Method and device for detecting whether target object is blocked, electronic equipment and storage medium

一种目标对象、遮挡检测的技术,应用在信息领域,能够解决遮挡检测计算量大、精确度低等问题,达到减少计算量大、减少计算复杂的效果

Active Publication Date: 2018-07-24
TENCENT TECH (SHENZHEN) CO LTD
View PDF3 Cites 39 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, an embodiment of the present invention provides a method for detecting an occlusion of a target object, an electronic device, and a storage medium, so as to solve the problems of large amount of computation and low accuracy of occlusion detection

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 detecting whether target object is blocked, electronic equipment and storage medium
  • Method and device for detecting whether target object is blocked, electronic equipment and storage medium
  • Method and device for detecting whether target object is blocked, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0152] This example proposes a set of methods for automatically detecting facial occlusions. When facial occlusions are detected, it can prompt to change photos or prompt for precautions in taking photos or photography.

[0153] First, by performing face detection marking on input photos or video streams containing faces;

[0154] After the image area where the face is located is determined based on the face detection mark, the block-blocked detection area is selected for the face mark result.

[0155] Carry out skin color detection on the detection area respectively, and automatically determine whether the corresponding detection area is covered by the face based on the skin color detection result.

[0156] If there is occlusion, a prompt to change the photo or adjust the head position can be given according to the scene.

[0157] The detection method provided in this example can effectively detect facial occlusion in most face scenes, and the detection speed is fast.

[01...

example 2

[0202] Such as Figure 10 , this example provides another face occlusion detection method, including:

[0203] Determine whether there is a face photo or an image frame including a face input; the image frame here can be an integral part of the video stream, if it enters the next step, otherwise return to this step;

[0204] The face detection mark is specifically: performing feature detection on a face photo or an image frame including a face;

[0205] Divide the image area of ​​the face according to the marker points to obtain the detection area, and calibrate the skin color area threshold of each detection area according to the statistical samples;

[0206] Perform skin color detection for each detection area;

[0207] Judging whether the detected actual skin color area is greater than the skin color area threshold;

[0208] When the skin color detection area of ​​all partitions is greater than the area threshold, it is determined that the face is unoccluded;

[0209] W...

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 embodiments of the invention disclose a method and a device for detecting whether a target object is blocked, a piece of electronic equipment and a storage medium. The method includes the following steps: determining a first position of a first feature and a second position of a second feature in a target image based on the pixel values of the pixels in the target image, wherein the first feature is the outer contour feature of a target object in the target image, the second feature is the feature of an interfering sub-object in the target object, and the interfering sub-object is a sub-object which interferes with occlusion detection in the target object; determining an image region where the target object is located based on the first position; dividing the image region into at leasttwo detection regions based on the second position; determining whether each detection region satisfies a preset no-occlusion condition based on at least part of the pixel values of each detection region; and if any detection region does not satisfy the preset no-occlusion condition, determining that there is occlusion in the detection region.

Description

technical field [0001] The present invention relates to the field of information technology, and in particular to a method for detecting an obstruction of a target object, electronic equipment and a storage medium. Background technique [0002] In some cases, the electronic device needs to acquire some images including the target object, and sometimes the target object is occluded in the captured image or the image uploaded by the user, which will cause the captured or uploaded image to fail to meet the requirements. [0003] In the prior art, this kind of occlusion detection can generally be manually screened, and the other is based on repeated detection, extraction and iteration of image features to automatically determine whether the current target object is occluded. The former method is obviously inefficient by manual operation. Although the latter method realizes the automatic determination of electronic equipment, it still has problems such as large amount of calculat...

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): G06K9/32G06K9/00
CPCG06V40/171G06V40/161G06V10/255G06V40/162G06V10/7553G06V40/165G06V2201/08G06F18/21375G06F18/2148G06F18/2163G06F18/2411
Inventor 易成李斌
Owner TENCENT TECH (SHENZHEN) CO 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
Try Eureka
PatSnap group products