Stable tracking method for target under complex background
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology for stable tracking and complex backgrounds, applied in the field of stable tracking of targets under complex backgrounds, can solve problems such as noise interference, nonlinear deformation cameras of targets with illumination changes, and few researches on stable tracking methods
Inactive Publication Date: 2018-10-23
XIAN TIANHE DEFENCE TECH
View PDF6 Cites 12 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
However, although many effective video target tracking algorithms have been proposed, they still face many difficulties in practical applications, such as lighting changes in the environment, nonlinear deformation of the target, camera shake, and noise interference in the background. , which poses a great challenge to target tracking
[0003] At the same time, most of the existing target tracking methods can only track the target in a short period of time, and there are few studies on the stable tracking method.
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 more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0071] The target stable tracking method under the complex background of the present invention, such as figure 1 As shown, the method is as follows:
[0072] 1. Obtain the current frame image according to the video image; when tracking for the first time, an initial image containing the tracking target information and a tracking video containing the initial image are required; in the initial image, provide the coordinates of the upper left corner of the tracking target, width, height, etc. information. The tracking target information in the initial image can be provided automatically by a detection algorithm, or can be selected in the initial image by manual framing.
[0073] 2. On the current frame image, take the position of the tracking target in the previous frame image as the center, and select the candidate area;
[0074] 3. Use the classifier model to obtain the response map of the candidate area, and obtain the maximum response value in the response map, and the posi...
Embodiment 2
[0119] On the basis of Embodiment 1, the video in this embodiment adopts the UAV video collected in the field, mainly for real-time detection and tracking of UAV targets for complex scenes such as buildings, bushes and disturbances at low altitudes.
[0120] At the beginning of the video, obtain the tracking target information in the first frame image. Such as figure 2 As shown, this embodiment sends the information of the target in the first frame image to the terminal through the detection algorithm, such as image 3 As shown, the tracking target box is displayed on the first frame image at the same time. The scene in the first frame of the video is relatively complex, and there are interference objects around the tracking target, which brings great difficulty to tracking.
[0121] The second frame image starts to enter the tracking state, and the classifier model generated by the tracking target in the first frame image is used to judge whether the candidate sample in th...
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 discloses a stable tracking method for target under a complex background, and relates to the field of target tracking. The method comprises the following steps that: obtaining the current frame of image of a video image; selecting a candidate area on the current frame of image; obtaining a target position corresponding to a candidate target by a classifier model; carrying out tracking failure judgment on the candidate target; and when the candidate target is the tracking target, carrying out tracking by the coordinate information of the tracking target in the current frame of image, and updating the classifier model to finish the stable tracking of the target in the video image. Through a response diagram oscillation situation between a candidate sample and a classifier model, a tracking losing judgment condition is set, and therefore, whether the target is under the situations including blocking, losing or blurring and the like can be accurately judged. Meanwhile, the historical value of the response value in the response diagram can be used for judging model update, a model drifting situation and a model update frequency are reduced, the tracking target can be accurately selected from the candidate samples from the complex scene, and the target can be quickly and stably tracked.
Description
technical field [0001] The invention relates to the field of target tracking, in particular to a method for stably tracking targets under complex backgrounds. Background technique [0002] Whether in the military or civilian fields, target tracking technology has a wide range of applications. Fully automatic or semi-automatic target tracking tasks in battlefield reconnaissance, low-altitude defense, traffic monitoring, and homeland security can greatly reduce staff and working hours. However, although many effective video target tracking algorithms have been proposed, they still face many difficulties in practical applications, such as lighting changes in the environment, nonlinear deformation of the target, camera shake, and noise interference in the background. , which poses a great challenge to target tracking. [0003] At the same time, most of the existing target tracking methods can only track the target in a short period of time, and there are few researches on the ...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more