Unmanned aerial vehicle obstacle recognition method based on monocular vision

Abstract

The invention discloses an unmanned aerial vehicle obstacle recognition method based on monocular vision, and the method comprises the following steps: obtaining an image, collected by a monocular camera, right ahead an unmanned aerial vehicle, and converting the image into a gray image; extracting each feature point from the grayscale image; acquiring another image in front of the unmanned aerialvehicle acquired by the monocular camera, converting the image into a grayscale image, and extracting each feature point from the grayscale image; matching the feature points in the two images, and forming a matching point pair by the two matched feature points; and traversing each matching point pair, and judging whether obstacles corresponding to the unmanned aerial vehicle and the feature points exceed a safe distance or not. According to the method, the calculation amount is low, the calculation speed is greatly increased, the real-time performance is high, the method can still be effective when the flight speed of the unmanned aerial vehicle is high, and the response time needed when the unmanned aerial vehicle encounters a sudden obstacle can be shortened.

Description

Technical field [0001] The invention belongs to the technical field of UAV image processing, and specifically relates to a UAV obstacle recognition method based on monocular vision. Background technique [0002] With the development of UAVs in recent years, the application range of UAV automatic cruise technology has become wider and wider. During the automatic cruise process, the drone is required to automatically recognize and avoid obstacles. Traditional obstacle avoidance methods are mostly based on various sensors. The drone must be equipped with a dedicated module, which increases cost and power consumption and reduces the cruise time. In recent years, with the development of image processing technology, obstacle avoidance methods based on machine vision have begun to emerge; on the other hand, most of the current drones are equipped with cameras, and such methods do not require additional equipment. At present, the commonly used visual obstacle avoidance methods are divid...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the deficiencies in the prior art, and propose a method for identifying obstacles based on monocular vision, which solves the shortcomings of the original ORB algorithm that does not have scale invariance, so that it can be applied to unmanned machine obstacle avoidance

Images