation efficiency.Second,with the booming development of evacuation simulation software,developing an extensive database for evacuation models is imperative.In this part,we have conducted a qualitative and quantitative analysis of the collected videotapes andaim to provide a complete and unitary database of pedestrians’ earthquake emergency response behaviors,including human-environment interactions.Using the qualitative analysis method,we have extracted keyword groups and keywords that code the response modes of pedestrians and construct a general decision flowchart using chronological organization.Using the quantitative analysis method,we have analyzed data on the delay time,evacuation speed,evacuation route and emergency exit choices.Furthermore,we have studied the effect of classroom layout on emergency evacuation.The database provides reliable input parameters and allows the construction of real and effective constraints for using in software and mathematical models.The database can also be used to validate the accuracy of evacuation models.Third,the correct and efficient earthquake emergency response modes of individuals are crucial for reducing casualties.Based on the keyword database of the earthquake emergency response behaviors of individuals,this research has used the machine learning method to construct a decision tree of the earthquake emergency response modes.Through the decision tree,this study has extracted decision rules that can predict the emergency response decisions of individuals in future earthquake and also determined the relative importance of six different factors(Seismic intensity>Social context>Location>Action>Age>Gender)in determining response behaviors.The set of rules is quite effective when evaluated using the test individuals with an overall accuracy of 85.23%.And then,we have extracted and analyzed the main response modes of individuals at seismic intensities Ⅳ-Ⅴ、Ⅵ、Ⅶ、Ⅷ-Ⅸ stricken regions by earthquake.The decision rules and main response modes of individuals are scientific bases for the targeted earthquake emergency safety education and the government emergency rescue.Fourth,based on the research on the quantitative of panic coefficient and the calibration of initial desired speed,this research has constructed the revised social force model which could accurately simulate the post-earthquake evacuation process of individuals.Using the revised social force model,the effects of classroom layout,seismic intensity,the number of safeties exits and the number of students in the classroom on the evacuation efficiency are further studied.And then,according to theresearch results,the classroom layout has been further optimized to improve the students’ earthquake emergency evacuation efficiency.These research results are scientific bases for the targeted earthquake emergency safety education and the design of classroom layout.Fifth,the empirical formula of evacuation success rate(Dimensionless)is proposed.The relative value of evacuation success rate in this paper is a dimensionless coefficient,which only represents the relative size and change trend of evacuation success rate,but does not represent the real evacuation success rate.The empirical formula of evacuation success rate relative value(dimensionless)has been fitted by normalization treatment of evacuation speed,peak acceleration of horizontal ground motion and evacuation time.The relative value of evacuation success rate is relatively high in VI,VII and VIII stricken regions,which indicates that the probability of crowd evacuation to safe area is high in limited available safe escape time.In Ⅳ-Ⅴstricken regions,the relative value of evacuation success rate is relatively low,because the crowd is not evacuated or the evacuation speed is slow,and the evacuation time is long;however,the buildings will not collapse,and the available escape time for individuals is long,and the survival rate of individuals is very high(not excluding the death caused by accidental factors).The fitting curve of evacuation success rate relative value(dimensionless)is close to the level in IX stricken region,and the probability of individual evacuation from the building to the safe area is low.