# US 2019/0244387 A1 · Image detection method, apparatus and system and storage medium

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

- Number: US 2019/0244387 A1
- Document ID: US20190244387A1
- Status: Published application
- Kind: A1
- Application number: 16/175,269
- Filed: 2018-10-30
- Published: 2019-08-08
- Earliest claimed: 2018-02-06
- Assignees: Beijing Kuangshi Technology Co., Ltd.
- Applicants: Beijing Kuangshi Technology Co., Ltd.
- Inventors: Shuchang ZHOU; Yi YANG; Lingwei MA
- Web page: https://patentgrep.com/patent/US20190244387A1

## CPC

- G06T 7/73: using feature-based methods
- G06T 3/4007: based on interpolation, e.g. bilinear interpolation (image demosaicing G06T3/4015; edge-driven or edge-based scaling G06T3/403)
- G06V 10/20: Image preprocessing
- G06V 40/103: {Static body considered as a whole, e.g. static pedestrian or occupant recognition}
- H04N 19/59: involving spatial sub-sampling or interpolation, e.g. alteration of picture size or resolution
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

Embodiments of the present disclosure provide an image detection method, apparatus and system and a non-volatile storage medium. The image detection method includes: compressing an initial image to obtain a compressed image; performing a target detection on the compressed image to obtain a first position information of a target object in the compressed image; and determining a second position information of the target object in the initial image based on the first position information.

## Claims

### Claim 1

An image detection method, comprising:
compressing an initial image to obtain a compressed image;
performing a target detection on the compressed image to obtain a first position information of a target object in the compressed image; and
determining a second position information of the target object in the initial image based on the first position information.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the first position infoimation comprises a coordinate of a first object frame for indicating a position of the target object in the compressed image, and
determining the second position information of the target object in the initial image based on the first position information comprises:
mapping the first object frame to the initial image, based on the coordinate of the first object frame and a compression ratio between the initial image and the compressed image, to obtain a second object frame in the initial image corresponding to the first object frame; and
obtaining a coordinate of the second object frame as the second position information.

### Claim 3 (depends on 1)

The method according to claim 1, further comprising:
extracting an image block comprising the target object from the initial image based on the second position infoimation; and
outputting the image block comprising the target object as an object image of the target object.

### Claim 4 (depends on 1)

The method according to claim 1, wherein compressing the initial image to obtain the compressed image comprises:
compressing the initial image at a preset ratio to obtain the compressed image.

### Claim 5 (depends on 1)

The method according to claim 1, wherein compressing the initial image to obtain the compressed image comprises:
compressing the initial image to a preset size to obtain the compressed image.

### Claim 6 (depends on 1)

The method according to claim 1, wherein compressing the initial image to obtain the compressed image comprises:
resampling the initial image to obtain the compressed image.

### Claim 7 (depends on 1)

The method according to claim 1, wherein prior to compressing the initial image to obtain the compressed image, the method further comprises:
determining that a size of the initial image is above a size threshold.

### Claim 8

An image detection apparatus, comprising:
a compression module configured to compress an initial image to obtain a compressed image;
a detection module configured to perform a target detection on the compressed image to obtain a first position infoiniation of a target object in the compressed image; and
a position determining module configured to determine a second position information of the target object in the initial image based on the first position information.

### Claim 9 (depends on 1)

An image detection system, comprising a processor and a memory,
wherein the memory stores a computer program instruction, and the computer program instruction when executed by the processor, causes the processor to perform the image detection method according to claim 1.

### Claim 10 (depends on 9)

The image detection system according to claim 9, further comprising a camera, wherein the camera comprises an image sensor for capturing the initial image.

### Claim 11 (depends on 1)

A non-volatile storage medium, storing a program instruction, the program instruction when executed by a computer, causing the computer to perform the image detection method according to claim 1.
