Moving target body surface temperature rapid detection method and system based on thermal infrared video

Abstract

The embodiment of the invention discloses a moving target body surface temperature rapid detection method and system based on a thermal infrared video. The method comprises the following steps: dynamically scanning a detection line, and carrying out temperature scanning on a moving target on a left line and a right line of a detection frame based on each frame of thermal infrared image in a thermal infrared video; determining the position of the left line, the position of the right line and the optimal step length between the offline line and the dynamic scanning detection line according to the temperature scanning result, and determining the position of the offline line according to the optimal step length; adaptively changing the detection frame according to the position of the left line, the position of the right line and the position of the lower line so as to carry out the positioning tracking of the target region of the moving target through the detection frame; and determining the body surface temperature of the moving target according to the temperature of the target position in the target area. According to the embodiment of the invention, the target area can be quickly tracked, the body surface temperature can be accurately detected, and a basis can be provided for daily body temperature monitoring, disease early warning and health evaluation.

Description

technical field [0001] The invention relates to the technical field of temperature detection, in particular to a method and system for quickly detecting body surface temperature of a moving target based on thermal infrared video. Background technique [0002] At present, measuring the temperature of a moving target through thermal infrared technology requires manual calibration. For example: technicians manually delineate the area of ​​interest, and then obtain the temperature of the corresponding location. However, the manual calibration method cannot meet the needs of online detection and consumes a lot of manpower. In recent years, the FDSST tracking method based on correlation filter has excellent tracking performance, but there are differences between visible light video and thermal infrared video. It can achieve better detection results in visible light video, but due to thermal infrared image noise, low image resolution, low contrast, lack of texture, and lack of cl...

AI Technical Summary

Problems solved by technology

It can achieve better detection results in visible light video, but due to thermal infrared image noise, low image resolution, low contrast, lack of texture, and lack of clear edges, the detection and tracking performance is degraded

Images