{"title":"开放场景中的跌倒识别","authors":"Kai Yao, Shanna Zhuang, Yale Zhao, Zhengyou Wang","doi":"10.1109/ICCEAI52939.2021.00060","DOIUrl":null,"url":null,"abstract":"Falls would cause harm to the fall-prone group, including the elderly, children and the disabled people. Fall behavior recognition is important to protect them from being injured. In order to improve the accurancy of the fall behavior recognition, a two-stream neural network model based on MobileNetV2, a lightweight deep neural network, is proposed in this paper. Experiments are conducted on the following three datasets, UR fall detection dataset, Multiple cameras fall dataset and Le2i fall detection dataset. The performances of the presented model are compared with those of single-stream model, 3D-CNN, and two-stream model combining CNN and optical stream. The effectiveness of the proposed method is indicated.","PeriodicalId":331409,"journal":{"name":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Fall Recognition in Open Scenes\",\"authors\":\"Kai Yao, Shanna Zhuang, Yale Zhao, Zhengyou Wang\",\"doi\":\"10.1109/ICCEAI52939.2021.00060\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Falls would cause harm to the fall-prone group, including the elderly, children and the disabled people. Fall behavior recognition is important to protect them from being injured. In order to improve the accurancy of the fall behavior recognition, a two-stream neural network model based on MobileNetV2, a lightweight deep neural network, is proposed in this paper. Experiments are conducted on the following three datasets, UR fall detection dataset, Multiple cameras fall dataset and Le2i fall detection dataset. The performances of the presented model are compared with those of single-stream model, 3D-CNN, and two-stream model combining CNN and optical stream. The effectiveness of the proposed method is indicated.\",\"PeriodicalId\":331409,\"journal\":{\"name\":\"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICCEAI52939.2021.00060\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCEAI52939.2021.00060","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Falls would cause harm to the fall-prone group, including the elderly, children and the disabled people. Fall behavior recognition is important to protect them from being injured. In order to improve the accurancy of the fall behavior recognition, a two-stream neural network model based on MobileNetV2, a lightweight deep neural network, is proposed in this paper. Experiments are conducted on the following three datasets, UR fall detection dataset, Multiple cameras fall dataset and Le2i fall detection dataset. The performances of the presented model are compared with those of single-stream model, 3D-CNN, and two-stream model combining CNN and optical stream. The effectiveness of the proposed method is indicated.