# US 12,602,793 B2 · Systems and methods for predicting object location within images and for analyzing the images in the predicted location for object tracking

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

- Number: US 12,602,793 B2
- Document ID: US12602793B2
- Status: Granted
- Kind: B2
- Application number: 17/855,522
- Filed: 2022-06-30
- Published: 2024-01-04
- Granted: 2026-04-14
- Earliest claimed: 2022-06-30
- Assignees: Lenovo Global Technology (United States) Inc.
- Applicants: Lenovo Enterprise Solutions (Singapore) Pte Ltd.
- Inventors: Fred Allison Bower, III; Gary D. Cudak; David W. Cosby; Jian Li
- Web page: https://patentgrep.com/patent/US12602793B2

## CPC

- G06T 7/20: Analysis of motion (motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51)
- G06T 7/215: Motion-based segmentation
- G06T 7/11: Region-based segmentation
- G06T 7/174: involving the use of two or more images
- G06T 7/90: Determination of colour characteristics
- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- G06V 20/60: Type of objects
- G06T 2207/30241: Trajectory
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Systems and methods for predicting object location within images and for analyzing the images in the predicted location for object tracking are disclosed. According to an aspect, a method includes receiving one or more first images captured by an image capture device. The method also includes determining a speed and/or a direction of movement of an object of interest based on the one or more first images. Further, the method includes receiving one or more second images captured by an image capture device. The method also includes predicting an area of location of the object of interest within the one or more second images based on the determined speed and/or direction of movement of the object. Further, the method includes analyzing the one or more second images in the predicted area of location for tracking the object of interest.

## Claims

### Claim 1

A method comprising:
capturing, by an image capture device, first images of a first object and a second object at a first predetermined image sampling rate;
determining a speed and/or a direction of movement of the first object based on one or more of the first images;
determining a contrast color and/or structure of the first object as compared to the second object in the first images;
capturing, by the image capture device, second images of the first object and the second object at a second predetermined image sampling rate different than the first predetermined image sampling rate based on the contrast color and/or structure of the first object as compared to the second object;
predicting an area of location of the first object within the second images captured at the second predetermined image sampling rate based on the determined speed and/or direction of movement of the first object; and
analyzing the second images in only the predicted area of location for tracking the object of interest.

### Claim 2 (depends on 1)

The method of claim 1, wherein the second images are captured subsequent to the capture of the first images.

### Claim 3 (depends on 1)

The method of claim 1, further comprising identifying the object of interest among the first images.

### Claim 4 (depends on 1)

The method of claim 1, further comprising preventing analysis of the second images outside of the predicted area of location.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
determining a contrast in appearance of the first object to areas in one or more of the first images; and
instructing the image capture device to capture the second images at a different image sampling rate than the first predetermined image sampling rate based on the contrast in appearance.

### Claim 6 (depends on 5)

The method of claim 5, wherein determining the contrast in appearance comprises determining a likeness of color and/or structure of the first object with colors and/or structure of the areas in the first images, and
wherein instructing the image capture device comprises instructing the image capture device to capture the second images at the different image sampling rate based on the determined likeness of color and/or structure.

### Claim 7 (depends on 1)

The method of claim 1, wherein the area of location is one of a plurality of areas in the second images, and
wherein the method further comprises:
determining whether the object of interest is in the predicted area; and
in response to determining that the object of interest is not located in the predicted area, determining whether the object of interest is located in another area among the plurality of areas that is adjacent to the predicted area; and
in response to determining that the object of interest is located in the predicted area, implementing the step of analyzing the second images in the predicted area of location.

### Claim 8 (depends on 1)

The method of claim 1, wherein the object of interest is a first object of interest, and
wherein the method further comprises:
determining a speed and/or a direction of movement of a second object of interest based on the first images;
receiving one or more second images captured by an image capture device;
predicting an area of location of the second object of interest within the second images based on the determined speed and/or direction of movement of the second object; and
analyzing the second images in the predicted area of location for tracking the second object of interest.

### Claim 9

A method comprising:
capturing, by an image capture device, first images in accordance with a first image sampling characteristic;
identifying an object of interest among the first images;
determining a speed and/or a direction of movement of the object of interest in relation to one or more other objects among the first images;
determining a contrast color and/or structure of the object as compared to other the one or more other objects and areas in the first images;
capturing, by the image capture device, second images at a second image sampling characteristic that is different than the first image sampling characteristic based on the determined speed and/or direction of movement of the object of interest and the determined contrast of color and/or structure of the object as compared to the one or more other objects and other areas in the first images; and
analyzing the one or more second images for tracking the object of interest.

### Claim 10 (depends on 9)

The method of claim 9, wherein the first and second image sampling characteristic comprises an image sampling rate.

### Claim 11 (depends on 9)

The method of claim 9, wherein the second images are captured subsequent to the capture of the first images.

### Claim 12 (depends on 9)

The method of claim 9, wherein determining the contrast in appearance comprises determining a likeness of color and/or structure of the object of interest with colors and/or structure of the areas in the first images, and
wherein instructing the image capture device comprises instructing the image capture device to capture the second images at the different image sampling rate based on the determined likeness of color and/or structure.