发明名称 Input detection
摘要 This disclosure involves proximity sensing of eye gestures using a machine-learned model. An illustrative method comprises receiving training data that includes proximity-sensor data. The data is generated by at least one proximity sensor of a head-mountable device (HMD). The data is indicative of light received by the proximity sensor(s). The light is received by the proximity sensor(s) after a reflection of the light from an eye area. The reflection occurs while an eye gesture is being performed at the eye area. The light is generated by at least one light source of the HMD. The method further comprises applying a machine-learning process to the training data to generate at least one classifier for the eye gesture. The method further comprises generating an eye-gesture model that includes the at least one classifier for the eye gesture. The model is applicable to subsequent proximity-sensor data for detection of the eye gesture.
申请公布号 US9207760(B1) 申请公布日期 2015.12.08
申请号 US201213630563 申请日期 2012.09.28
申请人 Google Inc. 发明人 Wu Bo;Zhao Yong;Neven Hartmut;Raffle Hayes Solos;Starner Thad Eugene
分类号 G06F15/18;G06N5/02;G06N3/02;G06F3/01;G06K9/62;G06K9/00;G06N99/00;G02B27/00;G02B27/01 主分类号 G06F15/18
代理机构 McDonnell Boehnen Hulbert & Berghoff LLP 代理人 McDonnell Boehnen Hulbert & Berghoff LLP
主权项 1. A method comprising: receiving training data that includes proximity-sensor data, wherein the proximity-sensor data is generated by at least one inward-facing proximity sensor of a head-mountable device (HMD), wherein the at least one proximity sensor is directed towards a side of an eye, wherein the proximity-sensor data is indicative of light received by the at least one proximity sensor after a reflection of the light from an eye area, wherein at least a substantial portion of the eye area is constituted by skin at the side of the eye that wrinkles when an eye gesture of the eye occurs, and wherein the light is generated by at least one light source of the HMD; applying a machine-learning process to the training data to generate at least one one-dimensional classifier for the eye gesture; and generating an eye-gesture model that includes the at least one one-dimensional classifier for the eye gesture, wherein the eye-gesture model is applicable to subsequent proximity-sensor data for detection of the eye gesture based on subsequent proximity-sensor data corresponding to wrinkles in the skin at the side of the eye.
地址 Mountain View CA US