Human face detection and tracking method based on unmanned aerial vehicle mobile platform

Abstract

The invention discloses a human face detection and tracking method based on an unmanned aerial vehicle mobile platform and belongs to the field of computer vision. The human face detection and tracking method is mainly characterized by comprising the following steps: an offline studying step: taking a standard human face library as a sample space to carry out offline studying to obtain a human face detector, and taking a target human face library as a sample space to carry out offline studying to obtain a target human face detector; a human face detection steps: receiving a video frame photographed by an unmanned aerial vehicle; extracting a characteristic value of the video frame and conveying the characteristic value into the human face detector; judging whether a human face is detected or not by the human face detector according to the characteristic value; if the characteristic value of the video frame is conveyed into the target human face detector, judging whether a target human face is detected or not by the target human face detector according to the characteristic value; if so, marking the characteristic value of the target human face and adding the characteristic value into a tracking list; and a human face tracking step: predicating the position of the target human face in the next video frame according to a coordinate position in the current video frame according to the target human face.

Description

technical field [0001] The invention belongs to the field of computer vision, and is a real-time face detection and tracking method, in particular a face detection and tracking method based on an unmanned mobile platform for specific crowd objects. Background technique [0002] Due to its intuition, face image has been paid more and more attention as the main means for human to identify a single target. It has been widely used in intelligent monitoring, perception interface, virtual reality, video search, e-commerce and other fields. Face detection and Tracking technology has always been a research hotspot in computer vision. [0003] At present, face detection and tracking are mainly focused on face detection and tracking solutions under fixed vision, but there are few reports on multi-vision and mobile vision face detection and tracking methods for moving platforms such as drones . [0004] This is mainly because the video image sequence collected by a moving platform su...

AI Technical Summary

Problems solved by technology

[0004] This is mainly because the video image sequence collected by a moving platform such as a UAV usually belongs to the face target information in a dynamic background, that is, due to the unavoidable platform shaking of the airborne platform during the flight, this shaking will inevitably cause people There is relative motion between the face target and the background, which will make the face target detection and tracking technology in the moving platform down-view scene more complicated

In addition, the face area of ​​the drone's down-view scene is small, and it is in a complex ground scene background, which has problems such as poor contrast, occlusion, and stereoscopic effects. This makes face detection and tracking in this background application difficult. Technical accuracy and robustness are difficult to guarantee, which is also one of the most prominent difficulties in face detection and tracking on unmanned mobile platforms

Images