Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Target object recognition method and device

A target object and identification method technology, applied in the field of target object identification methods and devices, can solve the problems of high network bandwidth requirements and large traffic consumption, and achieve the effect of saving network traffic and reducing network bandwidth requirements.

Active Publication Date: 2020-09-11
TENCENT TECH (SHENZHEN) CO LTD
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem in the related art that all videos or pictures taken by the shooting terminal need to be uploaded to the cloud server, which requires high network bandwidth and consumes a large amount of traffic, the embodiment of the present invention provides a target object recognition method and device

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
  • Target object recognition method and device
  • Target object recognition method and device
  • Target object recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] In order to make the object, technical solution and advantages of the present invention clearer, the implementation manner of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0033] implementation environment

[0034] Please refer to figure 1 , which shows an implementation environment diagram involved in the target object recognition method provided by some embodiments of the present invention. figure 1 The illustrated implementation environment includes: a shooting terminal 110 and a cloud server 120 ; optionally, the implementation environment may also include a mobile terminal 130 .

[0035] The shooting terminal 110 may be a device with a video or picture shooting function, such as a fixed or mobile camera, a driving recorder, or a sports camera.

[0036] The cloud server 120 may be a server, or may also be a service cluster composed of several servers, or may also be a cloud computing center.

[00...

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 a method and a device for identifying a target object, belonging to the technical field of application of the Internet of Things. The method is used in a shooting terminal, and includes: acquiring n picture frames captured by the shooting terminal; calculating the matching degree between the images of each object contained in the n picture frames and the preset image samples, and obtaining the image corresponding to each object Matching value; among the objects, the image of the object whose corresponding matching value is higher than the preset value is sent to the cloud server, and the cloud server performs image recognition on the image of the object whose corresponding matching value is higher than the preset value to detect the corresponding Whether the object whose matching value is higher than the preset value is the target object. The invention performs simple matching on the shooting terminal to screen out the images that need to be further identified, and uploads the screened images to the cloud server for further identification, so as to meet the needs of rapid identification while reducing the requirements for network bandwidth and saving network traffic. Effect.

Description

technical field [0001] The present invention relates to the technical field of Internet of Things applications, in particular to a target object identification method and device. Background technique [0002] With the continuous development of Internet of Things application technology, in many application scenarios, it is necessary to quickly identify the target object based on the captured image, which puts forward high requirements on the speed and accuracy of recognition. [0003] Existing target object recognition solutions usually rely on the powerful computing power of the cloud to upload the video or pictures taken by the shooting terminal to the cloud server, and the cloud server performs image processing on it and recognizes the target object, and then returns the recognition result to the shooting terminal . [0004] In the prior art, when the cloud server performs target object recognition, all videos or pictures captured by the shooting terminal need to be uploa...

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): G06K9/46G06K9/00
CPCG06V20/48G06V10/443
Inventor 王达峰
Owner TENCENT TECH (SHENZHEN) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products