Granted Patent B2

US 12,536,812 · App. 18/599,015 · Granted Jan 27, 2026

Inventors: Long Sha (San Diego, CA); Lezhou Feng (San Diego, CA); Pengfei Chen (San Diego, CA); Panqu Wang (San Diego, CA)

Assignee: CreateAI, Inc.

G06V20/584G06T7/90G06V10/25G06V10/44G06V10/60G06V10/806G06T2207/20132G06V2201/07

Abstract

Claims (80)

1 . A method of driving operation, comprising:

receiving, by a computer located in a vehicle, a first set of images obtained by a first camera over time and a second set of images obtained by a second camera over time, wherein the first camera and the second camera are located on or in the vehicle;

determining, for each image in the first set of images, a first set of features of a first object;

determining, for each image in the second set of images, a second set of features of a second object;

obtaining, in response to determining that the first object is same as the second object, a third set of features of an object as a function of time by combining the first set of features of the first object for the first set of images and the second set of features of the second object for the second set of images;

obtaining a fourth set of features of the object by including one or more features of a light signal of the object determined from the third set of features of the object;

determining one or more characteristics indicated by the light signal of the object from the fourth set of features of the object; and

causing the vehicle to perform a driving related operation on a road based on the one or more characteristics of the object,

wherein the determining the first set of features and the second set of features includes performing following operations for each image from the first set of images and the second set of images:

cropping a region comprising one object from an image, wherein the one object includes the first object or the second object;

obtaining an adjusted region comprising the one object by adjusting the region to have a pre-determined width and a pre-determined height;

obtaining, for the one object, a first array comprising values associated with a plurality of variables that includes:

an order of the image within a time-dependent series of images that include the first set of images or the second set of images,

a camera that obtained the image, and

information associated with the adjusted region;

obtaining a second array that includes a set of features for the one object by analyzing information associated with the adjusted region from the first array, wherein the set of features included of the one object includes the first set of features of the first object or the second set of features of the second object.

2 . The method of claim 1 , wherein the cropping the region includes adding a bounding box around the one object detected from the image and cropping the region comprising the bounding box around the one object.

3 . The method of claim 1 , wherein the information associated with the adjusted region includes:

a width of the adjusted region,

a height of the adjusted region, and

a color component of the image.

4 . The method of claim 1 , wherein the second array includes:

the order of the image within the time-dependent series of images that include the first set of images or the second set of images,

the camera that obtained the image, and

the set of features for the one object.

5 . The method of claim 1 , wherein the third set of features of the object is obtained by combining the second array of the one object for each image from the first set of images and the second set of images.

6 . The method of claim 5 , wherein the combining the second array of the one object for each image from the first set of images and the second set of images is performed based on the order of the image within the time-dependent series of images.

7 . The method of claim 5 , wherein the third set of features includes:

the order of the image within the time-dependent series of images that include the first set of images or the second set of images, and

the set of features for the one object.

8 . An apparatus for vehicle operation, comprising:

a processor configured to implement a method, the processor configured to:

receive, by a computer located in a vehicle, a first set of images obtained by a first camera over time and a second set of images obtained by a second camera over time, wherein the first camera and the second camera are located on or in the vehicle;

determine, for each image in the first set of images, a first set of features of a first object;

determine, for each image in the second set of images, a second set of features of a second object;

obtain, in response to determining that the first object is same as the second object, a third set of features of an object as a function of time by combining the first set of features of the first object for the first set of images and the second set of features of the second object for the second set of images;

obtain a fourth set of features of the object by including one or more features of a light signal of the object determined from the third set of features of the object;

determine one or more characteristics indicated by the light signal of the object from the fourth set of features of the object; and

cause the vehicle to perform a driving related operation on a road based on the one or more characteristics of the object,

wherein the determining the first set of features and the second set of features includes performing following operations for each image from the first set of images and the second set of images:

cropping a region comprising one object from an image, wherein the one object includes the first object or the second object;

obtaining an adjusted region comprising the one object by adjusting the region to have a pre-determined width and a pre-determined height;

obtaining, for the one object, a first array comprising values associated with a plurality of variables that includes:

an order of the image within a time-dependent series of images that include the first set of images or the second set of images,

a camera that obtained the image, and

information associated with the adjusted region;

obtaining a second array that includes a set of features for the one object by analyzing information associated with the adjusted region from the first array, wherein the set of features included of the one object includes the first set of features of the first object or the second set of features of the second object.

