Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Method and device for associating large and small images in intelligent capture device

An intelligent, image-cutting technology, applied in image communication, closed-circuit television system, selective content distribution, etc., can solve problems such as difficult traceability

Active Publication Date: 2020-12-11
SHENZHEN INFINOVA TECH LTD
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, in some business applications, it is necessary to trace the corresponding background and environmental conditions of the target object in the current environment from the small picture, so the corresponding large picture is found through the small picture. If the smart capture device only saves two kinds of pictures separately, then this Traceability is very difficult

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
  • Method and device for associating large and small images in intelligent capture device
  • Method and device for associating large and small images in intelligent capture device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0080] On the basis of the above scheme, the target object information of each analysis frame extracted in the step S2 is stored in the text of the json format;

[0081] Before the step S3, it includes parsing the text in json format to obtain the timestamp of the analysis frame where the target object is located in the target object information, the target object ID, the target object coordinates and the target object quality score.

[0082] In this embodiment, the text of the json format is used to record the target object information. The Json format is a text format, which is more convenient to read and has a corresponding third-party library for analysis.

Embodiment 2

[0084] In the above, after the step S5 is stored as a small image, compression coding is performed on the small image.

[0085] In this embodiment, the thumbnail image can be compressed by various types of commonly used graphics such as JPEG, so as to reduce the size of the thumbnail image and reduce the storage pressure.

Embodiment 3

[0087] In the above, the step of setting up the first linked list / array or cache for storing the small images is also included. It also includes the step of setting up a second linked list / array or cache for storing large images.

[0088] It can be seen that in this solution, the MJPG stream obtained by the front end is essentially a JPG image. As for the original video stream and video analysis stream used as reference frames for matting, both are data in yuv format, and the video analysis stream is also sent to the smart phone for analysis in the form of image frames. The cutout reference frame is mainly used to cut out the small picture. According to the object coordinates output by the analysis, the corresponding face or vehicle small picture is dug out in the cutout reference frame, which is also in yuv format, and then encoded into a JPG picture. So the final association, as well as the size of the transmission, are all JPG images. Therefore, two linked lists / arrays or...

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 provides a method and a device for associating small and big pictures in an intelligent snapshot device. By applying resources of equipment, a time stamp serves as a link, and a target object is obtained through fast analysis of a video analysis stream; then the small picture is extracted from a video MJPG code stream, and the big picture is obtained from an original video stream; and the big picture and the small picture are associated. Therefore, the space consumption for storing a large amount of videos is avoided, and the requirements of actual application can be met.

Description

technical field [0001] The invention relates to the field of security monitoring, in particular to a method and device for associating large and small images in an intelligent capture device. Background technique [0002] Smart capture device is a front-end video capture device commonly used in modern security. After the front-end sensor (Sensor) collects the video (usually in RAW format), it sends it to the front-end processor, which will be divided into video analysis stream, original stream, and MJPG encoded stream for output. Then through intelligent analysis, not only can save each frame in the video stream (big picture), but also analyze the video in time through the built-in intelligent algorithm, so as to extract the information of the target object (such as a person or vehicle) in each frame of video, The picture (that is, the small picture) is saved for subsequent use to retrieve the picture information of the target object at any time. [0003] However, in some ...

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 Patents(China)
IPC IPC(8): H04N7/18H04N21/2343H04N21/8547
CPCH04N7/18H04N21/2343H04N21/8547
Inventor 肖仁伟
Owner SHENZHEN INFINOVA TECH LTD
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
Eureka Blog
Learn More
PatSnap group products