# US 2022/0284710 A1 · Object detection apparatus and method for vehicle

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

- Number: US 2022/0284710 A1
- Document ID: US20220284710A1
- Status: Published application
- Kind: A1
- Application number: 17/704,036
- Filed: 2022-03-25
- Published: 2022-09-08
- Earliest claimed: 2019-02-26
- Assignees: Hyundai Mobis Co., Ltd.
- Applicants: Hyundai Mobis Co., Ltd
- Inventors: Heung Rae Cho
- Web page: https://patentgrep.com/patent/US20220284710A1

## CPC

- G06T 7/55: from multiple images
- G06T 7/73: using feature-based methods
- G06T 7/97: {Determining parameters from multiple pictures (depth or shape recovery from multiple images G06T7/55; stereo camera calibration G06T7/85)}
- G06T 11/20: Drawing from basic elements
- G06V 10/145: Illumination specially adapted for pattern recognition, e.g. using gratings
- G06V 10/25: Determination of region of interest [ROI] or a volume of interest [VOI]
- G06V 20/56: exterior to a vehicle by using sensors mounted on the vehicle
- 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
- H04N 23/54: Mounting of pick-up tubes, electronic image sensors, deviation or focusing coils
- H04N 23/56: provided with illuminating means
- H04N 23/61: based on recognised objects
- H04N 23/74: by influencing the scene brightness using illuminating means
- H04N 23/90: Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums
- G06T 2207/10016: Video; Image sequence
- G06T 2207/30252: Vehicle exterior; Vicinity of vehicle
- G06T 2210/12: Bounding box
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

An object detection apparatus includes a first camera unit, a second camera unit, and a control unit. The first camera unit includes one or more cameras, and is configured to capture an image around a vehicle. The second camera unit includes one or more cameras, and is configured to capture an image of an area ahead of the vehicle. The control unit is configured to: determine a displacement of a feature point positioned in a common area from the image acquired via the first camera unit; determine a pixel displacement of the feature point in the image acquired via the second camera unit; and determine distance information to an object recognized in the image captured via the second camera unit based on the displacement of the feature point and the pixel displacement of the feature point.

## Claims

### Claim 1

An object detection apparatus comprising:
a first camera unit comprising one or more cameras, the first camera unit being configured to capture an image outside a vehicle;
a second camera unit comprising one or more cameras, the second camera unit being configured to capture an image outside the vehicle, wherein the first camera unit and the second camera unit have a different shooting angle; and
a control unit configured to:
determine a first displacement information of a feature point positioned in a common area from the image acquired via the first camera unit;
determine a second displacement information of the feature point in the image acquired via the second camera unit; and
determine distance information to an object recognized in the image captured via the second camera unit based on the first and second displacement information of the feature point.

### Claim 2 (depends on 1)

The object detection apparatus of claim 1, wherein the control unit is configured to:
determine per-pixel distance information of the image captured via the second camera unit based on the first and second displacement information of the feature point; and
determine the distance information to the recognized object using the per-pixel distance information.

### Claim 3 (depends on 1)

The object detection apparatus of claim 1, wherein the control unit is configured to store per-pixel distance information of the image acquired via the first camera unit as predetermined information.

### Claim 4 (depends on 1)

The object detection apparatus of claim 1, wherein the common area is an area in a shooting area of the first camera unit overlapping a shooting area of the second camera unit.

### Claim 5 (depends on 1)

The object detection apparatus of claim 1, wherein:
the first camera unit comprises a surround view monitor (SVM) camera; and
the second camera unit comprises a multi-function camera (MFC).

### Claim 6 (depends on 1)

The object detection apparatus of claim 1, further comprising:
a lamp module configured to illuminate the common area,
wherein the control unit is configured to generate the feature point in the common area via the lamp module.

### Claim 7 (depends on 1)

The object detection apparatus of claim 1, further comprising:
an illumination sensor configured to detect illuminance outside the vehicle; and
a lamp module configured to illuminate the common area,
wherein the control unit is configured to generate the feature point in the common area via the lamp module in response to the illuminance satisfying a preset reference value.

