FIELD: digital image processing.
SUBSTANCE: invention relates to digital image processing, in particular to the detection of target designation objects in images obtained from optoelectronic systems of unmanned aerial vehicles (UAVs) and their auto-tracking. Disclosed is a method for detection and auto-tracking of objects. The method analyzes the distance of each area of the target designation object from the target designation point and whether the target designation point belongs to the found area. Small areas are combined. The target designation area is divided into several rectangular areas. The center of these rectangular areas is at the target designation point. The procedure of the mathematical morphological description of the target designation object is carried out. Areas in which the target designation point is not located are excluded. Likewise, areas less than the minimum area of the object are excluded. Initial training of the object model representation is performed and the corresponding classifier is trained. The object models and the classifier are updated. The results of the calculation of the interframe displacement are combined into a single fragment of the image, which is taken as the current position of the object. A set of positive and negative examples is formed for training object models. The current images are combined. They are combined and compared with the original one. Then the estimation of the distorting function of the current image is calculated. Images are restored and the current angle of misalignment between the interframe displacement of target designation objects and the stabilization system of the optical-electronic means of the UAV apparatus is determined.
EFFECT: increasing the information content of images for identification and auto-tracking of objects in abnormal conditions.
1 cl, 1 dwg
Title | Year | Author | Number |
---|---|---|---|
METHOD AND DEVICE FOR SELECTION OF GROUND AND AIR OBJECTS (MODIFICATIONS) | 1999 |
|
RU2173881C2 |
METHOD OF PROCESSING IMAGE SEQUENCE FOR DETERMINING COORDINATES OF OBJECTS BASED ON BASIC ALGORITHM COMPLEXING | 2014 |
|
RU2575401C1 |
METHOD FOR CORRECTING STRAPDOWN INERTIAL NAVIGATION SYSTEM OF UNMANNED AERIAL VEHICLE OF SHORT RANGE USING INTELLIGENT SYSTEM OF GEOSPATIAL INFORMATION | 2019 |
|
RU2722599C1 |
ANTI-JAMMING METHOD FOR DETECTING SMOKE AND FLAMES IN A COMPLEX BACKGROUND-LIGHT ENVIRONMENT | 2021 |
|
RU2760921C1 |
APPARATUS FOR PROCESSING VIDEO INFORMATION OF SECURITY ALARM SYSTEM | 2009 |
|
RU2484531C2 |
METHOD FOR INTELLIGENT PROCESSING OF ARRAY OF NON-UNIFORM IMAGES | 2021 |
|
RU2767281C1 |
GLARE DETECTION IN THE IMAGE DATA FRAME | 2014 |
|
RU2653461C2 |
RECONSTRUCTION OF THE DOCUMENT FROM DOCUMENT IMAGE SERIES | 2017 |
|
RU2659745C1 |
METHOD OF SEARCH AND DETECTION OF SMALL LOW-RADIATING MOVING RADIATION SOURCES AGAINST SPATIAL NON-UNIFORM BACKGROUND BY OPTICAL-ELECTRONIC DEVICES | 2013 |
|
RU2536082C1 |
VIDEO TRACKING METHOD WITH IMPROVED DYNAMIC CHARACTERISTICS AND DEVICE FOR IMPLEMENTATION THEREOF | 2018 |
|
RU2716005C2 |
Authors
Dates
2021-05-31—Published
2020-08-31—Filed