# US 2021/0334527 A1 · Image processing method, image processing apparatus and non-transitory 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 2021/0334527 A1
- Document ID: US20210334527A1
- Status: Published application
- Kind: A1
- Application number: 17/242,287
- Filed: 2021-04-27
- Published: 2021-10-28
- Earliest claimed: 2020-04-28
- Assignees: Roland Corporation
- Applicants: Roland Corporation
- Inventors: Atsushi Kida
- Web page: https://patentgrep.com/patent/US20210334527A1

## CPC

- G06V 40/164: {using holistic features}
- G06T 7/11: Region-based segmentation
- G06T 7/73: using feature-based methods
- G06V 10/25: Determination of region of interest [ROI] or a volume of interest [VOI]
- G06V 20/40: in video content (extracting overlay text G06V20/62; video retrieval G06F16/70; processing of video elementary streams in video servers H04N21/234; processing of video elementary streams in video clients H04N21/44)
- G06V 40/103: {Static body considered as a whole, e.g. static pedestrian or occupant recognition}
- G06V 40/161: {Detection; Localisation; Normalisation}
- H04N 23/611: where the recognised objects include parts of the human body
- H04N 23/635: {Region indicators; Field of view indicators}
- G06T 2207/10016: Video; Image sequence
- G06T 2207/30196: Human being; Person
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

A non-transitory computer readable medium storing an image processing program causing a computer to execute image processing, the image processing program causing the computer to execute: a person storage step of storing a person region that is a region that includes a person detected in a frame image and is smaller than the frame image; an image acquisition step of acquiring the frame image from a moving image; a detection region setting step of setting a detection region that is a region based on the person region stored in the person storage step in the frame image acquired in the image acquisition step; and a person detection step of detecting the person from the detection region set in the detection region setting step.

## Claims

### Claim 1

A non-transitory computer readable medium storing an image processing program causing a computer to execute image processing, the image processing program causing the computer to execute:
a person storage step of storing a person region that is a region that includes a person detected in a frame image and is smaller than the frame image;
an image acquisition step of acquiring the frame image from a moving image;
a detection region setting step of setting a detection region that is a region based on the person region stored in the person storage step in the frame image acquired in the image acquisition step; and
a person detection step of detecting the person from the detection region set in the detection region setting step.

### Claim 2 (depends on 1)

The non-transitory computer readable medium according to claim 1,
wherein the computer further executes a person region acquisition step of acquiring a person region based on the person detected in the person detection step, and
wherein the person storage step is a step of storing the person region set in the person region acquisition step.

### Claim 3 (depends on 1)

The non-transitory computer readable medium according to claim 1,
wherein the computer further executes
a partial image acquisition step of acquiring a partial image that is an image based on the person region stored in the person storage step from the frame image acquired in the image acquisition step, and
a detection image generation step of generating a detection image that is an image based on the partial image acquired in the partial image acquisition step, and
wherein the person detection step is a step of detecting the person from the detection image generated in the detection image generation step.

### Claim 4 (depends on 2)

The non-transitory computer readable medium according to claim 2,
wherein the computer further executes
a partial image acquisition step of acquiring a partial image that is an image based on the person region stored in the person storage step from the frame image acquired in the image acquisition step, and
a detection image generation step of generating a detection image that is an image based on the partial image acquired in the partial image acquisition step, and
wherein the person detection step is a step of detecting the person from the detection image generated in the detection image generation step.

### Claim 5 (depends on 3)

The non-transitory computer readable medium according to claim 3,
wherein the person detection step is a step of detecting the person from the detection image generated in the detection image generation step and detecting the person from the detection region set in the detection region setting step.

### Claim 6 (depends on 4)

The non-transitory computer readable medium according to claim 4,
wherein the person detection step is a step of detecting the person from the detection image generated in the detection image generation step and detecting the person from the detection region set in the detection region setting step.

### Claim 7 (depends on 1)

The non-transitory computer readable medium according to claim 1,
wherein the computer further executes a range setting step of setting a specific range including the person in the frame image acquired in the image acquisition step, and
wherein the person detection step is a step of detecting the person present in a region that satisfies the specific range set in the range setting step and the detection region set in the detection region setting step.

