公开(公告)号：US09785837B2

公开(公告)日：2017-10-10

申请号：US14918154

申请日：2015-10-20

Applicant: BAE SYSTEMS Information and Electronic Systems Integration Inc.

Inventor： Michael N. Mercier ,  Joseph M. Schlupf

IPC: G06K9/66 ,  G06K9/00

CPC classification number: G06K9/0063 ,  G06K2009/00644

Abstract: A mechanism for determining atmospheric conditions from an image is described. A mechanism for determining atmospheric conditions includes determining an intensity value for pixels above and below the horizon in an image, calculating a slope between the intensity values for the pixels above the horizon, and a slope between the intensity values for the pixels below the horizon, and determining a difference between the slopes to determine the atmospheric conditions.

公开(公告)号：US20160140426A1

公开(公告)日：2016-05-19

申请号：US14887863

申请日：2015-10-20

Applicant: BAE SYSTEMS Information and Electronic Systems Integration Inc.

Inventor： Michael N. Mercier

IPC: G06K9/72 ,  G06F17/30

CPC classification number: G06K9/72 ,  G06F17/30265 ,  G06K9/00677 ,  G06K2209/27

Abstract: A mechanism for image recognition based on multiple factors is described. A method, system and computer-readable medium for multi-factor image recognition includes using environmental contextual attributes to create likelihood tiers in an image recognition database such that irrelevant entries are excluded from the search. The mechanism described here limits and sorts by contextual likelihood the number of entries to be searched, increasing both the speed and accuracy of the image recognition process.

Abstract translation: 描述了一种基于多因素的图像识别机制。 用于多因素图像识别的方法，系统和计算机可读介质包括使用环境上下文属性来创建图像识别数据库中的似然层，使得不相关的条目被排除在搜索之外。 这里描述的机制通过上下文可能性限制和排序要搜索的条目的数量，增加图像识别过程的速度和准确性。