公开(公告)号：US09098741B1

公开(公告)日：2015-08-04

申请号：US13837621

申请日：2013-03-15

Applicant: Google Inc.

Inventor： Dragomir Anguelov ,  Alexander Toshkov Toshev ,  Deva K. Ramanan ,  Xiangxin Zhu

IPC: G06K9/62 ,  G06K9/00

CPC classification number: G06K9/00536 ,  G06K9/3241 ,  G06K9/4642 ,  G06T7/73 ,  G06T2207/20081

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for object detection are disclosed. Methods can include, for each of a plurality of locations in one or more positive images, image filters are identified, each image filter representing visual features of a location in a positive image (e.g., an image that includes a particular object). Positive location feature scores and negative location feature scores are determined for locations within images. A positive location feature score is based on a similarity between the image filter and feature values for a positive image. A negative location feature score is determined based on a similarity between the image filter and feature values for a negative image. A distinctive location is identified based on the positive and negative location feature scores, and distinguishing feature values for identifying the particular object are identified for the distinctive location.

Abstract translation: 公开了包括在计算机存储介质上编码的用于对象检测的计算机程序的方法，系统和装置。 方法可以包括对于一个或多个正图像中的多个位置中的每一个，识别图像滤波器，每个图像滤波器表示正图像中的位置的视觉特征（例如，包括特定对象的图像）。 确定位置图像中的位置特征得分和负位置特征得分。 正位置特征得分基于图像滤波器和正图像的特征值之间的相似度。 基于图像滤波器和负像的特征值之间的相似度来确定负位置特征得分。 基于正负位置特征得分识别特征位置，识别特定对象的区别特征值用于特征位置。