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

Method for detecting heads based on vertically-placed depth cameras

A depth camera and detection method technology, applied in the field of image processing and pattern recognition, can solve the problems of unfavorable popularization and application, sensitivity to parameter changes, etc., and achieve the effects of small parameter dependence, convenient operation, and wide adaptability

Inactive Publication Date: 2013-02-13
AUTHENMETRIC
View PDF3 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The above two methods must achieve good results under specific conditions in specific scenarios, and are sensitive to parameter changes.

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 for detecting heads based on vertically-placed depth cameras
  • Method for detecting heads based on vertically-placed depth cameras

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The present invention will be further described below in conjunction with specific drawings and embodiments.

[0031] The whole process of the present invention is: firstly, a pedestrian image in the detection area is acquired by a vertically placed camera, a background model is performed on the acquired depth image, and then a simulated random dripping operation is performed according to the acquired foreground size, and each point is based on The size of the surrounding points determines its running direction and staying position. Finally, the gathering place of all the points is counted, and the area size filtering is performed to obtain the number of people in the scene.

[0032] Such as figure 1 with figure 2 As shown: the human head detection method of the present invention includes the following steps, respectively:

[0033] a. Set up a vertically distributed camera 1 and an active light source matching the camera 1, and use the camera 1 to obtain a depth image of the ...

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 a method for detecting heads based on vertically-placed depth cameras. The method comprises the following steps of: a, setting vertically-distributed cameras and an active light source, and acquiring depth images of passersby; b, performing background modeling on the acquired depth images to acquire corresponding foreground images; c, performing simulated random water droplet sprinkling operation on the foreground images; d, taking the water droplets falling to the foreground images as sampling points, comparing the sampling points with adjacent areas thereof until the sampling points move to local minimum value areas and stay in the local minimum value areas, and adjusting the depth numerical values of the local minimum value areas; and e, obtaining a distribution map of the sampling points, comparing the depth numerical values of the local minimum value areas in the distribution map with a preset threshold value, and filtering the local minimum value areas of which the depth numerical values are smaller than the preset threshold value to obtain required head position areas of the passersby, thus realizing the detection of the number of the passersby. The method is convenient to operate, good in robustness and wide in adaptability.

Description

Technical field [0001] The invention relates to a detection method, in particular to a human head detection method based on a vertical depth camera, which belongs to the technical field of image processing and pattern recognition. Background technique [0002] Head count is an important part of surveillance video applications, such as tourist statistics. The existing human head counting methods based on visible light can be roughly divided into the following three directions: detection-based counting, regression-based counting and unsupervised tracking. Counting based on detection uses a multi-scale sliding frame to classify all positions in the image to be detected to determine whether there are people in the sliding frame; counting based on regression uses a regression method to train an image texture and the number of people in it. The distribution thus counts the number of people in the image; the method based on unsupervised tracking uses the point tracking method to cluste...

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): G06T7/00G06M11/00
Inventor 李子青雷震易东张旭聪
Owner AUTHENMETRIC
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