| Technical Name | A Fall Detection System based on AI Edge Computing Technique | ||
|---|---|---|---|
| Project Operator | Southern Taiwan University of ScienceTechnology | ||
| Project Host | 張萬榮 | ||
| Summary | In order to solve the undiscovered problem that caused by the fall ofelders, we develop a deep learning based systemnamed it 「SkyEye」,which includes our own sensor 「AI Falling Image Sensor」, a cloud sever that storespushes information about fall eventsa mobile app that communicates with users. | ||
| Market Potential Analysis | "隨著高齡化社會發展，「跌倒事件」已經成為世界各地意外或非故意傷害死亡的第二大原因，其中又以全世界近10億位老人佔最大的比例。據衛福部調查顯示，65歲以上老人跌倒比率為16.5，造成每年有26萬位老人因跌倒而死亡，其中85歲以上跌倒者致死率更高達40，且隨著發現時間越晚死亡率越高，每年將耗費掉233億的醫療成本，造成醫療體系及家庭龐大的負擔。 高齡化的人口結構使得醫療服務與長期照護的需求大幅增加，其中發展「遠距居家照顧(tele-home care, THC)」成為一主要方向，是全球政府經濟發展的重要願景之一。例如在美國，遠距醫療居家照護市場是醫療產業中少數出現成長的領域，預計至2025年的年成長率可達20以上，而我國政府亦將「遠距居家照護服務」列為我國2008年新興服務產業的發展計畫之一，成為名列國家發展重點計畫中的新興服務產業。" | ||
| Industrial Applicability | With system integration provided by 「SkyEye」, Mobile phone app for family memberscaregivers can instantly be reported by the cloud server when the fall event happened, that can improve the efficiency of the nursing station to grasp the information of the elderly fall,reduce both rescue timechance of death of the elderly. | ||
| Keyword | Fall event detection Image recognition Deep learning TensorFlow Openpose VGG19 Human tracking Fall recognition Edge computing Realtime multi-person skeleton detection | ||
| Notes | |||
- Contact
- ling701218@stust.edu.tw
Other people also saw
