Driver face detection method, computer device and computer readable storage medium

Abstract

The invention provides a driver face detection method, a computer device and a computer readable storage medium. The driver face detection method comprises the steps of obtaining a frame of image andinputting the image to a detection network unit, wherein the detection network unit comprises multiple stages of detection modules, and each level of detection module acquires a plurality of face candidate areas and performs non-maximum suppression calculation; calculating the intersection-parallel ratio of the face candidate region with the highest classification score in the face candidate regions output by the detection module to the detection region of the historical information; when the cross-parallel ratio is smaller than a cross-parallel ratio threshold value, applying a next-stage detection module to detect the face candidate area output by the current-stage detection module; and when the cross-parallel ratio is greater than the cross-parallel ratio threshold value, and after non-maximum suppression calculation is performed on the face candidate area output by the current-level detection module, outputting a calculation result of the current-level detection module when the number of the output face candidate areas is not more than one. The invention further provides a computer device and a computer readable storage medium for implementing the driver face detection method.According to the driver face detection method, the calculation amount of face detection can be reduced.

Description

technical field [0001] The present invention relates to the technical field of image recognition, in particular, a driver's face detection method, a computer device and a computer-readable storage medium for realizing the method. Background technique [0002] With the development of intelligent technology, the identification of persons by means of image recognition has been widely used in many fields such as security, among which, the recognition of persons' faces is a key research field in the field of image recognition. [0003] In recent years, with the rapid development of artificial intelligence technology, deep learning neural network has achieved great success in pattern recognition, such as image classification, target detection, image segmentation, speech recognition and machine translation. Notable achievement. In the application of face detection, the performance of deep learning models far exceeds that of traditional machine learning methods. Moreover, in the e...

AI Technical Summary

Problems solved by technology

In addition, the existing face detection system does not make good use of the target motion information between frames. Using this information can perform prediction compensation in the case of missed detection to a certain extent.

Images