发明名称 |
TRAINING DATA GENERATING DEVICE, METHOD, AND PROGRAM, AND CROWD STATE RECOGNITION DEVICE, METHOD, AND PROGRAM |
摘要 |
To provide a training data generating device capable of easily generating a large amount of training data used for machine-learning a dictionary of a discriminator for recognizing a crowd state. A person state determination unit 72 determines a person state of a crowd according to a people state control designation as designation information on a person state of people and an individual person state control designation as designation information on a state of an individual person in the people. A crowd state image synthesis unit 73 generates a crowd state image as an image in which a person image corresponding to the person state determined by the person state determination unit 72 is synthesized with an image at a predetermined size acquired by a background extraction unit 71, and specifies a training label for the crowd state image. |
申请公布号 |
US2016132755(A1) |
申请公布日期 |
2016.05.12 |
申请号 |
US201414899340 |
申请日期 |
2014.05.21 |
申请人 |
NEC CORPORATION |
发明人 |
IKEDA Hiroo |
分类号 |
G06K9/66;G06K9/46;G06K9/00 |
主分类号 |
G06K9/66 |
代理机构 |
|
代理人 |
|
主权项 |
1. A training data generating device comprising:
a background extraction unit for selecting a background image from a plurality of previously-prepared background images, extracting a region in the background image, and enlarging or downsizing the image corresponding to the extracted region to an image at a predetermined size; a person state determination unit for determining a person state of a crowd according to a people state control designation as designation information on a person state of people and an individual person state control designation as designation information on a state of an individual person in the people; and a crowd state image synthesis unit for generating a crowd state image as an image in which a person image corresponding to the person state determined by the person state determination unit is synthesized with the image at a predetermined size acquired by the background extraction unit, specifying a training label for the crowd state image, and outputting a pair of crowd state image and training label. |
地址 |
Tokyo JP |