Processing

Please wait...

Settings

Settings

Goto Application

1. CN105160313 - 视频监控中人群行为分析的方法及装置

Office China
Application Number 201510540230.1
Application Date 28.08.2015
Publication Number 105160313
Publication Date 16.12.2015
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
G06N 3/02
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
H04N 7/18
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
NPICTORIAL COMMUNICATION, e.g. TELEVISION
7Television systems
18Closed-circuit television systems, i.e. systems in which the signal is not broadcast
CPC
G06K 9/00778
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
00624Recognising scenes, i.e. recognition of a whole field of perception; recognising scene-specific objects
00771Recognising scenes under surveillance, e.g. with Markovian modelling of scene activity
00778Recognition or static of dynamic crowd images, e.g. recognition of crowd congestion
G06N 3/02
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
H04N 7/18
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
NPICTORIAL COMMUNICATION, e.g. TELEVISION
7Television systems
18Closed circuit television systems, i.e. systems in which the signal is not broadcast
Applicants 中国科学院重庆绿色智能技术研究院
Inventors 匡金骏
颜卓
周曦
王秀英
贺光明
周祥东
石宇
易敏
鲁江坤
Agents 上海光华专利事务所 31219
Title
(ZH) 视频监控中人群行为分析的方法及装置
Abstract
(ZH)

本发明适用于视频监控技术,涉及一种视频监控人群行为分析的方法及装置,所述方法包括:获取视频流,将视频流中每帧图像按行人身高作为尺度基准,分成不同透视程度的图像子块;提取图像子块中的深层神经网络特征;分类优化该深层神经网络特征,得到相应的向量特征集,根据向量特征集,建立不同核函数的SVR数学模型,统计不同密度人群的人数;采用摄像机标定方法,获取深层神经网络特征的坐标向量,对比前后两帧图像子块的深层神经网络特征的位移,根据位移计算人群的移动方向与移动速度。本发明通过对视频监控中的人群进行跟踪分析,获取人群移动的速度、方向、人数等特征信息,同时与历史数据分析比较,对人群态势做出判断,对异常事件报警。