Rapid multi-face detection and tracking method based on embedded system

Abstract

The invention discloses a rapid multi-face detection and tracking method based on an embedded system, which comprises the following steps: embedding a camera module and a special coprocessor or a VPUin the embedded system, firstly, carrying out initialization configuration on the embedded system, and carrying out initialization acquisition to obtain a global buffer queue containing face corresponding position information; Face image data are collected through the camera module. preprocessing the face image data, and inputting the face image data into a special coprocessor or a VPU; carrying out deep learning network operation on the face image data by a special coprocessor or a VPU to obtain position information corresponding to the face image data, comparing the position information withthe position information in the global buffer queue, and judging whether the position information matched with the position information exists in the global buffer queue or not; and finally, processing all the obtained global buffer queues of the face image data to obtain face image data with optimal quality, and outputting and storing the face image data. According to the invention, the processing efficiency of the face image data can be effectively improved.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to a fast multi-face detection and tracking method based on an embedded system. Background technique [0002] Based on cost and power consumption considerations, embedded devices, especially surveillance cameras, mostly use low-cost ARM processors as the core processing platform of the system. Compared with the x86 platform, the ARM processor uses the RISC instruction set, which has high execution efficiency and low power consumption. However, the main frequency of the ARM processor is low, the computing resources are limited, and the computing power is weak, so it is difficult to complete complex computing tasks. [0003] Traditional surveillance cameras mainly complete video codec, transmission and other software-level work. With the rapid development of artificial intelligence technology, more and more AI functions, such as face recognition technology, are...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problems of low face recognition accuracy and large amount of recognition calculation in the above-mentioned prior art, the present invention proposes a fast multi-face detection and tracking method based on an embedded system. The specific technical scheme of the method is as follows:

Images