发明名称 Handheld computer systems and techniques for character and command recognition related to human movements
摘要 Systems and methods for human hand gesture recognition through a training mode and a recognition mode are disclosed. In the training mode, a user can move a handheld device with a hand gesture intended to represent a command. Sensors within the handheld device can record raw data, which can be processed to obtain a set of values corresponding to a set of discrete features, which is stored in a database and associated with the intended command. The process is repeated for various hand gestures representing different commands. In the recognition mode, the user can move the handheld device with a hand gesture. A computer system can compare a set of values corresponding to a set of discrete features derived from the hand gesture with the sets of values stored in the database, select a command with the closest match and displays and/or executes the command.
申请公布号 US9174123(B2) 申请公布日期 2015.11.03
申请号 US201012832707 申请日期 2010.07.08
申请人 INVENSENSE, INC. 发明人 Nasiri Steve;Sachs David;Castro Alex;Li Richard;Gu Anjia;Lin Shang-Hung;Nakayama Takashi
分类号 G05B23/00;A63F13/20;G06F1/16;G06F3/01;G06F3/0346;G06F3/038;G06F21/32;H04M1/725 主分类号 G05B23/00
代理机构 Sawyer Law Group, P.C. 代理人 Sawyer Law Group, P.C.
主权项 1. A handheld device, comprising: inertial sensors comprising a gyroscope that generates gyroscope data representing a trajectory of a movement of the handheld device and an accelerometer that generates accelerometer data representing a tilt of the handheld device relative to earth's gravity; and a processing component that: determines the trajectory of the movement of the handheld device by combining the gyroscope data representing the trajectory of the movement of the handheld device and the accelerometer data representing the tilt of the handheld device relative to earth's gravity;converts, via a training mode, a first portion of the data into a first set of values corresponding to a first plurality of discrete features,associates the first set of values with a character, stores the first set of values and information representing the character in a training database,converts, via a recognition mode, a second portion of the data into a second set of values corresponding to a second plurality of discrete features, wherein a discrete feature of the first plurality of discrete features or the second plurality of discrete features includes at least one of an angle of the trajectory, an inverse tangent of a change in a pitch associated with the movement divided by a change in a yaw associated with the movement, a location of a crossing point associated with the character, or a number of times in which the trajectory changes direction; andin response to a determination that the second set of values matches the first set of values with respect to a defined condition, displays the character.
地址 San Jose CA US