### Claim 8 (depends on 7)

The non-transitory computer readable medium according to claim 7,
wherein the range setting step is a step of setting, as the specific range, a range in which a specific body part of the person in the frame image acquired in the image acquisition step is located, and
wherein the person detection step is a step of detecting the person whose specific body part is present in the region that satisfies the specific range set in the range setting step and the detection region set in the detection region setting step.

### Claim 9 (depends on 1)

The non-transitory computer readable medium according to claim 1,
wherein the computer further executes a non-specific range setting step of setting a non-specific range that is a range not specified as a person region in the frame image acquired in the image acquisition step, and
wherein the person detection step is a step of detecting the person from a region in which the non-specific range set in the non-specific range setting step is excluded from the detection region set in the detection region setting step.

### Claim 10 (depends on 7)

The non-transitory computer readable medium according to claim 7,
wherein the person is a performer, and
wherein the range setting step is a step of setting, as the specific range, a stage on which the person performs in the frame image acquired in the image acquisition step.

### Claim 11 (depends on 8)

The non-transitory computer readable medium according to claim 8,
wherein the range setting step is a step of setting feet of the person as the specific body part.

### Claim 12 (depends on 9)

The non-transitory computer readable medium according to claim 9,
wherein the person is a performer, and
wherein the non-specific range setting step is a step of setting, as the non-specific range, a screen provided around a stage on which the person performs in the frame image acquired in the image acquisition step.

### Claim 13

An image processing apparatus comprising:
a person storage part that stores a person region that is a region that includes a person detected in a frame image and is smaller than the frame image;
an image acquisition part that acquires the frame image from a moving image;
a detection region setting part that sets a detection region that is a region based on the person region stored in the person storage part in the frame image acquired by the image acquisition part; and
a person detection part that detects the person from the detection region set by the detection region setting part.

### Claim 14 (depends on 13)

The image processing apparatus according to claim 13, further comprising:
a person region acquisition part that acquires a person region based on the person detected by the person detection part,
wherein the person storage part stores the person region set by the person region acquisition part.

### Claim 15 (depends on 13)

The image processing apparatus according to claim 13, further comprising:
a partial image acquisition part that acquires a partial image that is an image based on the person region stored in the person storage part from the frame image acquired by the image acquisition part; and
a detection image generation part that generates a detection image that is an image based on the partial image acquired by the partial image acquisition part,
wherein the person detection part detects the person from the detection image generated by the detection image generation part.

### Claim 16 (depends on 14)

The image processing apparatus according to claim 14, further comprising:
a partial image acquisition part that acquires a partial image that is an image based on the person region stored in the person storage part from the frame image acquired by the image acquisition part; and
a detection image generation part that generates a detection image that is an image based on the partial image acquired by the partial image acquisition part,
wherein the person detection part detects the person from the detection image generated by the detection image generation part.

### Claim 17

An image processing method comprising:
storing a person region that is a region that includes a person detected in a frame image and is smaller than the frame image;
acquiring the frame image from a moving image;
setting a detection region that is a region based on the stored person region in the acquired frame image; and
detecting the person from the set detection region.

### Claim 18 (depends on 17)

The image processing method according to claim 17, further comprising:
acquiring the person region based on the person detected from the set detection region,
wherein the storing the person region comprises storing the acquired person region.

### Claim 19 (depends on 17)

The image processing method according to claim 17, further comprising:
acquiring a partial image that is an image based on the stored person region from the acquired frame image; and
generating a detection image that is an image based on the acquired partial image,
wherein the detecting the person from the detection image comprises detecting the person from the generated detection image.

### Claim 20 (depends on 18)

The image processing method according to claim 18, further comprising:
acquiring a partial image that is an image based on the stored person region from the acquired frame image; and
generating a detection image that is an image based on the acquired partial image,
wherein the detecting the person from the detection image comprises detecting the person from the generated detection image.
