# US 2023/0410515 A1 · Object tracking apparatus, object tracking system, object tracking method, display control device, object detection device, and computer-readable medium

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

- Number: US 2023/0410515 A1
- Document ID: US20230410515A1
- Status: Published application
- Kind: A1
- Application number: 18/239,597
- Filed: 2023-08-29
- Published: 2023-12-21
- Earliest claimed: 2014-09-26
- Assignees: NEC Corporation
- Applicants: NEC Corporation
- Inventors: Ryoma OAMI; Hiroyoshi MIYANO
- Web page: https://patentgrep.com/patent/US20230410515A1

## CPC

- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- G06T 7/246: using feature-based methods, e.g. the tracking of corners or segments
- G06T 7/292: Multi-camera tracking
- G06T 2207/30196: Human being; Person
- G06T 2207/30232: Surveillance
- G06T 2207/30241: Trajectory
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

An object tracking apparatus, method and computer-readable medium for detecting an object from output information of sensors, tracking the object on a basis of a plurality of detection results, generating tracking information of the object represented in a common coordinate system, outputting the tracking information, and detecting the object on a basis of the tracking information.

## Claims

### Claim 1

An object tracking system comprising:
at least one memory storing instructions; and
at least one processor configured to execute the instructions to perform:
generating, via a first detector implemented by the at least one processor, a first detection result of an object from a first image;
generating, via a second detector implemented by the at least one processor, a second detection result of the object from a second image, the second image being different from the first image;
storing the first detection result and the second detection result generated during a predetermined time period in a buffer; and
tracking the object by integrating the first detection result and the second detection result stored in the buffer.

### Claim 2 (depends on 1)

The object tracking system according to claim 1, wherein the at least one processor is further configured to execute the instructions to perform:
acquiring a position of a first object in the first detection result and a position of a second object in the second detection result;
calculating a distance between the position of the first object and the position of the second object; and
associating the first object and the second object in a case where the distance is less than a predetermined value.

### Claim 3 (depends on 2)

The object tracking system according to claim 2, wherein the at least one processor is further configured to execute the instructions to perform:
acquiring an appearance feature of the first object and an appearance feature of the second object;
calculating a similarity between the appearance feature of the first object and the appearance feature of the second object; and
associating the first object and the second object in a case where the similarity is more than a predetermined value.

### Claim 4 (depends on 3)

The object tracking system according to claim 3, wherein the appearance feature is at least either one of a color and a pattern.

### Claim 5 (depends on 2)

The object tracking system according to claim 2, wherein the at least one processor is further configured to execute the instructions to perform:
evaluating accuracy of predicted positions of the first object and the second object; and
deciding a position which makes the accuracy maximum as the position of the object.

### Claim 6 (depends on 5)

The object tracking system according to claim 5, wherein the at least one processor is further configured to execute the instructions to perform:
weighting the positions of the first object and the second object based on the accuracy of the predicted positions determined by angles of cameras which captures the first image and the second image and distances from the cameras to the first object and the second object;
performing a statistical calculation regarding the weighted positions; and
deciding a position indicated by the statistical calculation as the position of the object.

### Claim 7 (depends on 1)

The object tracking system according to claim 1, wherein the at least one processor is further configured to execute the instructions to perform setting the predetermined time period based on a frame interval of cameras which captures the first image and the second image in a case where frame rates of the cameras are same.

### Claim 8

An object tracking method comprising:
generating, via a first detector implemented by the at least one processor, a first detection result of an object from a first image;
generating, via a second detector implemented by the at least one processor, a second detection result of the object from a second image, the second image being different from the first image;
storing the first detection result and the second detection result generated during a predetermined time period in a buffer; and
tracking the object by integrating the first detection result and the second detection result stored in the buffer.

### Claim 9 (depends on 8)

The object tracking method according to claim 8, further comprising:
acquiring a position of a first object in the first detection result and a position of a second object in the second detection result;
calculating a distance between the position of the first object and the position of the second object; and
associating the first object and the second object in a case where the distance is less than a predetermined value.

### Claim 10 (depends on 9)

The object tracking method according to claim 9, further comprising:
acquiring an appearance feature of the first object and an appearance feature of the second object;
calculating a similarity between the appearance feature of the first object and the appearance feature of the second object; and
associating the first object and the second object in a case where the similarity is more than a predetermined value.

### Claim 11 (depends on 10)

The object tracking method according to claim 10, wherein the appearance feature is at least either one of a color and a pattern.

### Claim 12 (depends on 9)

The object tracking method according to claim 9, further comprising:
evaluating accuracy of predicted positions of the first object and the second object; and
deciding a position which makes the accuracy maximum as the position of the object.

### Claim 13 (depends on 12)

The object tracking method according to claim 12, further comprising:
weighting the positions of the first object and the second object based on the accuracy of the predicted positions determined by angles of cameras which captures the first image and the second image and distances from the cameras to the first object and the second object;
performing a statistical calculation regarding the weighted positions; and
deciding a position indicated by the statistical calculation as the position of the object.

### Claim 14 (depends on 8)

The object tracking method according to claim 8, further comprising:
setting the predetermined time period based on a frame interval of cameras which captures the first image and the second image in a case where frame rates of the cameras are same.

### Claim 15

A non-transitory computer-readable medium for storing instructions which, when executed, cause a processor to perform:
generating, via a first detector implemented by the at least one processor, a first detection result of an object from a first image;
generating, via a second detector implemented by the at least one processor, a second detection result of the object from a second image, the second image being different from the first image;
storing the first detection result and the second detection result generated during a predetermined time period in a buffer; and
tracking the object by integrating the first detection result and the second detection result stored in the buffer.

### Claim 16 (depends on 15)

The non-transitory computer-readable medium according to claim 15, for storing instructions which, when executed, cause the processor to perform:
acquiring a position of a first object in the first detection result and a position of a second object in the second detection result;
calculating a distance between the position of the first object and the position of the second object; and
associating the first object and the second object in a case where the distance is less than a predetermined value.

### Claim 17 (depends on 16)

The non-transitory computer-readable medium according to claim 16, for storing instructions which, when executed, cause the processor to perform:
acquiring an appearance feature of the first object and an appearance feature of the second object;
calculating a similarity between the appearance feature of the first object and the appearance feature of the second object; and
associating the first object and the second object in a case where the similarity is more than a predetermined value.

### Claim 18 (depends on 17)

The non-transitory computer-readable medium according to claim 17, wherein the appearance feature is at least either one of a color and a pattern.

### Claim 19 (depends on 16)

The non-transitory computer-readable medium according to claim 16, for storing instructions which, when executed, cause the processor to perform:
evaluating accuracy of predicted positions of the first object and the second object; and
deciding a position which makes the accuracy maximum as the position of the object.

### Claim 20 (depends on 19)

The non-transitory computer-readable medium according to claim 19, for storing instructions which, when executed, cause the processor to perform:
weighting the positions of the first object and the second object based on the accuracy of the predicted positions determined by angles of cameras which captures the first image and the second image and distances from the cameras to the first object and the second object;
performing a statistical calculation regarding the weighted positions; and
deciding a position indicated by the statistical calculation as the position of the object.
