FIELD: video data processing.
SUBSTANCE: invention relates to analysis of a video image. In the method for determining the predicted state of a traffic light, a video of the traffic light is received, still images of the traffic light are formed, a vector for each lamp in the corresponding still image is determined for each still image by means of a first machine learning algorithm (MLA), thereby forming a set of vectors corresponding to said video. Each vector indicates the predicted probability of each of the set of states of the corresponding lamp. The first MLA is trained based on a set of marked still images of traffic lights. Each marked still image indicates the state of each lamp of the corresponding marked still image. The predicted state of the traffic light is then determined, wherein the second MLA is trained based on a set of marked vectors. Each marked vector is associated with a mark indicating the actual state of this traffic light. The indicator of the predicted state of the traffic light is saved.
EFFECT: determination of the state of the traffic light condition is improved.
20 cl, 8 dwg
| Title | Year | Author | Number |
|---|---|---|---|
| METHODS AND SYSTEMS FOR AUTOMATED DETERMINATION OF OBJECTS PRESENCE | 2019 |
|
RU2744012C1 |
| METHODS AND SYSTEMS FOR AUTOMATED DETECTION OF THE PRESENCE OF OBJECTS | 2019 |
|
RU2769921C2 |
| METHODS AND PROCESSORS FOR STEERING CONTROL OF SELF-DRIVING CAR | 2019 |
|
RU2751734C2 |
| SEARCH INDEX CONSTRUCTION METHOD AND SYSTEM USING MACHINE LEARNING ALGORITHM | 2018 |
|
RU2720954C1 |
| METHOD AND DEVICE FOR CONTROLLING AN UNMANNED VEHICLE | 2021 |
|
RU2805539C2 |
| METHODS AND SYSTEMS FOR DETERMINING THE PRESENCE OF DYNAMIC OBJECTS BY A COMPUTER | 2019 |
|
RU2767955C1 |
| METHOD AND SYSTEM FOR CREATING ANNOTATION VECTORS FOR DOCUMENT | 2017 |
|
RU2720074C2 |
| METHOD AND SYSTEM FOR SPEECH SYNTHESIS FROM TEXT | 2017 |
|
RU2692051C1 |
| METHOD AND SYSTEM FOR DETERMINATION OF RANKED POSITIONS OF ELEMENTS BY RANKING SYSTEM | 2020 |
|
RU2781621C2 |
| METHOD AND SYSTEM FOR PROCESSING USER SPOKEN SPEECH FRAGMENT | 2019 |
|
RU2757264C2 |
