Back to results
US 11,688,176 B2Granted
Devices and methods for calibrating vehicle cameras
AssigneeNauto, Inc.
InventorsBenjamin Alpert, Alexander Dion Wu
Life of this patent
Estimating the term…
Abstract
An apparatus includes: a first camera configured to view an environment outside a vehicle; and a processing unit configured to receive images generated at different respective times by the first camera; wherein the processing unit is configured to identify objects in front of the vehicle based on the respective images generated at the different respective times, determine a distribution of the identified objects, and determine a region of interest based on the distribution of the identified objects in the respective images generated at the different respective times.
Claims25
An apparatus comprising:
- a first camera configured to view an environment outside a vehicle;
- and
- a processing unit configured to receive images generated at different respective times by the first camera;
- wherein the processing unit is configured to identify objects in front of the vehicle based on the respective images generated at the different respective times, determine a distribution of the identified objects, and determine a region of interest based on the distribution of the identified objects in the respective images generated at the different respective times;
- and
- wherein the objects comprise a first object detected in a first image of the images, and a second object detected in a second image of the images, and wherein the distribution of the identified objects comprises an aggregation of a first area associated with a first position of the first object detected in the first image and a second area associated with a second position of the second object detected in the second image.
3 more elements
An apparatus comprising:
- a first camera configured to view an environment outside a vehicle;
- and
- a processing unit configured to receive images generated at different respective times by the first camera;
- wherein the processing unit is configured to identify objects in front of the vehicle based on the respective images generated at the different respective times, determine a distribution of the identified objects, and determine a region of interest based on the distribution of the identified objects in the respective images generated at the different respective times;
- wherein the apparatus further comprises a non-transitory medium storing a model, wherein the processing unit is configured to identify the objects in front of the vehicle using the model, the model comprising a neural network model;
- and
- wherein the neural network model is trained based on images generated by on-board devices in other vehicles.
4 more elements
An apparatus comprising:
- a first camera configured to view an environment outside a vehicle;
- and
- a processing unit configured to receive images generated at different respective times by the first camera;
- wherein the processing unit is configured to identify objects in front of the vehicle based on the respective images generated at the different respective times, determine a distribution of the identified objects, and determine a region of interest based on the distribution of the identified objects in the respective images generated at the different respective times;
- wherein the processing unit is configured to determine an image crop frame based on the identified objects;
- and
- wherein the processing unit is configured to determine a median position of the identified objects, and determine the image crop frame based on the median position.
4 more elements
An apparatus comprising:
- a first camera configured to view an environment outside a vehicle;
- and
- a processing unit configured to receive images generated at different respective times by the first camera;
- wherein the processing unit is configured to identify leading vehicles in front of the vehicle in the respective images generated at the different respective times, wherein the processing unit is configured to identify the leading vehicles using a neural network model that is trained based on images generated by on-board devices in other vehicles;
- wherein the processing unit is configured to determine identifiers corresponding respectively with the identified leading vehicles in the respective images;
- wherein the processing unit is configured to combine the identifiers associated with the respective images to form a set of identifiers;
- and
- wherein the processing unit is configured to determine a region of interest based on the set of identifiers associated with the respective images, the region of interest being a single area defined with respect to an image frame.
5 more elements
A method performed by an apparatus, comprising:
- receiving images generated at different respective times by a first camera viewing an environment outside a vehicle;
- identifying objects in front of the vehicle based on the respective images generated at the different respective times;
- determining a distribution of the identified objects;
- and
- determining a region of interest based on the distribution of the identified objects in the respective images generated at the different respective times;
- wherein the objects comprise a first object detected in a first image of the images, and a second object detected in a second image of the images, and wherein the distribution of the identified objects comprises an aggregation of a first area associated with a first position of the first object detected in the first image and a second area associated with a second position of the second object detected in the second image.
3 more elements
Dependencies are inferred from the claim text.