FIELD: object tracking algorithms.
SUBSTANCE: invention relates to an object tracking algorithm using neural networks for processing video streams. The claimed method includes the formation of a training data set consisting of images of an object, bringing the images into a format for input into a neural network, selecting the desired area on the images, introducing the resulting training data set into a convolutional neural network, training the convolutional neural network, obtaining a set of coefficients, introducing the studied images into a trained convolutional neural network, object recognition on the studied images.
EFFECT: increasing the reliability of object detection and increasing the speed of object recognition.
3 cl, 1 dwg
| Title | Year | Author | Number |
|---|---|---|---|
| INTELLIGENT SYSTEM FOR DETECTING AND PREDICTING EVENTS BASED ON NEURAL NETWORKS | 2021 |
|
RU2797748C2 |
| METHOD FOR CREATING COMBINED NEURAL NETWORK CASCADES WITH COMMON FEATURE EXTRACTION LAYERS AND WITH MULTIPLE OUTPUTS, TRAINED ON DIFFERENT DATASETS SIMULTANEOUSLY | 2021 |
|
RU2779408C1 |
| DEVICE OF CASCADE PROCESSING OF A STREAM OF IMAGES BY MEANS OF CONVOLUTIONAL NEURAL NETWORK | 2017 |
|
RU2651147C1 |
| METHOD FOR PERSONAL IDENTIFICATION BASED ON THE HAND VEIN PATTERN | 2020 |
|
RU2761776C1 |
| METHOD FOR IDENTIFICATION OF PERSON BY PATTERN OF VEINS OF PALM | 2020 |
|
RU2788590C1 |
| DRONE PROTECTION DEVICE | 2023 |
|
RU2813389C1 |
| METHOD FOR DETECTING A FACE IN ACCESS MONITORING AND CONTROL SYSTEMS | 2021 |
|
RU2765439C1 |
| METHOD AND SYSTEM FOR RECOGNITION OF THE EMOTIONAL STATE OF EMPLOYEES | 2021 |
|
RU2768545C1 |
| METHOD AND SYSTEM FOR DETECTING A PERSON IN A DANGEROUS AREA AND WARNING THEM OF THE DANGER | 2021 |
|
RU2781356C1 |
| METHOD FOR AUDIOVISUAL RECOGNITION OF PERSONAL PROTECTION EQUIPMENT ON HUMAN FACE | 2022 |
|
RU2791415C1 |
