Face-based temperature detection method, device and system and storage medium

Abstract

The invention provides a face-based temperature detection method. The face-based temperature detection method comprises the following steps: acquiring an RGB image through an RGB image acquisition device and acquiring a thermal image through a thermal image acquisition device; fusing the RGB image and the thermogram to obtain a fused image, wherein the fused image retains feature information of the RGB image and feature information of the thermogram; determining a face part in the fused image according to the feature information of the fused image; performing texture extraction and division on the face part to obtain a target area Mi, wherein i is a positive integer not less than 2; calculating the average temperature value Ti of the target area Mi according to the temperature values corresponding to all the pixel points in the target area Mi so as to obtain the average temperature value Ti corresponding to all the target areas; and weighting all the average temperature values Ti to obtain the final human head temperature. According to the invention, the accuracy of long-distance temperature measurement can be improved.

Description

technical field [0001] The present invention relates to the technical field of temperature detection, in particular to a method, device, system and storage medium for temperature detection based on human faces. Background technique [0002] It should be noted that the contents recorded in this section do not represent all prior art. [0003] Temperature detection is required in many fields, especially in human body temperature detection. In some environments, the accuracy requirements for temperature detection are relatively low, which can be completed by general infrared cameras. However, in a specific environment, the accuracy of temperature detection is very high, and strict screening is required. General infrared cameras have relatively large errors and cannot complete related work. CN104980710A discloses a temperature detection method and a mobile terminal, which performs binarization processing on thermal images, selects pixels whose gray value is greater than a pres...

AI Technical Summary

Problems solved by technology

However, in a specific environment, the accuracy of temperature detection is very high, and strict screening is required. General infrared cameras have relatively large errors and cannot complete related work.

CN104980710A discloses a temperature detection method and a mobile terminal, which performs binarization processing on thermal images, selects pixels whose gray value is greater than a preset value as target pixels, and then obtains the facial temperature according to all target pixels, which This method has certain advantages, but most of the pixels are discarded, and the accuracy still cannot meet the requirements

Images