公开(公告)号：US20140126777A1

公开(公告)日：2014-05-08

申请号：US14151717

申请日：2014-01-09

Applicant: AMAZON TECHNOLOGIES, INC.

Inventor： Kenneth M. Karakotsios ,  KAH KUEN FU ,  VOLODYMYR V. IVANCHENKO ,  MINGJING HUANG

IPC: G06K9/00

CPC classification number: G06K9/00255 ,  G06K9/00228 ,  G06K9/0061

Abstract: The computational resources needed to perform processes such as image recognition can be reduced by determining appropriate frames of image information to use for the processing. In some embodiments, infrared imaging can be used to determine when a person is looking substantially towards a device, such that an image frame captured at that time will likely be adequate for facial recognition. In other embodiments, sound triangulation or motion sensing can be used to assist in determining which captured image frames to discard and which to select for processing based on any of a number of factors indicative of a proper frame for processing.

Abstract translation: 可以通过确定用于处理的图像信息的适当帧来减少执行诸如图像识别的处理所需的计算资源。 在一些实施例中，可以使用红外成像来确定人物何时基本上朝向设备观看，使得当时捕获的图像帧将可能足以用于面部识别。 在其他实施例中，可以使用声音三角测量或运动感测来基于指示用于处理的适当帧的多个因素中的任何一个来确定要丢弃哪个捕获的图像帧以及哪个被选择用于处理。