Unmanned aerial vehicle detection method and device
A detection method and unmanned aerial vehicle technology, applied in the field of image processing, can solve the problems of low detection accuracy
Pending Publication Date: 2021-07-20
XIAN TIANHE DEFENCE TECH
View PDF0 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The YOLO algorithm improves the detection speed to a certain extent. However, the accuracy of the YOLO algorithm is related to the number of training sets. If the number of training sets is small, there will be a problem of low detection accuracy caused by the YOLO algorithm.
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
[0028] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
[0029] It should be understood that the term "and / or" used in the description of the present application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations. In addition, in the description of the specification and appended claims of the present application, the terms "first", "...
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 an unmanned aerial vehicle detection method and device, relates to the technical field of image processing, and can effectively improve the detection accuracy of an unmanned aerial vehicle. The method comprises the following steps: determining a first video frame; determining a plurality of reference prediction results corresponding to the first video frame, wherein the plurality of reference prediction results comprise at least two of the following: a first reference prediction result of the first video frame obtained through a YOLO network prediction model related to unmanned aerial vehicle identification; a second reference prediction result of the first video frame obtained according to an unmanned aerial vehicle feature point identification model and a preset distance range between two unmanned aerial vehicle feature sample points; a third reference prediction result obtained by matching the first video frame with a target image corresponding to an unmanned aerial vehicle scene to which the first video frame belongs; and performing unmanned aerial vehicle detection on the first video frame according to the plurality of reference prediction results.
Description
technical field [0001] The present application relates to the technical field of image processing, in particular to a method and device for detecting a drone. Background technique [0002] As a new target detection method, YOLO (you only look once) algorithm can treat the target detection problem as a regression problem of target area prediction and category prediction. The YOLO algorithm improves the detection speed to a certain extent. However, the accuracy of the YOLO algorithm is related to the number of training sets. If the number of training sets is small, there will be a problem of low detection accuracy caused by the YOLO algorithm. Contents of the invention [0003] The embodiment of the present application provides a UAV detection method and device, which can improve the UAV detection accuracy to a certain extent. [0004] In view of this, in the first aspect, the present application provides a drone detection method, including: determining a first video frame;...
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 Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/46G06V20/41G06V2201/07G06F18/253
Inventor 李雪董强刘博孙芯彤邢刚
Owner XIAN TIANHE DEFENCE TECH