# US 2022/0017096 A1 · Field determination for obstacle detection

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

- Number: US 2022/0017096 A1
- Document ID: US20220017096A1
- Status: Published application
- Kind: A1
- Application number: 16/930,489
- Filed: 2020-07-16
- Published: 2022-01-20
- Earliest claimed: 2020-07-16
- Assignees: Rivian IP Holdings, LLC
- Applicants: Rivian IP Holdings, LLC
- Inventors: Vikram Appia; Umit Batur; Qian Song
- Web page: https://patentgrep.com/patent/US20220017096A1

## CPC

- G06V 20/00: Scenes; Scene-specific elements (control of digital cameras H04N23/60)
- G08G 1/166: {for active traffic, e.g. moving vehicles, pedestrians, bikes}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G08G: TRAFFIC CONTROL SYSTEMS (guiding railway traffic, ensuring the safety of railway traffic B61L; arrangement of road signs or traffic signals E01F9/00; radar or analogous systems, sonar systems, lidar systems specially adapted for traffic control G01S13/91, G01S15/88, G01S17/88; {radar or analogous systems, sonar systems, lidar systems specially adapted for anti-collision purposes G01S13/93, G01S15/93, G01S17/93})

## Abstract

Disclosed embodiments include apparatuses, systems, and methods for determining a field in a path of travel of a vehicle for detection of objects in the path of travel. In an illustrative embodiment, an apparatus includes a path identifier configured to identify a path of travel for a vehicle. At least one camera is disposed on the vehicle and is configured to capture image data of an area including the path of travel. A region of interest selector is configured to select a region of interest within the image data. A horizon identifier is configured to identify a horizon in the image data. A field determiner is configured to project the horizon onto the region of interest to isolate a field specified by the path of travel and the horizon, the field being evaluatable for the presence of objects in the path of travel of the vehicle.

## Claims

### Claim 1

An apparatus comprising:
a path identifier configured to identify a path of travel for a vehicle;
at least one camera disposed on the vehicle configured to capture image data of an area including the path of travel;
a region of interest selector configured to select a region of interest within the image data;
a horizon identifier configured to identify a horizon in the image data; and
a field determiner configured to project the horizon onto the region of interest to isolate a field specified by the path of travel and the horizon, the field being evaluatable for the presence of objects.

### Claim 2 (depends on 1)

The apparatus of claim 1, wherein the field determiner includes a neural network executable on a computing system aboard the vehicle.

### Claim 3 (depends on 1)

The apparatus of claim 1, wherein the path identifier is configured to identify the path of travel by using at least one path indicator chosen from:
at least one lane marking on a roadway detected in the image data of the area including the path of travel by one of the at least one camera and additional image data captured by at least one additional camera disposed on the vehicle; and
a route included in pre-mapped roadway data.

### Claim 4 (depends on 3)

The apparatus of claim 3, wherein the field is identified as being laterally specified by the at least one path indicator and transversely specified by the horizon.

### Claim 5 (depends on 1)

The apparatus of claim 1, wherein the horizon identifier is configured to identify the horizon using a gradient-and-color-based approach.

### Claim 6 (depends on 1)

The apparatus of claim 1, wherein:
the at least one camera is configured to capture additional sets of image data as the vehicle continues to travel the path of travel; and
the horizon identifier is further configured to perform at least one action chosen from:
identifying the horizon in each of the additional sets of image data; and
tracking the horizon identified in previously-captured image data.

### Claim 7 (depends on 1)

The apparatus of claim 1, further comprising an object detector configured to compare the field in the image data to a database of object image data representing objects encounterable during travel of the vehicle to determine if at least of the encounterable objects is present in the field.

### Claim 8

A vehicle comprising:
a cabin configured to receive an operator;
a drive system configured to motivate, accelerate, decelerate, stop, and steer the vehicle; and
a vehicle control system configured to perform at least one function chosen from:
autonomously controlling the vehicle without assistance of the operator; and
assisting the operator in controlling the vehicle, wherein the vehicle control system includes:
at least one camera configured to capture image data of an area including a path of travel for a vehicle; and
a computing system including:
a path identifier configured to identify the path of travel;
a region of interest selector configured to select a region of interest within the image data;
a horizon identifier configured to identify a horizon in the image data; and
a field determiner configured to project the horizon onto the region of interest to isolate a field specified by the path of travel and the horizon, the field being evaluatable for the presence of objects.

### Claim 9 (depends on 8)

The vehicle of claim 8, wherein the field determiner includes a neural network executable on the computing system.

### Claim 10 (depends on 8)

The vehicle of claim 8, wherein the path identifier is configured to identify the path of travel by using at least one path indicator chosen from:
at least one lane marking on a roadway detected in the image data of the area including the path of travel by one of the at least one camera and additional image data captured by at least one additional camera disposed on the vehicle; and
a route included in pre-mapped roadway data.

### Claim 11 (depends on 10)

The vehicle of claim 10, wherein the field is identified as being laterally specified by the at least one path indicator and transversely specified by the horizon.

### Claim 12 (depends on 8)

The vehicle of claim 8, wherein the horizon identifier is configured to identify the horizon using a gradient-and-color-based approach.

### Claim 13 (depends on 8)

The vehicle of claim 8, wherein:
the at least one camera is configured to capture additional sets of image data as the vehicle continues to travel the path of travel; and
the horizon identifier is further configured to perform at least one action chosen from:
identifying the horizon in each of the additional sets of image data; and
tracking the horizon identified in previously-captured image data.

### Claim 14 (depends on 8)

The vehicle of claim 8, further comprising an object detector configured to compare the field in the image data to a database of object image data representing objects encounterable during travel of the vehicle to determine if at least of the encounterable objects is present in the field.

### Claim 15

A computer-implemented method comprising:
identifying a path of travel for a vehicle;
capturing image data of an area including the path of travel using a camera disposed on the vehicle;
selecting a region of interest within the image data;
identifying a horizon in the image data; and
projecting the horizon onto the region of interest to isolate a field specified by the path of travel and the horizon, the field being evaluatable for presence of objects in the path.

### Claim 16 (depends on 15)

The computer-implemented method of claim 15, wherein the path of travel is identified by using at least one path indicator chosen from:
at least one lane marking on a roadway detected in the image data of the area including the path of travel by one of the at least one camera and additional image data captured by at least one additional camera disposed on the vehicle; and
a route included in pre-mapped roadway data

### Claim 17 (depends on 16)

The computer-implemented method of claim 16, wherein the field is identified as being laterally specified by the at least one path indicator and transversely specified by the horizon.

### Claim 18 (depends on 15)

The computer-implemented method of claim 15, wherein identifying the horizon is performed using a gradient-and-color-based approach.

### Claim 19 (depends on 15)

The computer-implemented method of claim 15, further comprising:
capturing additional sets of image data with the at least one camera as the vehicle continues to travel the path of travel; and
monitoring the horizon by performing at least one action chosen from:
identifying the horizon in each of the additional sets of image data; and
tracking the horizon identified in previously-captured image data.

### Claim 20 (depends on 15)

The computer-implemented method of claim 15, further comprising comparing the field in the image data to a database of object image data that represents objects encounterable during travel of the vehicle to determine if at least of the encounterable objects is present in the field.
