The invention relates to command processing using multi-modal signal analysis. A first set of signals corresponding to a first signal modality, such as the direction of gaze, is collected from the individual during a time interval. A second set of signals corresponding to different signal modalities, such as finger-directed gestures made by the individual, is also collected. In response to a command where the command does not identify a particular object to which the command points, the first set of signals and the second set of signals are used to identify candidate objects of interest, and an operation associated with selecting an object from the candidate objects is performed.
本公开涉及使用多模态信号分析进行命令处理。在时间间隔期间从个体收集与第一信号模态(诸如,注视的所述方向)相对应的第一组信号。还收集与不同信号模态(诸如,由所述个体作出的手指向姿态)相对应的第二组信号。响应于命令,其中所述命令不识别所述命令所指向的特定对象,所述第一组信号和所述第二组信号用于识别所关注的候选对象,并且执行与从所述候选对象中选定对象相关联的操作。
Command processing using multi-modal signal analysis
使用多模态信号分析进行命令处理
2022-11-01
Patent
Electronic Resource
Chinese