MS-KCF (MobileNet-SSD-kernelized correlation filters) based rapid and stable detection method of human face in image sequence

Abstract

The invention provides an MS-KCF (MobileNet-SSD-kernelized correlation filters) based rapid and stable detection method of a human face in an image sequence. To solve the problem about detection of the human face with larger angle change and very severe shielding in the image sequence, a new automatic DTD (detection-tracking-detection) mode integrating rapid and accurate target detection model MSand rapid tracking model KCF is provided, that is, an MS-KCF human face detection model is provided. The method comprises steps as follows: S1, establishing an MS detection network; S2, detecting a target by use of the MS network; S3, updating the tracking model to predict the position of the next frame of human face target; S4, updating an MS detection network after tracking several frames, and performing redetection and positioning on the human face target; S5, comparing and analyzing experiment results. Experiments prove that the MS-KFC model guarantees the detection stability of the humanface with larger angle change and very severe shielding in the image sequence, and besides, the detection speed is greatly increased.

Description

technical field [0001] The invention belongs to the technical field of machine vision target detection, in particular to a fast and stable face detection method based on MS-KCF in image sequences. Background technique [0002] With the continuous development of computer technology and the continuous improvement of computer performance, face detection technology, as an important branch in the field of computer vision, has also made great breakthroughs. Today, face detection has a wide range of applications in access control systems, intelligent monitoring, and intelligent cameras. Applications. Face detection is also a challenging technology. How to detect faces with large angle changes and serious occlusions in image sequences in real time and stably has become an urgent problem to be solved in applications. At present, the traditional method of using shallow features can no longer meet the needs, so the deep convolutional neural network (Convolutional Neural Network, CNN) ...

AI Technical Summary

Problems solved by technology

This model not only solves the stability problem of face detection with large angle changes and serious occlusion, but also greatly improves the detection speed of face targets in image sequences.

Images