Face recognition method based on unmanned aerial vehicle

Abstract

The invention belongs to the field of face recognition systems, and particularly relates to a face recognition method based on an unmanned aerial vehicle, which comprises a video stream acquisition / transmission module of an unmanned aerial vehicle end, a video stream receiving module of a ground station, a face recognition module, a face acquisition module and a database interaction module. The video stream acquisition / transmission module of the unmanned aerial vehicle end is responsible for calling the Raspberry Pi to shoot image information in a target area through a UVC camera mounted on aUSB interface; the video stream receiving module of the ground station is mainly responsible for receiving a data packet transmitted from the unmanned aerial vehicle subsystem and decoding the data packet into a format which can be recognized and processed by the human face recognition module; the face recognition module is mainly responsible for a face recognition function; and the ground stationface acquisition module provides a real-time acquisition mode and a batch import mode. The method is high in recognition precision, free of face image distortion and high in anti-interference capability.

Description

technical field [0001] The invention belongs to the field of face recognition, in particular to a face recognition method based on an unmanned aerial vehicle. Background technique [0002] After actual research, it is found that the application of face recognition in the field of public security still has its limitations: on the one hand, the object of collection—face, is under uncertain conditions, including factors such as lighting conditions, angles, and occluders. It will directly lead to the accuracy of face recognition; on the other hand, due to the characteristics of the face collection equipment, that is, the camera, its physical position is fixed once deployed, and the working angle range of the background face recognition system is very limited, so there is a large Blind spots of vision. In addition, due to cost considerations, the public security organs in various places have limited coverage of face recognition cameras, and many needs to obtain live images in a ...

AI Technical Summary

Problems solved by technology

[0002] After actual research, it is found that the application of face recognition in the field of public security still has its limitations: on the one hand, the object of collection—face, is under uncertain conditions, including factors such as lighting conditions, angles, and occluders. It will directly lead to the accuracy of face recognition; on the other hand, due to the characteristics of the face collection equipment, that is, the camera, its physical position is fixed once deployed, and the working angle range of the background face recognition system is very limited, so there is a large blind spot

[0004] But it is regrettable that some local public security departments use the video collected by drones more for macroscopic information acquisition based on artificial visual methods, such as the detection of terrain in group disposal, Determination of personnel size, etc.; statistics of traffic flow in traffic management; taking pictures of the macro-environment of the scene to collect evidence during case investigation, etc. It is relatively rare to directly perform face recognition work on video streams. The reasons are as follows: 1. Market The provided drone products equipped with mature face recognition functions are insufficient; 2. The face recognition algorithm is interfered by unfavorable factors such as the face being at a large angle, resulting in distortion of the face image and poor recognition accuracy

Images