Intelligent video monitoring system based on deep learning

An intelligent video surveillance and deep learning technology, applied in the computer field, can solve problems such as false detection, inability to concentrate for a long time, and missed detection of important information

Inactive Publication Date: 2021-01-15
SHANDONG UNIV OF SCI & TECH
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since people's attention cannot be concentrated for a long time, it is easy to miss or misdetect important information in the video when using manual analysis
With the rapid development of science and technology, various video devices are gradually popularized, and the number of videos shows an exponential growth trend. It is difficult for traditional methods to carry out effective analysis in this case.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Intelligent video monitoring system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The specific embodiments of the present invention will be further described below in conjunction with the accompanying drawings and specific embodiments:

[0022] combine figure 1 , an intelligent video surveillance system based on deep learning, including image acquisition preprocessing module, pedestrian detection module, pedestrian tracking module, pedestrian analysis module and client module.

[0023] The image acquisition preprocessing module is used to provide input image data to the system and preprocess the image; the image acquisition preprocessing module uses a USB camera or a network IP camera for real-time image acquisition, and preprocesses the collected images. The preprocessing includes Color channel order conversion and image format conversion.

[0024] The pedestrian detection module is used to calibrate the human body in the collected image and return the position coordinates of the center of mass of the human body; the pedestrian detection module use...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an intelligent video monitoring system based on deep learning, and relates to the field of computers. The intelligent video monitoring system based on deep learning comprises an image acquisition preprocessing module, a pedestrian detection module, a pedestrian tracking module, a pedestrian analysis module and a client module. The image acquisition preprocessing module is used for providing input image data for the system and preprocessing an image. And the pedestrian detection module is used for calibrating the human body of the acquired image and returning the mass center position coordinates of the human body. And the pedestrian tracking module is used for tracking pedestrians and generating a tracking track. And the pedestrian analysis module is used for judgingthe acquired data according to an abnormal behavior judgment rule. And the client module is used for displaying a real-time monitoring picture and displaying a detection result. Related ideas and algorithm models in deep learning are utilized to realize 'intellectualization' of video monitoring.

Description

technical field [0001] The invention relates to the field of computers, in particular to an intelligent video monitoring system based on deep learning. Background technique [0002] At present, video surveillance generally has the problem of "only recording but not judging", that is, only recording and saving the monitoring picture, but not able to timely judge and detect the abnormal behavior that may appear in the video. When abnormal behavior occurs, it needs to rely on a lot of manpower and material resources to analyze and judge the video content. Since people's attention cannot be concentrated for a long time, it is easy to cause missed detection or false detection of important information in the video when using manual analysis. With the rapid development of science and technology, various video devices are gradually popularized, and the number of videos shows an exponential growth trend. It is difficult for traditional methods to perform effective analysis in this s...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K9/00G06K9/20G06T7/20
CPCG06T7/20G06T2207/10016G06T2207/20081G06T2207/20084G06T2207/30232G06T2207/20024G06V40/10G06V20/40G06V10/10G06V2201/07
Inventor 杨勇清潘正祥朱淑娟胡家正
Owner SHANDONG UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products