# US 2026/0065646 A1 · Method for generating bird's eye view features by utilizing similarity between features including image context and mobility device using the method

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0065646 A1
- Document ID: US20260065646A1
- Status: Published application
- Kind: A1
- Application number: 19/017,912
- Filed: 2025-01-13
- Published: 2026-03-05
- Earliest claimed: 2024-09-03
- Assignees: Hyundai Motor Company; Kia Corporation
- Applicants: Hyundai Motor Company; Kia Corporation
- Inventors: Jin Ho PARK
- Web page: https://patentgrep.com/patent/US20260065646A1

## CPC

- G06V 10/7715: {Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods}
- G06V 20/56: exterior to a vehicle by using sensors mounted on the vehicle
- B60W 60/00: Drive control systems specially adapted for autonomous road vehicles
- G01C 21/3841: {Data obtained from two or more sources, e.g. probe vehicles}
- G06V 10/761: {Proximity, similarity or dissimilarity measures}
- G06V 10/82: using neural networks
- G06V 20/58: Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- B60W: CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- G01C: MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY (measuring liquid level G01F; radio navigation, determining distance or velocity by use of propagation effects, e.g. Doppler effects, propagation time, of radio waves, analogous arrangements using other waves G01S)

## Abstract

A method performed by an apparatus of a vehicle, the method includes: generating one or more image features from one or more images using an image analysis model; producing a reference BEV feature with reference direction information at a reference level and a height BEV feature with height direction information for each level by mapping the image features to a BEV grid; calculating a weight based on information in the reference BEV feature and the height BEV feature; and generating a single enhanced BEV feature by applying the calculated weight to the reference BEV feature and the height BEV feature.

## Claims

### Claim 1

A method performed by an apparatus of a vehicle, the method comprising:
using a processor to:
generate at least one or more image features from at least one or more images through an image analysis model;
produce a reference BEV feature including reference direction information corresponding to a reference level and a BEV feature including height direction information corresponding to each level by mapping the image features and a BEV grid;
calculate a weight based on information included in the reference BEV feature and a height BEV feature; and
generate a single enhanced BEV feature by reflecting the calculated weight in the reference BEV feature and the height BEV feature.

### Claim 2 (depends on 1)

The method of claim 1, wherein the image feature is generated at a plurality of different scales through an operation between feature maps at different scales derived from an adjacent layer among layers constituting image analysis model using the processor.

### Claim 3 (depends on 1)

The method of claim 1, wherein the producing of the reference BEV feature and the height BEV feature generates the reference BEV feature and the height BEV feature for each of the image features by mapping the BEV grid and the at least one or more image features independently using the processor.

### Claim 4 (depends on 1)

The method of claim 1, wherein the mapping of the BEV grid projects a predefined reference point of each grid cell included in the BEV grid onto the image features based on a transform table that is generated based on geometry information of each camera used for capturing the images using the processor.

### Claim 5 (depends on 4)

The method of claim 4, wherein the reference BEV feature is produced by projecting a reference point of each grid cell in the BEV grid defined in a reference direction based on the transform table including a concatenation relationship corresponding to the reference level onto the image features using the processor.

### Claim 6 (depends on 4)

The method of claim 4, wherein the height BEV feature is produced at each interval by projecting a reference point of each grid cell in the BEV grid defined in a height direction based on the transform table including a concatenation relationship corresponding to each level of the height direction onto the image features using the processor.

### Claim 7 (depends on 1)

The method of claim 1, wherein the weight is produced at each level based on a score calculated by performing an inner product of each element included in the reference BEV feature and the height BEV feature at each level using the processor.

### Claim 8 (depends on 7)

The method of claim 7, wherein the generating of the single enhanced BEV feature comprises:
using the processor to:
calculate an aggregate weight by concatenating and element-wise adding the weight obtained by normalizing the score to a predetermined range and a weight of the reference level;
calculate a similarity for each level by computing a ratio of the weight and the weight of the reference level to the aggregate weight; and
generate the enhanced BEV feature by reflecting the similarity in the reference BEV feature and the height BEV feature of a corresponding level and perform element-wise addition.

### Claim 9 (depends on 8)

The method of claim 8, wherein the weight corresponding to the reference level is set to a maximum value.

### Claim 10 (depends on 8)

The method of claim 8, wherein the similarity corresponding to the reference level is set to a maximum value.

### Claim 11

A mobility device comprising:
a memory configured to store at least one instruction; and
a processor configured to execute the at least one instruction stored in the memory based on data obtained from the memory,
wherein the processor is further configured to:
generate at least one or more image features from at least one or more images through an image analysis model,
produce a reference BEV feature including reference direction information corresponding to a reference level and a BEV feature including height direction information corresponding to each level by mapping the image features and a BEV grid,
calculate a weight based on information included in the reference BEV feature and a height BEV feature,
generate a single enhanced BEV feature by reflecting the calculated weight in the reference BEV feature and the height BEV feature, and
perform autonomous driving control by using the enhanced BEV feature.

### Claim 12 (depends on 11)

The mobility device of claim 11, wherein the image feature is generated at a plurality of different scales through an operation between feature maps at different scales derived from an adjacent layer among layers constituting the image analysis model using the processor.

### Claim 13 (depends on 11)

The mobility device of claim 11, wherein the producing of the reference BEV feature and the height BEV feature generates the reference BEV feature and the height BEV feature for each of the image features by mapping the BEV grid and the at least one or more image features independently using the processor.

### Claim 14 (depends on 11)

The mobility device of claim 11, wherein the mapping of the BEV grid projects a predefined reference point of each grid cell included in the BEV grid onto the image features based on a transform table that is generated based on geometry information of each camera used for capturing the images using the processor.

### Claim 15 (depends on 14)

The mobility device of claim 14, wherein the reference BEV feature is produced by projecting a reference point of each grid cell in the BEV grid defined in a reference direction based on the transform table including a concatenation relationship corresponding to the reference level onto the image features using the processor.

### Claim 16 (depends on 14)

The mobility device of claim 14, wherein the height BEV feature is produced at each interval by projecting a reference point of each grid cell in the BEV grid defined in a height direction based on the transform table including a concatenation relationship corresponding to each level of the height direction onto the image features using the processor.

### Claim 17 (depends on 11)

The mobility device of claim 11, wherein the weight is produced at each level based on a score calculated by performing an inner product of each element included in the reference BEV feature and the height BEV feature at each level using the processor.

### Claim 18 (depends on 17)

The mobility device of claim 17, wherein the generating of the single enhanced BEV feature comprises:
using the processor to:
calculate an aggregate weight by concatenating and element-wise adding the weight obtained by normalizing the score to a predetermined range and a weight of the reference level;
calculate a similarity for each level by computing a ratio of the weight and the weight of the reference level to the aggregate weight; and
generate the enhanced BEV feature by reflecting the similarity in the reference BEV feature and the height BEV feature of a corresponding level and perform element-wise addition.

### Claim 19 (depends on 18)

The mobility device of claim 18, wherein the weight corresponding to the reference level is set to a maximum value as a ground truth reference.

### Claim 20 (depends on 18)

The mobility device of claim 18, wherein the similarity corresponding to the reference level is set to a maximum value.
