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

Digital retina software definition camera method and system

A software-defined and camera-based technology, applied in digital transmission systems, closed-circuit television systems, transmission systems, etc., can solve the problems of dynamic target extraction, analysis, update, and video analysis algorithm definition that cannot be used for people and vehicles, and achieve flexible video processing and analysis functions, the effect of good application reliability

Active Publication Date: 2020-08-14
PEKING UNIV
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The embodiment of the present invention provides a digital retina software-defined camera method and system, which solves the problem that the traditional video surveillance cameras cannot extract and analyze dynamic objects such as people and vehicles in the monitoring scene, and the monitoring video cannot be used in large-scale convergence applications. The problem of defining and updating the video analysis algorithm of the camera

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
  • Digital retina software definition camera method and system
  • Digital retina software definition camera method and system
  • Digital retina software definition camera method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] In the process of rapid development, the video surveillance industry is constantly developing in the direction of networking, high-definition, intelligence, and diversification. With the in-depth application of artificial intelligence, cloud computing, big data, and drone technologies, the diversification of video intelligent analysis has become the most distinctive feature of the new generation of video surveillance systems. "Digital Retina End-to-End System" is an intelligent video surveillance platform developed by the National Engineering Laboratory of Digital Video Codec of Peking University (referred to as "the platform" ), the platform integrates many cutting-edge technologies such as visual content analysis, visual feature retrieval, big data analysis, cloud storage, deep learning, etc., and has developed parallel multi-channel video condensed transcoding, visual feature extraction of people and vehicles, fast retrieval of massive visual big data, Multiple techn...

Embodiment 2

[0057] A digital retina software-defined camera method, specifically comprising the following steps:

[0058] Step 1. Add a video intelligent analysis module (including but not limited to Nvidia Jetson TX2) to the video stream output port of the video surveillance camera. Nvidia Jetson TX2 is an AI supercomputer in the embedded field of Nvidia. .

[0059] Step 2. Process the monitoring video stream according to the software-defined camera protocol, including: detecting the format of the input video, extracting camera parameters refers to decapsulating the accessed rtsp monitoring video stream, and extracting the monitoring camera ID information (such as IP address ) and video encoding format (resolution, frame rate, bit rate) parameters, etc.;

[0060] Open a surveillance video, extract camera parameters and decode

[0061] Protocol: zmq-req / rep

[0062] Function: Prompt to open a video, extract camera parameters and decode, and return handle if successful.

[0063]

[...

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 field of security monitoring and artificial intelligence, in particular to a digital retina software definition camera method. The method comprises the following steps: accessing a monitoring video stream, and inputting the monitoring video stream into an intelligent converter; processing the monitoring video stream according to a software-defined camera protocol; monitoring system resources of the intelligent converter; when system resources of the intelligent converter are available, calling a corresponding calculation model for the processed monitoring video stream to perform intelligent calculation; sending the intelligent calculation result to a cloud platform; enabling the cloud platform to store the received data, receive retrieval and feature calculation of the terminal, and return results obtained by retrieval and feature calculation to the terminal for display. The problems that a traditional video monitoring camera cannot extract and analyze dynamic targets such as people and vehicles in a monitoring scene and a video analysis algorithm of the camera cannot be defined and updated during large-scale convergence application of monitoring videosare solved.

Description

technical field [0001] The invention relates to the fields of security monitoring and artificial intelligence, in particular to a digital retina software-defined camera method and system. Background technique [0002] The currently deployed video surveillance system adopts the technical standard H.264 more than ten years ago. The data compression efficiency is low, the construction cost is high, and the application effect is unsatisfactory. The main performances are as follows: [0003] 1) Early standard compression was inefficient. In the case of ensuring video quality, the 30 million cameras deployed in my country are estimated to require hundreds of billions of yuan in storage costs. When the storage space is insufficient, the video is often over-compressed, causing a large number of video images to deteriorate seriously. Unclear key persons and vehicles; [0004] 2) Surveillance video networking is difficult. The number of cameras deployed in many provinces and cities ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): H04N7/18H04N21/6437H04L29/06H04L29/08H04L12/46G06F16/71
CPCG06F16/71H04L12/4633H04L67/06H04L69/08H04N7/18H04N21/6437
Inventor 贾惠柱李源杨长水崔玥解晓东高文
Owner PEKING UNIV
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