FIELD: physics.
SUBSTANCE: invention relates to a method and a device for detecting the position of an object, a computer device and a storage medium. Method comprises: obtaining image data, the image data comprising a target object; detecting two-dimensional first information about the position of the three-dimensional bounding box upon projection thereof into image data by inputting image data into a two-dimensional detection model, wherein the bounding box is configured to describe the position of the target object in 3D space; mapping the two-dimensional first position information to the three-dimensional second position information; and detecting third information on position of target object based on three-dimensional second information on position, wherein two-dimensional detection model comprises encoder, decoder and prediction network; and detecting two-dimensional first information on the position of the three-dimensional bounding box by inputting image data into the two-dimensional detection model comprises: obtaining a first image feature by encoding image data in an encoder; obtaining a second image feature by decoding the first image feature in a decoder; and mapping - in a prediction network - the second image feature to the two-dimensional first information on the position of the bounding box.
EFFECT: more accurate prediction of two-dimensional information on the position of the bounding box.
15 cl, 11 dwg
| Title | Year | Author | Number | 
|---|---|---|---|
| METHOD AND DEVICE FOR TRAINING A FACE RECOGNITION MODEL AND A DEVICE FOR DETERMINING THE KEY POINT OF THE FACE | 2019 | 
									
  | 
                RU2770752C1 | 
| DATA PROCESSING METHOD AND VISION SYSTEM FOR A ROBOTIC DEVICE | 2021 | 
									
  | 
                RU2782662C1 | 
| SYSTEM, DEVICE AND METHOD FOR CURRENT MONITORING OF VEHICLE, LOADING DEVICE AND CARGO POSITION AND ORIENTATION, WHILE LOADING DEVICE OPERATION | 2012 | 
									
  | 
                RU2623295C2 | 
| EVALUATING THREE-DIMENSIONAL ROAD TOPOLOGY BASED ON VIDEO SEQUENCES BY TRACKING PEDESTRIANS | 2005 | 
									
  | 
                RU2409854C2 | 
| METHOD FOR PROVIDING COMPUTER VISION | 2022 | 
									
  | 
                RU2791587C1 | 
| METHOD FOR CONTROL AND MEASUREMENT OF SAMPLES USING OPTICAL MEANS | 2022 | 
									
  | 
                RU2797717C1 | 
| METHOD OF OBTAINING INFORMATION ON SHAPE AND DIMENSIONS OF THREE-DIMENSIONAL OBJECT FROM ITS TWO-DIMENSIONAL IMAGE | 2022 | 
									
  | 
                RU2816504C1 | 
| METHOD FOR CONTROLLING A ROBOT FOR INTELLIGENT SPRAYING OF MULTIPLE MODELS OF VEHICLES | 2019 | 
									
  | 
                RU2758692C1 | 
| METHODS AND APPARATUS FOR REFINING PREDICTION FOR REFINING MOTION VECTOR ON SIDE OF DECODER USING OPTICAL STREAM | 2020 | 
									
  | 
                RU2820051C2 | 
| SOFTWARE AND HARDWARE COMPLEX DESIGNED FOR PROCESSING AEROSPACE IMAGE OF TERRAIN FOR PURPOSE OF DETECTION, LOCALIZATION AND CLASSIFICATION BY TYPE OF AVIATION AND LAND EQUIPMENT | 2021 | 
									
  | 
                RU2811357C2 | 
Authors
Dates
2025-04-28—Published
2021-08-09—Filed