Screening method for unmanned aerial vehicle autonomous landing candidate area in complex scene without preset target
A technology for complex scenes and candidate areas, applied in scene recognition, computer parts, instruments, etc., can solve problems such as not being widely popularized and reducing the flexibility of autonomous landing of UAVs
Active Publication Date: 2018-07-06
NORTH CHINA UNIVERSITY OF TECHNOLOGY
View PDF3 Cites 7 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Therefore, this method cannot be popularized on a large scale; and because it only recognizes the target, the landing site is limited to the area where the target is laid in advance, which reduces the flexibility of the drone's autonomous landing to a certain extent.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0036] figure 1 It is a flowchart of a method for screening a candidate area for autonomous landing of a drone in a complex scene without a preset target according to an embodiment of the present invention. According to an embodiment of the present invention, a method for screening unmanned aerial vehicle autonomous landing candidate areas in complex scenes without preset targets includes:
[0037] A) Calculation of flatness of landing field of view based on gradient modulus, including:
[0038] A1) Image collection, including the use of an onboard camera to collect images or video equipment to collect continuous frames of images when the drone is above the landing area;
[0039] A2) Landing field flatness calculation, read in color image data img, and read RGB three-channel data img_1, img_2, img_3 respectively, calculate the gradient modulus mod_1, mod_2, mod_3 of RGB three-channel data pixel by pixel, and take img Each pixel position corresponds to the maximum gradient modulus mo...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides a screening method for an unmanned aerial vehicle autonomous landing candidate area in a complex scene without a preset target. The method processes an image in the landing areaacquired in real time. Firstly, landing field leveling calculation based on gradient magnitude is performed on the collected image, and then the preliminary generation of the landing candidate area is realized based on a leveling area. Then, comprehensive determination and screen are performed on the preliminary candidate area by comprehensively using the hue and height confidence coefficient ofthe candidate area. The screening method for the unmanned aerial vehicle autonomous landing candidate area in the complex scene without the preset target has the advantages that the adaptability to complex scene regions is good, the method does not depend on prior target laying, the dependence on the landing environment is lower, and the universality is better. In addition, the candidate area automatically screened by the method usually comprises a number of falling areas, thereby achieving maximum multi-target simultaneous autonomous landing under cluster conditions, and regional adaptivity is provided, thereby greatly improving the range of application and degree of automation of unmanned aerial vehicle autonomous landing.
Description
Technical field [0001] The invention belongs to the application field of image processing drones. It relates to an efficient and reliable method for screening candidate areas for autonomous landing of drones based on image processing without a preset target. Background technique [0002] At present, UAVs play a very important role in various fields of military and civilian use. The main applications in the civilian field include: environmental monitoring, express delivery, film and television shooting, post-disaster rescue, remote sensing mapping, agricultural plant protection, etc. The main applications in the military field include: combat material transportation, battlefield search and rescue, reconnaissance and early warning, tracking and positioning, etc. In the autonomous flight missions of UAVs, autonomous landing has become one of its research hotspots. Autonomous landing is one of the key technologies for achieving fully autonomous flight in the above applications and ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06K9/00G06K9/46G06K9/34G06K9/32
CPCG06V20/13G06V10/255G06V10/267G06V10/56
Inventor 毕福昆杨志华雷明阳侯金元边明明
Owner NORTH CHINA UNIVERSITY OF TECHNOLOGY