Gender and age identification method for vertical image flow counting

Abstract

The present invention discloses a gender and age identification method for vertical image flow counting. The overhead color image and depth information of the mounting point are obtained by an infrared 3D sensor (RGB-D device); human characteristics information such as image identification and height, shoulder width and head body ratio are used; machine learning methods are adopted to get the gender and age attribute analysis results, current flow count applications can be improved, only the number of people can be counted while the characteristics of their demographic shortcomings cannot be analyzed, and flow of people counting system practicality and product competitiveness can be improved through the provision of multiple demographic information.

Description

technical field [0001] The invention belongs to a gender and age identification method for vertical image people counting, in particular to a technology that can protect visitor analysis, people counting and 3D image recognition. Background technique [0002] At present, the people counting products of other companies suffer from the disadvantage that they can only count the number of people but not analyze the attributes of their customers. To achieve this function, it needs to be assisted by multiple hardware devices. The increase in hardware costs makes it difficult to promote. [0003] In view of the shortcomings derived from the above-mentioned existing methods, the inventor of the present case was eager to improve and innovate, and after years of painstaking research, he finally successfully developed and completed the gender and age identification method of this vertical video people counting method. Contents of the invention [0004] In order to achieve the above p...

AI Technical Summary

Problems solved by technology

[0004] In order to achieve the above purpose, the present invention proposes to provide a gender and age identification method for vertical video people counting, which mainly has a high demand for high-accuracy people counting and customer attribute analysis integration products, and provides a method for vertical people counting The gender and age identification method of the counting system, combined with the innovative gender and age identification method of image recognition and height, shoulder width, and head-to-body ratio, improves the current vertical people counting application, which can only count the number of people but not analyze its shortcomings. Provide multi-customer attribute information to improve the practicability and product competitiveness of the image-based people counting system

Images