Unmanned aerial vehicle cruising and tracking system and method based on deep learning technology

Abstract

The invention relates to an unmanned aerial vehicle cruise and tracking system and method based on a deep learning technology. The system comprises a cruise mode and a tracking mode. The cruise mode comprises an image real-time collection module, a dangerous article, dangerous behavior and dangerous personnel detection module, and an warning module which is used for warning a ground command station after discovering dangers. The tracking mode comprises a real-time video acquisition module, a detected dangerous person tracking module, a laser ranging module which is used for detecting the distance between a dangerous person and the unmanned aerial vehicle, a flight control module which adjusts the flight speed and direction of the unmanned aerial vehicle, and a data transmission module which shares the real-time position of the unmanned aerial vehicle with the ground command station and shoots videos in real time. The unmanned aerial vehicle cruise system and the unmanned aerial vehicletracking system provided by the invention are high in operation speed, high in detection precision and flexible in detection area, so that the timeliness of alarm can be guaranteed, the defects of existing monitoring can be overcome, and real-time guarantee is provided for personnel safety in areas such as squares.

Description

technical field [0001] The invention relates to the field of security monitoring and personnel tracking in areas such as public security, parks, squares, etc., and specifically relates to a drone cruising and tracking system and method based on deep learning technology. Background technique [0002] In areas such as railway station plazas, commercial plazas, and park plazas, due to the relatively dense population and active crowds, once dangerous objects, dangerous people, or dangerous behaviors appear, it will bring great harm. monitor. [0003] At present, most squares are equipped with fixed cameras to realize 24-hour surveillance. But there are still the following deficiencies: First, due to the limitation of camera installation, it is generally installed at the edge of the square, and it is difficult to monitor clearly in the central area; secondly, the camera installation often has dead angles, which cannot be monitored, which brings high security risks; Finally, cam...

AI Technical Summary

Problems solved by technology

However, there are still some deficiencies in the following points: First, due to the limitation of camera installation, it is generally installed at the edge of the square, and it is difficult to monitor clearly in the central area; secondly, the camera installation often has dead angles, which cannot be monitored, which brings high potential safety hazards; Finally, cameras often struggle to keep track of people who need special attention

However, there is no effective means to timely and effectively detect and warn dangerous objects, dangerous people or dangerous behaviors in the square area.

Images