FIELD: computer vision.
SUBSTANCE: claimed solution includes a block for selecting video and the tracking object, a video preprocessing block consisting of a subblock for normalizing the colour component, a subblock for normalizing the white balance in the vicinity of the selected object, a subblock for eliminating the noise component, a subblock for eliminating the influence of camera movement, and also tracking block of the tracked object, consisting of a subblock for calculating inter-frame disparity, a subblock for calculating probabilities, an expert selection system based on a neural network approach, a subblock for visualizing the result, a block for assessing the loss of the tracked object, a block for selecting a method for tracking an object based on the analysis of the frame plot in a sequence of video fragments, containing a neural a network that evaluates which method can provide the highest tracking accuracy and predicts the location of the object by each method.
EFFECT: increase of the accuracy of tracking moving ground and air objects.
1 cl, 4 dwg
| Title | Year | Author | Number |
|---|---|---|---|
| METHOD FOR AUDIOVISUAL RECOGNITION OF PERSONAL PROTECTION EQUIPMENT ON HUMAN FACE | 2022 |
|
RU2791415C1 |
| METHOD AND SYSTEM OF SUPERRESOLUTION BY COMBINED SPARSE APPROXIMATION | 2016 |
|
RU2661537C2 |
| HARDWARE-SOFTWARE COMPLEX DESIGNED FOR TRAINING AND (OR) RE-TRAINING OF PROCESSING ALGORITHMS FOR AERIAL PHOTOGRAPHS OF THE TERRITORY FOR DETECTION, LOCALIZATION AND CLASSIFICATION UP TO TYPE OF AVIATION AND GROUND EQUIPMENT | 2020 |
|
RU2747044C1 |
| METHOD AND APPARATUS FOR VIDEO ENCODING | 2020 |
|
RU2789146C1 |
| SYSTEM AND METHOD FOR DETECTING AND CLASSIFYING MICROORGANISM COLONIES USING IMAGES BASED ON ARTIFICIAL INTELLIGENCE AND COMPUTER VISION TECHNOLOGIES | 2022 |
|
RU2791813C1 |
| METHOD AND DEVICE FOR ALGORITHMS TO RESIST ERRORS IN WIRELESS VIDEO TRANSFER | 2007 |
|
RU2404536C2 |
| SOFTWARE-HARDWARE SYSTEM FOR TESTING SYSTEMS OF AUTOMATIC AND/OR SEMI-AUTOMATIC DETECTION AND LOCALIZATION OF OBJECTS IN VIDEO SEQUENCE | 2018 |
|
RU2714182C1 |
| VIDEO TRACKING METHOD WITH IMPROVED DYNAMIC CHARACTERISTICS AND DEVICE FOR IMPLEMENTATION THEREOF | 2018 |
|
RU2716005C2 |
| SYSTEMS AND METHODS OF TRAINING GENERATIVE-ADVERSARIAL NETWORKS, AS WELL AS USE OF TRAINED GENERATIVE-ADVERSARIAL NETWORKS | 2019 |
|
RU2819619C2 |
| METHOD OF CONTROLLING MOVING OBJECT AND APPARATUS FOR REALISING SAID METHOD | 2011 |
|
RU2476825C2 |
