US 11,636,688 B1Granted

Enhanced vehicle operation

AssigneeFord Global Technologies, LLC

InventorsNaman Kohli, Vidhya Iyer, Sonal Doomra, Anuja Anil Shirsat, Shounak Athavale

Life of this patent

Estimating the term…

Loading patent…

Abstract

A first image is obtained prior to a second image. Upon dividing the second image into a plurality of zones, light characteristic values for each of the plurality of zones are determined based on at least one of a brightness value, a contrast value, and an intensity value for the respective zones. A first difference score for one of the zones is determined based on a difference between corresponding light characteristic values for the one zone in the first and second images. Upon identifying an object in the one zone of the first and second images, a second difference score for the one zone is determined based on determining a difference between respective confidence scores associated with the corresponding identified objects. Upon determining at least one of the first or second difference score is greater than a respective threshold, the vehicle is operated based on the first image.

Claims20

Dependent claims

A system, comprising a computer including a processor and a memory, the memory storing instructions executable by the processor to:

obtain a first image and a second image, wherein the first image is obtained prior to the second image;
upon dividing the second image into a plurality of zones, determine respective light characteristic values for the plurality of zones based on at least one of a brightness value, a contrast value, and an intensity value for the respective zones;
determine a first difference score for one of the zones based on a difference between the light characteristic value for the one zone of the second image and a light characteristic value for a corresponding zone of the first image;
upon identifying an object in the one zone of the first image and identifying the object in the corresponding zone of the second image, determine a second difference score for the one zone based on determining a difference between respective confidence scores associated with the corresponding identified objects;
and
upon determining at least one of the first difference score is greater than a first threshold or the second difference score is greater than a second threshold, operate a vehicle based on the first image.

3 more elements

A method, comprising:

obtaining a first image and a second image, wherein the first image is obtained prior to the second image;
upon dividing the second image into a plurality of zones, determining respective light characteristic values for the plurality of zones based on at least one of a brightness value, a contrast value, and an intensity value for the respective zones;
determining a first difference score for one of the zones based on a difference between the light characteristic value for the one zone in the first image and a light characteristic value for a corresponding zone of the first image;
upon identifying an object in the one zone of the first image and identifying the object in the corresponding zone of the second image, determining a second difference score for the one zone based on determining a difference between respective confidence scores associated with the corresponding identified objects;
and
upon determining at least one of the first difference score is greater than a first threshold or the second difference score is greater than a second threshold, operating a vehicle based on the first image.

3 more elements

Dependencies are inferred from the claim text.

Facts

Application: 17/495,118Filed 6 Oct 2021
Published: US 2023/0105853 A16 Apr 2023
Granted: 25 Apr 2023
Term ends: Not estimatedThe source records don’t support an estimate.

Classification11 codes

G06V 20/56
Context or environment of the image: exterior to a vehicle by using sensors mounted on the vehicle
G06F 18/2163
Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation: partitioning the feature space
G06V 10/50
Extraction of image or video features: by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients…
G06V 10/60
Extraction of image or video features: relating to illumination properties, e.g. using a reflectance or lighting model