Check patentability & draft patents in minutes with Patsnap Eureka AI!

Edge calculation and communication system for video monitoring

An edge computing and communication system technology, applied in CCTV systems, computing, image communication, etc., can solve the problems of long development cycle, large R&D investment, high technical difficulty, and achieve the effect of simple interface and high sensitivity

Pending Publication Date: 2020-06-09
利卓创新(北京)科技有限公司
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, high technical difficulty, long development cycle, and large R&D investment have seriously hindered the progress of artificial intelligence in the field of production and life.
First of all, the existing security protocols do not support artificial intelligence algorithm protocols. Traditional security protocols need to be redefined. At the same time, new application logic frameworks need to be developed to support data and communication management in different stages and scenarios of artificial intelligence algorithms.

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
  • Edge calculation and communication system for video monitoring
  • Edge calculation and communication system for video monitoring

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0020] Embodiment 1, see attached figure 1 , an edge computing and communication system for video monitoring, which includes: a resource scheduling module 1, a data storage module 2, a network transmission module 3, a video analysis module 4, an edge computing module and an image processing module 5.

[0021] Resource scheduling module 1 is used to trigger data storage module 2, network transmission module 3, video analysis module 4, edge computing module and image processing module 5, open up space required by the system, read / write system configuration, register / logout System events, enable event monitoring and exception collection, diagnosis, and response mechanisms, open module registration ports and wait for module component registration.

[0022]The edge computing module includes: a target recognition module 6, a target tracking module 7, and a target detection module 8; wherein: the target recognition module 6 is based on deep learning, using a depth-separable convoluti...

Embodiment 2

[0025] Embodiment 2, see attached figure 2 , on the basis of Embodiment 1, each module in the system is further refined:

[0026] The resource scheduling module 1 includes: a module management unit 1.1, a first event management unit 1.2, an exception handling unit 1.3 and a log recording unit 1.4; the module management unit 1.1 is used to manage the functions of other modules in the communication system; the first event management unit 1.2 is used to schedule other modules in the communication system according to events; the exception processing unit 1.3 is used to collect and process abnormal events in other modules in the communication system; the log recording unit 1.4 is used to read or write each module of other modules in the communication system item parameter.

[0027] The data storage module 2 includes: a data storage unit 2.1 and a data reading unit 2.2; the data storage unit 2.1 and the data reading unit 2.2 are respectively used for storing and reading communicat...

Embodiment 3

[0035] Embodiment 3, on the basis of embodiment 1 or 2, the function / parameter of each module in the described system is further limited:

[0036] The event processing period of the resource scheduling module 1 is not less than 20ms.

[0037] The data storage module 2 supports reading and writing of local data files and network database reading and writing. The reading rate of the data storage module 2 is not less than 4096byte / s, and the data storage rate is not less than 2048byte / s.

[0038] The network transmission module 3 supports command transmission based on TCP and data transmission based on UDP, wherein the transmission rate of UDP is not less than 2048byte / s, and the transmission rate of TCP is not less than 1024byte / s.

[0039] The video analysis module 4 supports H264, H265, and MPEG three video decoding capabilities, and supports standard Onvif, Rtsp, and network camera proprietary video protocols.

[0040] The image processing module 5 supports dynamic drawing o...

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 relates to the technical field of safety monitoring, in particular to a video monitoring communication system. The invention discloses an edge calculation and communication system for video monitoring. The edge calculation and communication system comprises a resource scheduling module, a data storage module, a network transmission module, a video analysis module, an edge calculationmodule and an image processing module, according to the invention, an edge end deep learning application framework is combined; the system integrates three intelligent monitoring functions of targetrecognition, target tracking and target detection into a whole through a high-efficiency network transmission mechanism and a mature graphic image processing technology, performs image recognition, tracking and moving target detection on infrared or visible light videos, and transmits detail information such as target classification, labeling and position to a client through a network transmissionmode. According to the invention, abundant and concise use interfaces are provided for users, and a high-reliability, high-sensitivity and remote monitoring image, recognition and tracking solution is provided.

Description

technical field [0001] The invention relates to the technical field of security monitoring, in particular to an intelligent video monitoring communication system. Background technique [0002] With the continuous development of deep learning technology, artificial intelligence has been applied in all aspects of production and life. In particular, the maturation of target recognition, target tracking, and target detection technologies have brought new breakthroughs in security monitoring technology. The application of network camera-based video early warning, target counting, and target tracking has brought security and artificial intelligence closer together. Smart distance. However, high technical difficulty, long development cycle, and large R&D investment have seriously hindered the progress of artificial intelligence in the fields of production and life. First of all, the existing security protocols do not support artificial intelligence algorithm protocols. Traditiona...

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): G06K9/00G06N3/04G06N3/08H04N7/18H04N21/234H04N21/2343
CPCG06N3/08H04N7/18H04N21/23418H04N21/234309G06V20/00G06V20/40G06V2201/07G06N3/045
Inventor 韩杰赵亚峰郑智瑛孙鹏杨浩
Owner 利卓创新(北京)科技有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More