# US 2024/0005665 A1 · System and device for counting people in side view image

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

- Number: US 2024/0005665 A1
- Document ID: US20240005665A1
- Status: Published application
- Kind: A1
- Application number: 18/344,825
- Filed: 2023-06-29
- Published: 2024-01-04
- Earliest claimed: 2022-06-29
- Assignees: Hanwha Vision Co., Ltd.
- Applicants: Hanwha Vision Co., Ltd.
- Inventors: Changho SONG; Hyunhak SHIN
- Web page: https://patentgrep.com/patent/US20240005665A1

## CPC

- G06V 10/774: Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
- G06V 20/53: {Recognition of crowd images, e.g. recognition of crowd congestion}
- G06V 10/225: {based on a marking or identifier characterising the area}
- G06V 10/945: {User interactive design; Environments; Toolboxes}
- G06V 40/103: {Static body considered as a whole, e.g. static pedestrian or occupant recognition}
- G06V 40/166: {using acquisition arrangements}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A surveillance camera and a control method for the surveillance camera are disclosed. The present disclosure makes it possible to determine whether at least one of a bounding box for a head region of an objected detected from a side view image and a bounding box for an entire body region thereof intersects a preset counting line, thereby counting people passing through the counting line. In the present disclosure, one or more of a surveillance camera, an autonomous vehicle, a user terminal, and a server may be linked to an artificial intelligence module, a robot, an augmented reality (AR) device, a virtual reality (VT) device, and a 5G service.

## Claims

### Claim 1

A surveillance camera comprising:
an image sensor; and
a processor configured to perform counting as at least one of a first bounding box and a second bounding box intersects at least one preset counting line,
wherein the first bounding box indicates a head region and the second bounding box indicates entire body region, respectively, of a person detected from an image obtained by the image sensor,
wherein, as the first bounding box and the second bounding box originate from the same object, the processor controls the counting to be performed based on only either the first bounding box or the second bounding box.

### Claim 2 (depends on 1)

The surveillance camera of claim 1, wherein the processor determines that the first bounding box and the second bounding box originated from the same object, and the processor links the first and second bounding boxes to each other.

### Claim 3 (depends on 2)

The surveillance camera of claim 2, wherein the processor determines that the first bounding box is contained in the second bounding box, and the processor determines that the first bounding box and the second bounding box originated from the same object.

### Claim 4 (depends on 1)

The surveillance camera of claim 1, wherein the processor performs up-counting as at least one point of the second bounding box intersects the counting line while the first bounding box traverses the counting line.

### Claim 5 (depends on 1)

The surveillance camera of claim 1, wherein the processor selects either the first bounding box or the second bounding box depending on the counting line closest to the object to determine whether the selected bounding box intersects the counting line.

### Claim 6 (depends on 1)

The surveillance camera of claim 1, wherein the processor selects either the first bounding box or the second bounding box depending on the height of the counting line to determine whether the selected bounding box intersects the counting line.

### Claim 7 (depends on 1)

The surveillance camera of claim 1, wherein, as a plurality of different objects simultaneously traverse the counting line, and at least one of the plurality of objects overlaps with at least one other object, for the plurality of overlapping objects, the first bounding box is utilized in determining whether the plurality of overlapping objects intersect the counting line.

### Claim 8 (depends on 7)

The surveillance camera of claim 7, wherein, as there are more first bounding boxes for the plurality of objects than second bounding boxes, the processor determines that the at least one object overlaps with at least one other object.

### Claim 9 (depends on 1)

The surveillance camera of claim 1, wherein, as a plurality of different objects simultaneously traverse the counting line, and no second bounding box is detected from at least one of the plurality of objects, the processor applies a virtual second bounding box and determines whether the virtual second bounding box intersects the counting line.

### Claim 10 (depends on 1)

The surveillance camera of claim 1, wherein the processor recognizes the type of the counted object and outputs an alarm if the object is not authorized for access.

### Claim 11 (depends on 1)

The surveillance camera of claim 1, wherein the counting line is set within the image based on a predetermined user input.

### Claim 12 (depends on 11)

The surveillance camera of claim 11, wherein the processor recognizes an entrance area within the image, and upon receiving an input for designating the entrance area, automatically sets the counting line to a position corresponding to the entrance area,
wherein the processor automatically sets the counting line to the height of the entrance area.

### Claim 13

A control method for a surveillance camera, the control method comprising:
detecting a person in a side view image wherein an entire body of the detected person including a face of the detected person can be recognized;
detecting a head region and entire body region of the detected person;
extracting a first bounding box corresponding to the head region and a second bounding box corresponding to the entire body region;
performing counting as the second bounding box intersects a preset counting line; and
performing counting as the first bounding box intersects the counting line but there is no bounding box linked to the first bounding box.

### Claim 14 (depends on 13)

The control method of claim 13, further comprising linking the first and second bounding boxes to each other as the first bounding box and the second bounding box originate from the same object.

### Claim 15 (depends on 13)

The control method of claim 13, wherein the first bounding box is contained in the second bounding box.

### Claim 16 (depends on 13)

The control method of claim 13, further comprising:
detecting the first bounding box traversing the counting line; and
performing counting as the second bounding box intersects the counting line at at least one point the instant the first bounding box traverses the counting line.

### Claim 17 (depends on 13)

The control method of claim 13, further comprising, as the object is proximate to an end of the preset counting line, selecting the second bounding box to determine whether the second bounding box intersects the counting line and performing counting.

### Claim 18 (depends on 13)

The control method of claim 13, further comprising selecting either the first bounding box or the second bounding box based on the relative heights of the preset counting line and the object to determine whether the selected bounding box intersects the counting line.

### Claim 19

A surveillance camera comprising:
an image sensor; and
a processor that detects a first bounding box and a second bounding box, which indicate two different regions, respectively, of an object detected from a side view image obtained by the image sensor, and performs counting based on the relative positions of the first and second bounding boxes, as at least one of the first and second bounding boxes intersects a counting line as the object traverses the counting line.

### Claim 20 (depends on 19)

The surveillance camera of claim 19, wherein the detected object is a human, and the two different regions include a head region and entire body region of the detected human,
wherein the processor links the first bounding box corresponding to the head region and the second bounding box corresponding to the entire body region to each other, and recognizes the linked first and second bounding boxes as originating from the same detected human.
