Face detection method and device

Abstract

The invention discloses a face detection method and a device. The face detection method comprises an infrared image of a target object acquired by an infrared image sensor; a coordinate region of the human body contour of the target object is extracted from the infrared image; based on the coordinate region, a visible light image sensor is controlled to finish a local exposure of the human body contour, so the exposure of at least a part of the area of the human body contour including the facial area is larger than the exposure of the other areas in the image acquisition range; the local exposure and a collection of a locally exposed visible light image of the target object are finished at the same time; the face detection is applied to the visible light image. According to the face detection method, problems such as slowdowns in performance of the face detection and missing detections in the dark environment are solved effectively. The device has similar advantages.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a face detection method and device capable of improving the performance of face detection in dark light environments. Background technique [0002] With the development of the economy, the speed of urban construction is accelerating, and the rapid development of the Internet has led to a dense population in the city and an increase in the floating population, which has caused urban management problems in urban construction, such as traffic, social security, prevention of key areas, and increasingly prominent cybercrime. Therefore, video surveillance systems are more and more widely used, and how to make the collected images contain high-quality face images has become the focus of research. [0003] The main problem in the current image acquisition is that the image collected in a dark environment is dark and fuzzy, which is not conducive to face detection and recognitio...

AI Technical Summary

Problems solved by technology

[0003] The main problem in the current image acquisition is that the image collected in a dark environment is dark and blurred, which is not conducive to face detection and recognition

At present, in a dark environment, in order to improve the image quality and improve the face detection performance of the equipment, it is mainly realized through the following methods: 1. Adjust the digital gain, analog gain, Parameters such as backlight compensation, wide dynamic range, and image quality parameters such as brightness and contrast are used to improve image quality. However, the defect of this method is that it is difficult to detect faces when the light is too dark; The method of filling light is used for filling light. The disadvantage of this method is that the filling light is not aimed at the face and the brightness of the face and the background image are similar to the detection.

Images