# US 2021/0174096 A1 · Partial frame perception

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

- Number: US 2021/0174096 A1
- Document ID: US20210174096A1
- Status: Published application
- Kind: A1
- Application number: 16/706,259
- Filed: 2019-12-06
- Published: 2021-06-10
- Earliest claimed: 2019-12-06
- Assignees: Black Sesame International Holding Limited
- Applicants: Black Sesame International Holding Limited
- Inventors: Yuekun Zhang; Zuoguan Wang; Jizhang Shan; Ying Zhou
- Web page: https://patentgrep.com/patent/US20210174096A1

## CPC

- G06V 20/56: exterior to a vehicle by using sensors mounted on the vehicle
- G06V 20/54: of traffic, e.g. cars on the road, trains or boats
- G06V 20/584: {of vehicle lights or traffic lights}
- B60R 2300/30: characterised by the type of image processing
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- B60R: VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR

## Abstract

A method of partial frame perception, comprising receiving a bottom portion of an inverted image, detecting traffic areas of interest in the bottom portion of the inverted image, streaming the detected traffic areas of interest to a perception processor, receiving a top portion of the inverted image, detecting stationary areas of interest in the top portion of the inverted image and streaming the detected stationary areas of interest to the perception processor.

## Claims

### Claim 1

A method of partial frame perception, comprising:
receiving a bottom portion of an inverted image;
detecting traffic areas of interest in the bottom portion of the inverted image;
streaming the detected traffic areas of interest to a perception processor;
receiving a top portion of the inverted image;
detecting stationary areas of interest in the top portion of the inverted image; and
streaming the detected stationary areas of interest to the perception processor.

### Claim 2 (depends on 1)

The method of partial frame perception of claim 1, wherein the inverted image is received from a reversed camera.

### Claim 3 (depends on 1)

The method of partial frame perception of claim 1, further comprising inverting a non-inverted image based on flipping the non-inverted image.

### Claim 4 (depends on 1)

The method of partial frame perception of claim 1, further comprising asymmetrically filtering the bottom portion of the inverted image.

### Claim 5 (depends on 1)

The method of partial frame perception of claim 1, further comprising asymmetrically filtering the top portion of the inverted image.

### Claim 6 (depends on 1)

The method of partial frame perception of claim 1, further comprising integrating the bottom portion of the inverted image and the top portion of the inverted image.

### Claim 7 (depends on 1)

The method of partial frame perception of claim 1, further comprising storing the top portion of the inverted image to a top frame buffer.

### Claim 8 (depends on 1)

The method of partial frame perception of claim 1, further comprising storing the bottom portion of the inverted image to a bottom frame buffer.

### Claim 9 (depends on 1)

The method of partial frame perception of claim 1, further comprising receiving a non-inverted image and inverting the non-inverted image.

### Claim 10 (depends on 1)

The method of partial frame perception of claim 1, wherein the bottom portion of the inverted image is received from a first camera and the top portion of the inverted image is received from a second camera.

### Claim 11

A method of partial frame perception, comprising:
receiving a bottom portion of an inverted image;
storing the bottom portion of the inverted image to a bottom frame buffer;
detecting traffic areas of interest in the bottom portion of the inverted image;
receiving a top portion of the inverted image;
storing the top portion of the inverted image to a top frame buffer; and
detecting stationary areas of interest in the top portion of the inverted image.

### Claim 12 (depends on 11)

The method of partial frame perception of claim 11, wherein the inverted image is received from a reversed camera.

### Claim 13 (depends on 11)

The method of partial frame perception of claim 11, further comprising inverting a non-inverted image based on flipping the non-inverted image.

### Claim 14 (depends on 11)

The method of partial frame perception of claim 11, further comprising asymmetrically filtering the bottom portion of the inverted image.

### Claim 15 (depends on 11)

The method of partial frame perception of claim 11, further comprising asymmetrically filtering the top portion of the inverted image.

### Claim 16 (depends on 11)

The method of partial frame perception of claim 11, further comprising integrating the bottom portion of the inverted image and the top portion of the inverted image.

### Claim 17 (depends on 11)

The method of partial frame perception of claim 11, further comprising streaming the detected traffic areas of interest to a perception processor.

### Claim 18 (depends on 11)

The method of partial frame perception of claim 11, further comprising streaming the detected stationary areas of interest to a perception processor.

### Claim 19 (depends on 11)

The method of partial frame perception of claim 11, further comprising receiving a non-inverted image and inverting the non-inverted image.

### Claim 20 (depends on 11)

The method of partial frame perception of claim 11, wherein the bottom portion of the inverted image is received from a first camera and the top portion of the inverted image is received from a second camera.
