{"title":"室内震后廊道障碍评价系统","authors":"Hankui Zhang, E. Chu, Shih-Yu Chen","doi":"10.1109/ICS.2016.0084","DOIUrl":null,"url":null,"abstract":"Due to the need of indoor emergency rescue for earthquake disasters, we propose the iPOST (Indoor Post-Earthquake Corridor Obstacle Assessment System) to determine the obstacles in the corridors after earthquakes. Before an earthquake hits, a pre-earthquake image is used to segment its corresponding floor area for determining the presence of obstacles. After an earthquake, the pre-earthquake and post-earthquake images are compared by using the interimage foreground technique for assessing the obstacles in the corridors. To verify the effectiveness of the iPOST, we collected over 40 pairs of images captured by corridor surveillance cameras from YouTube and Google, which included corridor scenarios with and without the presence of obstacles. The experiment results show that the iPOST's accuracy in obstacle assessment reaches 84%.","PeriodicalId":281088,"journal":{"name":"2016 International Computer Symposium (ICS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Indoor Post-Earthquake Corridor Obstacle Assessment System\",\"authors\":\"Hankui Zhang, E. Chu, Shih-Yu Chen\",\"doi\":\"10.1109/ICS.2016.0084\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Due to the need of indoor emergency rescue for earthquake disasters, we propose the iPOST (Indoor Post-Earthquake Corridor Obstacle Assessment System) to determine the obstacles in the corridors after earthquakes. Before an earthquake hits, a pre-earthquake image is used to segment its corresponding floor area for determining the presence of obstacles. After an earthquake, the pre-earthquake and post-earthquake images are compared by using the interimage foreground technique for assessing the obstacles in the corridors. To verify the effectiveness of the iPOST, we collected over 40 pairs of images captured by corridor surveillance cameras from YouTube and Google, which included corridor scenarios with and without the presence of obstacles. The experiment results show that the iPOST's accuracy in obstacle assessment reaches 84%.\",\"PeriodicalId\":281088,\"journal\":{\"name\":\"2016 International Computer Symposium (ICS)\",\"volume\":\"2 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2016 International Computer Symposium (ICS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICS.2016.0084\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 International Computer Symposium (ICS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICS.2016.0084","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Indoor Post-Earthquake Corridor Obstacle Assessment System
Due to the need of indoor emergency rescue for earthquake disasters, we propose the iPOST (Indoor Post-Earthquake Corridor Obstacle Assessment System) to determine the obstacles in the corridors after earthquakes. Before an earthquake hits, a pre-earthquake image is used to segment its corresponding floor area for determining the presence of obstacles. After an earthquake, the pre-earthquake and post-earthquake images are compared by using the interimage foreground technique for assessing the obstacles in the corridors. To verify the effectiveness of the iPOST, we collected over 40 pairs of images captured by corridor surveillance cameras from YouTube and Google, which included corridor scenarios with and without the presence of obstacles. The experiment results show that the iPOST's accuracy in obstacle assessment reaches 84%.