Processing

Please wait...

Settings

Settings

Goto Application

1. CN111881757 - Pedestrian re-identification method and device, equipment and medium

Office
China
Application Number 202010605966.3
Application Date 29.06.2020
Publication Number 111881757
Publication Date 03.11.2020
Publication Kind A
IPC
G06K 9/00
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
G06K 9/62
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
CPC
G06K 9/6223
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
6218Clustering techniques
622Non-hierarchical partitioning techniques
6221based on statistics
6223with a fixed number of clusters, e.g. K-means clustering
G06K 9/6256
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
6256Obtaining sets of training patterns; Bootstrap methods, e.g. bagging, boosting
G06V 40/10
Applicants INSPUR ELECTRONIC INFORMATION INDUSTRY CO., LTD.
浪潮电子信息产业股份有限公司
Inventors JIN LIANG
金良
YIN YUNFENG
尹云峰
FAN BAOYU
范宝余
ZHANG RUNZE
张润泽
GUO ZHENHUA
郭振华
JIANG JINZHE
姜金哲
LIANG LINGYAN
梁玲燕
Agents 北京集佳知识产权代理有限公司 11227
Title
(EN) Pedestrian re-identification method and device, equipment and medium
(ZH) 一种行人重识别方法、装置、设备及介质
Abstract
(EN) The invention discloses a pedestrian re-identification method and device, equipment and a medium. The method comprises the steps of extracting features of an original training set by utilizing a firstpedestrian re-identification model; wherein the original training set comprises pedestrian sample images and corresponding label information; performing clustering according to the characteristic space distribution characteristics of the original data set; screening out difficult samples according to a clustering result; adding the difficult sample to the original training set to obtain a targettraining set; training the first pedestrian re-identification model by using the target training set to obtain a second pedestrian re-identification model; and when a to-be-identified pedestrian imageis obtained, outputting a corresponding identification result by using the second pedestrian re-identification model. Therefore, the difficult samples are mined, the spatial distribution of the samples in the original data set is changed through the mined difficult samples, and the attention to the difficult samples can be increased, so that the pedestrian re-identification accuracy is improved.
(ZH) 本申请公开了一种行人重识别方法、装置、设备及介质,包括:利用第一行人重识别模型提取原始训练集的特征;其中,所述原始训练集包括行人样本图像和对应的标签信息;根据所述原始数据集的特征空间分布特性,进行聚类;根据聚类结果筛选出困难样本;将所述困难样本添加至所述原始训练集,得到目标训练集;利用所述目标训练集对所述第一行人重识别模型进行训练,得到第二行人重识别模型;当获取到待识别行人图像,则利用所述第二行人重识别模型输出对应的识别结果。这样,挖掘出困难样本,通过挖掘出的困难样本改变原始数据集中的样本空间分布,能够增加对困难样本的关注度,从而提升行人重识别的准确度。
Related patent documents