Human motion detection method based on infrared camera

Abstract

The invention provides a human motion detection method based on an infrared camera in the technical field of image recognition. The method comprises the steps: S10, obtaining video frames shot by the infrared camera in real time, converting each video frame into a gray-scale map, and recording the gray-scale map as a map A; step S20, performing mean filtering down-sampling on each image A to obtain an image B; step S30, respectively calculating a difference value of the two continuous graphs B to obtain a graph C; step S40, performing maximum pooling down-sampling on each image C to obtain an image D; step S50, setting a threshold value n, and performing max operation on the continuous graph D based on the threshold value n to obtain a graph E; and step S60, setting a gray threshold, creating a sliding window, traversing each image E by using the sliding window, calculating the sum of gray values in the sliding process of the sliding window, and performing human motion detection based on the sum of gray values and the gray threshold. The method has the advantage that the precision of human motion detection is greatly improved.

Description

Technical field [0001] The present invention relates to the field of image recognition, and in particular, a human motion detection method based on an infrared camera is referred to. Background technique [0002] With the advancement of technology, there have been access control equipment identified, that is, face recognition can be opened to open the door ban. In order to reduce the power consumption of the access control and protection screen, it is conventionally to determine whether there is anyone in front of the infrared sensor. When the infrared intensity is higher than the set threshold, some people will illuminate the screen and simultaneously start the camera. . [0003] However, the traditional method is applied to the outdoor environment, because the infrared intensity in the sun is high, the recognition accuracy of the infrared sensor is easily affected by the sun. Therefore, how to provide a human motion detection method based on an infrared camera, realizing the im...

AI Technical Summary

Problems solved by technology

[0003] However, when the traditional method is applied in an outdoor environment, due to the high intensity of infrared rays in sunlight, the recognition accuracy of infrared sensors is easily affected by sunlight.

Images