FIELD: computer equipment.
SUBSTANCE: group of inventions can be used to determine presence of objects around a self-controlled vehicle. Method comprises: generating a data tensor of a three-dimensional point cloud which characterizes information contained in data of a three-dimensional point cloud, image forming tensor characterizing information contained in image data, and subsequent analysis of the image tensor to identify the relevant part of the data in the image information relevant to at least one candidate object. Method further comprises combining the three-dimensional point cloud data tensor with the relevant part of the image tensor associated with the relevant part of the data in the image information, to form a combined tensor associated with the surrounding area, and preserve the combined tensor for the purpose of its use by the machine learning algorithm to determine the presence of an object in the surrounding area.
EFFECT: technical result is higher accuracy of vehicle detection.
26 cl, 8 dwg
Title | Year | Author | Number |
---|---|---|---|
METHODS AND SYSTEMS FOR DETERMINING THE PRESENCE OF DYNAMIC OBJECTS BY A COMPUTER | 2019 |
|
RU2767955C1 |
METHOD AND ELECTRONIC DEVICE FOR DETECTING THREE-DIMENSIONAL OBJECTS USING NEURAL NETWORKS | 2021 |
|
RU2776814C1 |
METHODS AND SYSTEMS FOR AUTOMATED DETERMINATION OF OBJECTS PRESENCE | 2019 |
|
RU2744012C1 |
METHOD AND SYSTEM FOR DETERMINING TRAJECTORY OF AUTONOMOUS VEHICLE | 2023 |
|
RU2821107C1 |
METHOD AND SYSTEM FOR DETERMINING DEGREE OF DETERIORATION OF LIDAR DATA | 2021 |
|
RU2826476C1 |
METHOD AND SYSTEM FOR TRAINING MACHINE LEARNING ALGORITHM FOR DETECTING OBJECTS AT A DISTANCE | 2020 |
|
RU2775817C2 |
METHOD AND PROCESSOR FOR CLASSIFICATION OF POINTS ON BOUNDARY OF POLYGONAL SECTION | 2023 |
|
RU2836700C1 |
METHOD OF CONTROLLING ON-BOARD SYSTEMS OF UNMANNED VEHICLES USING NEURAL NETWORKS BASED ON ARCHITECTURE OF TRANSFORMERS | 2024 |
|
RU2841111C1 |
METHODS AND ELECTRONIC DEVICES FOR DETECTING OBJECTS IN THE ENVIRONMENT OF AN UNMANNED VEHICLE | 2021 |
|
RU2767831C1 |
METHOD FOR PROVIDING COMPUTER VISION | 2022 |
|
RU2791587C1 |
Authors
Dates
2021-03-01—Published
2018-09-17—Filed