CN-115914623-B - Image effect processing method and device and computer equipment

CN115914623BCN 115914623 BCN115914623 BCN 115914623BCN-115914623-B

Abstract

The invention provides an image effect processing method, which comprises the steps of obtaining RAW image data with poor image effect, carrying out format conversion on the RAW image data to obtain multiple RAW image data with different formats, inputting the multiple RAW image data into multiple different processing platforms in a one-to-one correspondence mode to carry out ISP simulation processing to obtain a plurality of images, each processing platform supporting a format of the RAW image data, comparing whether the effects of the images are the same or not, judging that the image effect is caused by the RAW image data if the effects of the images are the same, and judging that the image effect is caused by the ISP of the processing platform if the effects of the images are different. In addition, the invention also provides an image effect processing device and computer equipment. The invention can trace back the reasons for poor image effect without professional detection equipment, and effectively saves the detection cost.

Inventors

FAN HONGZHONG
NI XUNENG

Assignees

瞰瞰技术(深圳)有限公司

Dates

Publication Date: 20260512
Application Date: 20221229

Claims (10)

1. An image effect processing method, the image being an image processed by an ISP, the image effect processing method comprising: Acquiring RAW image data with poor image effect, wherein the RAW image data with poor image effect is corresponding RAW image data acquired when the image does not reach the expected effect after being processed by ISP; performing format conversion on the RAW image data to obtain a plurality of RAW image data in different formats; Inputting the RAW image data into a plurality of different processing platforms in a one-to-one correspondence manner to perform ISP simulation processing to obtain a plurality of images, wherein each processing platform supports a format of RAW image data; Comparing whether the effects of the plurality of images are the same; If the effects of the images are the same, judging that the image effect is not good and is caused by RAW image data; If the effects of the images are different, judging that the image effects are not good and are caused by ISPs of the processing platform.
2. The image effect processing method according to claim 1, wherein after determining that the image effect is not good due to RAW image data, the image effect processing method further comprises: Shooting by using an imaging module for acquiring the RAW image data from different angles under the same color temperature condition to acquire a plurality of test RAW image data, wherein the imaging module comprises an imaging sensor and a lens; analyzing the plurality of test RAW image data to obtain that the reason for the poor image effect is caused by a lens or an imaging sensor in the imaging module.
3. The image effect processing method according to claim 2, wherein capturing a plurality of test RAW image data from different angles under the same color temperature condition using an imaging module that acquires the RAW image data specifically includes: Controlling the light source to emit the same light under a preset scene; and under the preset scene, shooting after sequentially adjusting the imaging module to different visual angles so as to obtain the plurality of test RAW image data.
4. The image effect processing method of claim 3, wherein capturing a plurality of test RAW image data from different angles under the same color temperature condition using an imaging module that acquires the RAW image data further comprises: the imaging module keeps the field angle of the imaging module unchanged in the preset scene; Controlling a light source to emit the same light under a preset scene and rotating the light source to change the light emitting direction of the light source; when the light emitting direction of the light source is changed from one direction to another, the imaging module is controlled to shoot, so that the multiple test RAW image data are obtained.
5. The method of claim 2, wherein analyzing the plurality of test RAW image data to determine whether the cause of the poor image effect is caused by a lens or an imaging sensor in the imaging module comprises: Inputting the multiple test RAW image data into the same processing platform for ISP simulation processing to obtain a plurality of images; analyzing whether the color effect of the images meets a preset effect or not; If the color effect of the images does not meet the preset effect, judging that the reason for the poor image effect is due to the lens in the imaging module.
6. An image effect processing apparatus, characterized in that the image effect processing apparatus comprises: an acquiring unit, configured to acquire RAW image data with an poor image effect, where the RAW image data with the poor image effect is corresponding RAW image data acquired when an image has not reached an expected effect after being processed by an ISP; a conversion unit, configured to perform format conversion on the RAW image data to obtain multiple RAW image data in different formats; The input unit is used for inputting the RAW image data into a plurality of different processing platforms in a one-to-one correspondence manner to perform ISP simulation processing to obtain a plurality of images, wherein each processing platform supports a format of RAW image data; A comparison unit for comparing whether the effects of the plurality of images are the same; a first judging unit for judging that the image effect is not good caused by the RAW image data if the effects of the plurality of images are the same; And the second judging unit is used for judging that the image effect is poor due to ISP of the processing platform if the effects of the plurality of images are different.
7. The image effect processing apparatus according to claim 6, further comprising: the image generation unit is used for shooting a plurality of test RAW image data from different angles under the same color temperature condition by using an imaging module for acquiring the RAW image data, and the imaging module comprises an imaging sensor and a lens; And the analysis unit is used for analyzing whether the reasons of the poor image effect are caused by a lens or an imaging sensor in the imaging module.
8. The image effect processing apparatus according to claim 7, wherein the image generating unit further comprises: the control unit is used for controlling the light sources to emit the same light under a preset scene; And the adjusting unit is used for shooting after sequentially adjusting the imaging module to different visual angles under the preset scene so as to obtain the plurality of test RAW image data.
9. A computer device, comprising: a memory for storing a computer executable program, A processor for executing the computer-executable program to implement the image effect processing method according to any one of claims 1 to 5.
10. A computer-readable storage medium having stored therein computer-executable instructions which, when executed by a processor, are adapted to carry out the image effect processing method of any one of claims 1 to 5.

