CAREER: Video-Based Computer Interfaces for People with Severe Disabilities

职业：为严重残障人士提供基于视频的计算机界面

• 批准号: 0093367
• 负责人: Margrit Betke
• 金额: $ 41.27万
• 依托单位: Trustees of Boston University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2001
• 资助国家: 美国
• 起止时间: 2001-08-01 至 2007-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0093367&HistoricalAwards=false
• 关键词: CAREER; Video; Based; Computer; Interfaces

People who are quadriplegic and nonverbal, for example from cerebral palsy or traumatic brain injury, often have great difficulties communicating their desires, thoughts, and needs. A video-based human-computer interface system will be developed to provide such people access to computers. The interface system will detect and track their limited voluntary motions to help them communicate with family, friends, and care providers. A set of cameras with pan, tilt, and zoom mechanisms will be pointed at the computer user. Computer vision algorithms will recognize the movements of a finger, foot, or facial feature in real time and interpret them as a communication of the computer user. Augmentative communication software will be developed that uses these interpretations to provide access to commercially available or custom-built application software. The system will be trained and tested by several non-speaking children with cerebral palsy and other serious disabilities. This research is expected to advance the state-of-the-art in the fields of computer vision and assistive technology with new video interpretation algorithms and innovative real-time system design. It will help people with severe disabilities gain access to a computer and thereby obtain a tool for communication, which in turn will enable them to actively acquire knowledge, to partake in increased recreational activities, to surf the internet, and to use computer-controlled technologies such as automated wheelchairs.

四肢瘫痪和不会说话的人，例如脑瘫或创伤性脑损伤，通常很难沟通他们的愿望、想法和需求。将开发一个基于视频的人机界面系统，为这些人提供访问计算机的机会。该接口系统将检测和跟踪他们有限的自愿动作，以帮助他们与家人、朋友和护理人员沟通。一组带有摇摄、倾斜和变焦机制的摄像头将对准计算机用户。计算机视觉算法将实时识别手指、脚或面部特征的运动，并将其解释为计算机用户的交流。将开发使用这些解释的增强型通信软件，以提供对商业上可用的或定制的应用软件的访问。该系统将由几名患有脑瘫和其他严重残疾的不会说话的儿童进行培训和测试。这项研究有望通过新的视频解译算法和创新的实时系统设计来推动计算机视觉和辅助技术领域的尖端技术。它将帮助严重残疾人士接触计算机，从而获得交流工具，这反过来将使他们能够积极获取知识，参与更多的娱乐活动，上网，并使用计算机控制的技术，如自动轮椅。