CN-122019816-A - Image scene library construction method, apparatus, chip, computer device, storage medium and program product

CN122019816ACN 122019816 ACN122019816 ACN 122019816ACN-122019816-A

Abstract

The present application relates to an image scene library construction method, apparatus, chip, computer device, computer readable storage medium and computer program product. The method comprises the steps of obtaining project demand information and project image original data, determining a plurality of types of scene libraries according to the project demand information, wherein the project image original data are obtained through image pickup equipment, establishing a plurality of classification labels for each scene library, extracting data of the project image original data according to the classification labels to obtain classification label data, and constructing corresponding image scene libraries according to the classification label data for each scene library. By adopting the method, the test evaluation efficiency of the camera can be improved.

Inventors

GUO PEIHONG
LEI QIAO
LI JINJIA

Assignees

西安紫光展锐科技有限公司

Dates

Publication Date: 20260512
Application Date: 20260128

Claims (10)

1. A method for constructing an image scene library, the method comprising: Acquiring project demand information and project image original data, and determining a plurality of types of scene libraries according to the project demand information; Establishing a plurality of classification labels for each scene library; carrying out data extraction on the original data of the project image according to the classification label to obtain classification label data; and constructing corresponding image scene libraries according to the classification tag data for each scene library.
2. The method of claim 1, wherein the scene library comprises a standard scene library, wherein the determining a plurality of types of scene libraries based on the project requirement information comprises: Analyzing the project demand information to obtain project demand data and project stage identifiers; According to the project demand data, matching corresponding project reference data; and determining a scene standard data set according to the project reference data and the project stage identification, and constructing a standard scene library according to the scene standard data set.
3. The method of claim 2, wherein the scene library further comprises an item scene library and/or a problem scene library, wherein the determining a plurality of types of scene libraries according to the item requirement information further comprises: extracting project process data of a plurality of nodes in a project process from the project image original data according to the project stage identification, and constructing a project scene library according to the project process data; and under the condition that abnormal data exists in the project process data, constructing a problem scene library according to the abnormal data.
4. The method of claim 1, wherein said creating a plurality of category labels for each of said scene libraries comprises: According to the acquired environmental information of the project image original data, establishing an environmental label, wherein the environmental label comprises one or more of a brightness label, a color temperature label and a dynamic range label; Establishing an algorithm tag according to algorithm processing information corresponding to the project image original data; establishing a shooting condition label according to shooting metadata information of the project image original data, wherein the shooting condition label comprises at least one of a shooting time label and a sensitivity label; And establishing a content label and a place label according to the image content information of the project image original data.
5. The method of claim 4, wherein for each of the scene libraries, constructing a corresponding image scene library from the category label data comprises: Carrying out abnormal data identification on the classified label data, and removing the abnormal data to obtain cleaned classified label data; carrying out data distribution analysis on the cleaned classification label data to generate an environment distribution map, an algorithm distribution map and a scene content distribution map; and constructing a data panel according to the environment distribution diagram, the algorithm distribution diagram and the scene content distribution diagram, and constructing an image scene library according to the cleaned classification label data and the data panel.
6. An image scene library construction apparatus, the apparatus comprising: The system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring project demand information and project image original data, and determining a plurality of types of scene libraries according to the project demand information; the label generation module is used for establishing a plurality of classification labels for each scene library; The data extraction module is used for carrying out data extraction on the original data of the project image according to the classification label to obtain classification label data; the data processing module is used for constructing corresponding image scene libraries according to the classification tag data for each scene library.
7. A chip comprising a processor and a data interface, the processor reading instructions stored on a memory via the data interface, the processor being capable of performing the steps of the method of any one of claims 1to 5.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 5 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 5.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any one of claims 1 to 5.

Description

Image scene library construction method, apparatus, chip, computer device, storage medium and program product Technical Field The present application relates to the field of image processing technology, and in particular, to an image scene library construction method, an apparatus, a chip, a computer device, a computer readable storage medium, and a computer program product. Background The camera is an important component in products such as smart phones, wearable equipment, vehicle-mounted equipment and the like, and the test and verification of the camera is an essential link before mass production and marketing. In the process of testing and evaluating the cameras, the image scene library plays a fundamental role, and the complexity of testing work and the accuracy of testing results are directly affected. However, in the related art, the image scene library is acquired in a mode of adopting the method, and related staff perform image acquisition according to the temporary requirement of the current test scene. The method causes that the test set collected by each item cannot be effectively inherited and multiplexed, and the data sets are stored in each disk file in a scattered manner, so that the test efficiency is reduced. Disclosure of Invention In view of the foregoing, it is desirable to provide an image scene library construction method, apparatus, chip, computer device, computer-readable storage medium, and computer program product that can improve the efficiency of test evaluation of an image pickup device. In a first aspect, the present application provides a method for constructing an image scene library, including: Acquiring project demand information and project image original data, and determining a plurality of types of scene libraries according to the project demand information; Establishing a plurality of classification labels for each scene library; carrying out data extraction on the original data of the project image according to the classification label to obtain classification label data; and constructing corresponding image scene libraries according to the classification tag data for each scene library. In one embodiment, the scene library comprises a standard scene library, and the determining a plurality of types of scene libraries according to the project requirement information comprises the following steps: Analyzing the project demand information to obtain project demand data and project stage identifiers; According to the project demand data, matching corresponding project reference data; and determining a scene standard data set according to the project reference data and the project stage identification, and constructing a standard scene library according to the scene standard data set. In one embodiment, the scene library further comprises an item scene library and/or a problem scene library, wherein the scene library determining a plurality of types of scene libraries according to the item demand information further comprises: extracting project process data of a plurality of nodes in a project process from the project image original data according to the project stage identification, and constructing a project scene library according to the project process data; and under the condition that abnormal data exists in the project process data, constructing a problem scene library according to the abnormal data. In one embodiment, the creating a plurality of classification labels for each of the scene libraries includes: According to the acquired environmental information of the project image original data, establishing an environmental label, wherein the environmental label comprises one or more of a brightness label, a color temperature label and a dynamic range label; Establishing an algorithm tag according to algorithm processing information corresponding to the project image original data; establishing a shooting condition label according to shooting metadata information of the project image original data, wherein the shooting condition label comprises at least one of a shooting time label and a sensitivity label; And establishing a content label and a place label according to the image content information of the project image original data. In one embodiment, for each of the scene libraries, constructing a corresponding image scene library according to the classification tag data includes: Carrying out abnormal data identification on the classified label data, and removing the abnormal data to obtain cleaned classified label data; carrying out data distribution analysis on the cleaned classification label data to generate an environment distribution map, an algorithm distribution map and a scene content distribution map; and constructing a data panel according to the environment distribution diagram, the algorithm distribution diagram and the scene content distribution diagram, and constructing an image scene library according to the cleaned classification label data an