Description

Image effect processing method and device and computer equipment Technical Field The present invention relates to the field of image detection technologies, and in particular, to an image effect processing method, a computer device, and an apparatus. Background Currently, an Image acquired by an original Image sensor (sensor) needs to be processed by an Image Processor (IMAGE SIGNAL Processor, ISP) of a platform to obtain the Image. Typically, the original image data (RAW IMAGE DATA, raw) is input to an ISP image processor of a processing platform to be processed to obtain a corresponding image. However, the obtained image may have problems such as too low or too high resolution, insufficient or too low exposure, too serious sharpening, or occurrence of foreign matters on the image. The problem of the image can be corrected if the cause of the problem of the image can be found. However, problems with the image may be caused by the ISP image processor or the original image data, which is difficult to distinguish by the naked eye, and thus additional detection equipment is required to detect problems with the ISP and the original image data, but additional specialized detection equipment will increase costs. Disclosure of Invention The invention provides an image effect processing method, computer equipment and device, which can trace back the reasons for generating image problems without professional detection equipment, and greatly save the problem detection cost. In a first aspect, an embodiment of the present invention provides an image effect processing method, where the image is an image processed by an ISP, and the image effect processing method includes obtaining RAW image data with poor image effect, performing format conversion on the RAW image data to obtain multiple RAW image data with different formats, inputting the multiple RAW image data into multiple different processing platforms in a one-to-one correspondence manner to perform ISP simulation processing to obtain multiple images, each processing platform supporting a format of the RAW image data, comparing whether effects of the multiple images are the same, if effects of the multiple images are the same, determining that the image effect is caused by the RAW image data, and if effects of the multiple images are different, determining that the image effect is caused by the ISP of the processing platform. In a second aspect, an embodiment of the present invention provides an image effect processing apparatus, including an acquisition unit, a conversion unit, an input unit, a comparison unit, a first determination unit, and a second determination unit. And the acquisition unit is used for acquiring RAW image data with poor image effect. And the conversion unit is used for carrying out format conversion on the RAW image data to obtain a plurality of RAW image data with different formats. And the input unit is used for inputting the plurality of RAW image data into a plurality of different processing platforms in a one-to-one correspondence manner to perform ISP simulation processing to obtain a plurality of images, and each processing platform supports a format of RAW image data. And the comparison unit is used for comparing whether the effects of the images are the same or not. And the first judging unit is used for judging that the image effect is poor due to the RAW image data if the effects of the images are the same. And the second judging unit is used for judging that the image effect is poor due to ISP of the processing platform if the effects of the plurality of images are different. In a third aspect, an embodiment of the present invention provides a computer device including a memory and a processor. And a memory for storing a computer executable program. And a processor for executing the computer-executable program to implement the image effect processing method as described above. In a fourth aspect, an embodiment of the present invention provides a computer readable storage medium, where computer executable instructions are stored, where the computer executable instructions are executed by a processor to implement an image effect processing method as described above. In the above embodiment, the original data of the image with poor effect is analyzed, the original data of the image is input into the ISP of the different processing platforms for processing, the image effect output by the ISP of the different processing platforms is checked, whether the reason for the poor image effect is the original data of the image or the original data of the image is determined by comparing whether the effect of the output image is consistent, the real reason for the image problem is effectively traced back, and the problem detection of the ISP and the original data of the image is not required by additional professional detection equipment, thereby saving the cost. Drawings In order to more clearly illustrate the embodiments of the present inve