### Claim 8 (depends on 1)

The object detection apparatus of claim 1, wherein, to generate a bounding box for the object, the control unit is configured to:
couple images of adjacent cameras among the cameras of the first and second camera units to form a coupled image;
perform object recognition on the coupled image; and
generate the bounding box based on the object recognition.

### Claim 9

An object detection method for a vehicle, comprising:
determining, by a control unit, a first displacement information of a feature point positioned in a common area of an image acquired via a first camera unit configured to capture an image outside the vehicle;
determining, by the control unit, a second displacement information of the feature point in an image acquired via a second camera unit configured to capture an image of outside the vehicle wherein the first camera unit and the second camera unit have a different shooting angle; and
determining, by the control unit, distance information to an object recognized in the image captured via the second camera unit based on the first and second displacement information of the feature point.

### Claim 10 (depends on 9)

The object detection method of claim 9, wherein determining the distance information to the object comprises:
determining, by the control unit, per-pixel distance information of the image captured via the second camera unit based on the first and second displacement information of the feature point; and
determining, by the control unit, the distance information to the object using the per-pixel distance information.

### Claim 11 (depends on 9)

The object detection method of claim 9, further comprising:
causing, at least in part, a lamp module to generate the feature point in the common area before determining the displacement of the feature point.

### Claim 12 (depends on 11)

The object detection method of claim 11, further comprising:
detecting, by the control unit, illuminance outside the vehicle via an illuminance sensor before generating the feature point,
wherein the control unit is configured to cause, at least in part, the lamp module to generate the feature point in response to the illuminance satisfying a preset reference value.

### Claim 13 (depends on 9)

The object detection method of claim 9, further comprising:
coupling, by the control unit, images of adjacent cameras among cameras of the first and second camera units; and
generating, by the control unit, a bounding box for an object recognized in the coupled image via object recognition.

### Claim 14 (depends on 13)

The object detection method of claim 13, further comprising:
causing, at least in part, a lamp module to illuminate the entire common area.

### Claim 15

An apparatus, comprising:
at least one processor; and
at least one memory comprising one or more sequences of one or more instructions configured to, in response to being executed via the at least one processor, cause the apparatus at least to:
determine a first displacement information of a feature point via one or more first images, the one or more first images corresponding to an area around a vehicle;
determine a second displacement information of the feature point via one or more second images, the one or more second images corresponding to an area in a path of travel of the vehicle; and
determine distance information to an object in the second image based on the first and second displacement information of the feature point.

### Claim 16 (depends on 15)

The apparatus of claim 15, wherein the feature point is located in an area common to the one or more first images and the one or more second images.

### Claim 17 (depends on 15)

The apparatus of claim 15, wherein the at least one memory and the one or more sequences of one or more instructions are configured to, in response to being executed via the at least one processor, cause the apparatus at least to:
determine per-pixel distance information via the one or more second images based on the first and second displacement information; and
determine the distance information to the object based on the per-pixel distance information.

### Claim 18 (depends on 15)

The apparatus of claim 15, wherein the at least one memory and the one or more sequences of one or more instructions are further configured to, in response to being executed via the at least one processor, cause the apparatus at least to illuminate a portion of the area in the path of travel of the vehicle to generate the feature point.

### Claim 19 (depends on 18)

The apparatus of claim 18, wherein:
the at least one memory and the one or more sequences of one or more instructions are further configured to, in response to being executed via the at least one processor, cause the apparatus at least to detect illuminance of an ambient environment; and
generation of the feature point is in response to satisfaction of a predetermined condition by the illuminance.

### Claim 20 (depends on 15)

The apparatus of claim 15, wherein the at least one memory and the one or more sequences of one or more instructions are further configured to, in response to being executed via the at least one processor, cause the apparatus at least to:
couple a first image among the one or more first images with a second image among the one or more second images; and
generate bounding box information with respect to the object.