9 . The apparatus of claim 8 , wherein the one or more features of the light signal of the object includes information that indicates whether the light signal is on or off.

10 . The apparatus of claim 8 , wherein each of the first set of images and the second set of images comprises a pre-determined number of images.

11 . The apparatus of claim 10 ,

wherein the determine the first set of features is performed in response to a first determination that the first set of images comprises the pre-determined number of images, and

wherein the determine the second set of features is performed in response to a second determination that the second set of images comprises the pre-determined number of images.

12 . The apparatus of claim 8 , wherein the first set of features or the second set of features includes a type of the first object or the second object, whether the light signal of the first object or of the second object is indicated, or a color of the light signal of the first object or of the second object.

13 . The apparatus of claim 8 , wherein each image in the first set of images and the second set of images is associated with a time stamp.

14 . A non-transitory computer readable program storage medium having code stored thereon, the code, when executed by a processor, causing the processor to implement a method, comprising:

receiving, by a computer located in a vehicle, a first set of images obtained by a first camera over time and a second set of images obtained by a second camera over time, wherein the first camera and the second camera are located on or in the vehicle;

determining, for each image in the first set of images, a first set of features of a first object;

determining, for each image in the second set of images, a second set of features of a second object;

obtaining, in response to determining that the first object is same as the second object, a third set of features of an object as a function of time by combining the first set of features of the first object for the first set of images and the second set of features of the second object for the second set of images;

obtaining a fourth set of features of the object by including one or more features of a light signal of the object determined from the third set of features of the object;

determining one or more characteristics indicated by the light signal of the object from the fourth set of features of the object; and

causing the vehicle to perform a driving related operation on a road based on the one or more characteristics of the object,

wherein the determining the first set of features and the second set of features includes performing following operations for each image from the first set of images and the second set of images:

cropping a region comprising one object from an image, wherein the one object includes the first object or the second object;

obtaining an adjusted region comprising the one object by adjusting the region to have a pre-determined width and a pre-determined height;

obtaining, for the one object, a first array comprising values associated with a plurality of variables that includes:

an order of the image within a time-dependent series of images that include the first set of images or the second set of images,

a camera that obtained the image, and

information associated with the adjusted region;

obtaining a second array that includes a set of features for the one object by analyzing information associated with the adjusted region from the first array, wherein the set of features included of the one object includes the first set of features of the first object or the second set of features of the second object.

15 . The non-transitory computer readable program storage medium of claim 14 , wherein the causing the vehicle to perform the driving related operation on the road in response to the determining the one or more characteristics of the object includes:

sending instructions to a brake system of the vehicle to cause the brake system to apply brakes in response to determining that the object has applied brakes and in response to determining that a distance between the object and the vehicle is less than a pre-determined distance.

16 . The non-transitory computer readable program storage medium of claim 14 , wherein the determining the one or more characteristics indicated by the light signal of the object from the fourth set of features of the object includes:

determining that brakes are being applied by the object in response to determining, using the fourth set of features of the object, that the light signal of the object has been on for more than a pre-determined length of time.

17 . The non-transitory computer readable program storage medium of claim 14 , wherein the determining the one or more characteristics indicated by the light signal of the object from the fourth set of features of the object includes:

determining that the object is intending to change lanes from a current lane to another lane on the road in response to determining, using the fourth set of features of the object, that the light signal on the object is periodically switching on and off.

18 . The non-transitory computer readable program storage medium of claim 14 , wherein the determining the one or more characteristics indicated by the light signal of the object from the fourth set of features of the object includes:

determining that the object is an emergency vehicle in response to determining, using the fourth set of features of the object, that a pattern of switching on and off for the light signal of the object is related to the emergency vehicle.

19 . The non-transitory computer readable program storage medium of claim 14 , wherein the determining the one or more characteristics indicated by the light signal of the object from the fourth set of features of the object includes:

determining that the object is indicating an emergency signal upon determining, using the fourth set of features of the object, that a pattern of switching on and off of the light signal of the object indicates the emergency signal.

Assignments (2)

Continuity (2)

References Cited (27)