Unlock instant, AI-driven research and patent intelligence for your innovation.

Target area detection method, device, terminal and storage medium

A technology of target area and detection method, applied in the computer field, can solve the problems of difficulty in re-detection, target area tracking failure, and exclusion, etc., to achieve ideal detection effect, improve classification accuracy, and subdivide the classification space.

Active Publication Date: 2020-04-24
TENCENT TECH (SHENZHEN) CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, if the position or attitude of the terminal changes greatly during the video shooting process, some images of the video will not include the target area. Even if there is a target area in the image, it is difficult to be re-detected

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 area detection method, device, terminal and storage medium
  • Target area detection method, device, terminal and storage medium
  • Target area detection method, device, terminal and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention more clear, the implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0036] Before the embodiment of the present invention is described in detail, first TLD (Tracking-Learning-Detection, tracking-learning-detection) algorithm is introduced as follows:

[0037] The TLD algorithm is used for long-term tracking of a single object in a video, see figure 1 , the TLD algorithm includes three modules: tracking module, detection module and learning module.

[0038] 1. Tracking module:

[0039] The tracking module is used to track the motion change between any two frames of adjacent images, and determine the position of the target area in the next frame image according to the position of the target area in the previous frame image and the motion change between the two frame images . T...

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 embodiment of the invention discloses a target area detection method, device, terminal and storage medium, belonging to the field of computer technology. The method includes: determining a plurality of sample areas and classification results; obtaining a classifier, which includes a plurality of classification nodes arranged in sequence; according to the classification results of the plurality of sample areas and the plurality of sample areas, the first The classification node is trained. After the first classification node is trained, continue to train the next classification node until the training of multiple classification nodes is completed; when it is determined that the current tracking image does not include the target area, apply the trained classification The device classifies at least one area in the second image after the currently tracked image, and determines the target area in the second image according to the classification result, without detecting each frame of image, reducing unnecessary calculation. And the accuracy of the classifier is improved, which in turn improves the accuracy of the target region.

Description

technical field [0001] The embodiments of the present invention relate to the field of computer technology, and in particular to a target area detection method, device, terminal and storage medium. Background technique [0002] With the rapid development of the Internet and the widespread rise of video social networking, the main type of dissemination of Internet information has gradually evolved from text and pictures to video, and various video processing functions have also appeared one after another, such as video filters, video tagging, etc. , through these video processing functions, some target areas in the video can be personalized, which improves the fun. [0003] In related technologies, when the terminal is playing a video, the user can manually determine the target area in the current image, and the terminal edits the target area in the current image, such as adding stickers to the target area or beautifying the target area. In addition, based on the position of...

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): G06K9/62
CPCG06F18/241G06F18/214
Inventor 姜媚
Owner TENCENT TECH (SHENZHEN) CO LTD