Image dynamic range test method, computer device and storage medium

Abstract

The present application provides an image dynamic range test method, which comprises: obtaining an image sample set, the image sample set comprising a set of images collected under simulated scenes and real scenes; calculating image data of the image sample set to obtain a plurality of different ideal image index values; collecting corresponding images by using a target device to obtain a to-be-tested image; calculating image data of the to-be-tested image to obtain a plurality of different to-be-tested image index values; and performing one-to-one comparison and calculation between the plurality of different ideal image index values and the plurality of different to-be-tested image index values to obtain a dynamic range score of the to-be-tested image. In addition, the present application also provides a computer device for implementing image dynamic range test and a storage medium.

Description

Technical Field

[0001] This application relates to the field of image parameter technology, and in particular to an image dynamic range testing method, computer equipment, and storage medium. Background Technology

[0002] In the information age, vehicle cameras play a significant role in autonomous driving technology, and consequently, the requirements for image quality are becoming increasingly stringent. During outdoor driving, vehicle cameras are often exposed to environments with varying lighting conditions, making the dynamic range and contrast of the camera images crucial for evaluating image quality; therefore, testing both is of paramount importance.

[0003] In current technology, testing methods for dynamic range and contrast are generally divided into objective testing and subjective testing. Objective testing mainly uses test charts such as the Kodak Gray Card or OECF card, while subjective testing relies on human visual comparison. However, objective testing has limited applicability in certain scenarios and performs poorly in outdoor environments; while subjective testing is highly subjective and lacks quantifiable standards. Summary of the Invention

[0004] This application provides an image dynamic range testing method, computer equipment, and storage medium, which can quantify the dynamic range of images with high applicability.

[0005] In a first aspect, embodiments of this application provide a dynamic range testing method, the dynamic range testing method comprising: acquiring an image sample set, the image sample set including a set of images acquired in simulated scenes and real scenes; calculating multiple different ideal image index values ​​on the image data of the image sample set; acquiring corresponding images using a target device to obtain a test image; calculating multiple different test image index values ​​on the image data of the test image, the test image index values ​​and the ideal image index values ​​corresponding one-to-one; comparing the multiple different ideal image index values ​​with the multiple different test image index values ​​one-to-one to calculate a dynamic range score for the test image, the dynamic range score being used to indicate whether the dynamic range of the test image meets the standard.

[0006] Secondly, this application provides a computer device for implementing image dynamic range testing, the computer device for image dynamic range testing including a memory and a processor. The memory is used to store a computer program; the processor is used to execute the computer program and implement the above-described image dynamic range testing method.

[0007] Thirdly, this application provides a computer-readable storage medium for storing a computer program that is executed to implement the above-described image dynamic range testing method.

[0008] The aforementioned image dynamic range testing method, computer equipment, and storage medium acquire an image sample set, calculate the corresponding image index values, and obtain the difference between the corresponding image index values ​​to measure the dynamic range of the image. It has a wide range of applications and is not limited to laboratory settings, and can more objectively measure the dynamic range of an image. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0010] Figure 1 A flowchart of an image dynamic range testing method provided in an embodiment of this application.

[0011] Figure 2 The flowchart of step S102 provided in the embodiments of this application.

[0012] Figure 3 The flowchart of sub-step S1024 provided in the embodiments of this application.

[0013] Figure 4 The flowchart of sub-step S10243 provided for the embodiments of this application.

[0014] Figure 5 The flowchart of sub-step S10244 provided for the embodiments of this application.

[0015] Figure 6 The flowchart of step S105 provided in the embodiments of this application is as follows.

[0016] Figure 7 A schematic diagram of a computer device for testing the dynamic range of applied images provided in an embodiment of this application.

[0017] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.

[0019] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar planned objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data are interchangeable where appropriate; in other words, the described embodiments are implemented according to a sequence other than that illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, may also include other content; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0020] It should be noted that the use of terms such as "first" and "second" in this application is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" and "second" may explicitly or implicitly include one or more of that feature. Furthermore, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0021] Please refer to Figure 1 This is a flowchart of an image dynamic range testing method provided in an embodiment of this application. The image dynamic range testing method includes steps S101-S105.

[0022] Step S101: Obtain an image sample set, which includes a set of images collected from simulated scenes and real scenes.

[0023] In step S101, the images in the image sample set can be debugged images, or subjective or objective images acquired on known devices, and different images can be acquired by category. For example, for vehicle-mounted cameras, images such as mobile terminal images, vehicle-mounted images, and camera working images can be acquired by category. For the image sample set, the more devices acquired and the more comprehensive the acquired images, the better the image sample set's quality.

[0024] In some feasible embodiments, the images in the image sample set can also be pre-tuned videos, or subjective or objective videos acquired on existing devices. The acquired video is divided into multiple frames. When performing dynamic range testing, the image sample set can be considered as calculating the dynamic range of a single frame multiple times.

[0025] Step S102: Calculate multiple different ideal image index values ​​from the image data of the image sample set.

[0026] The ideal image index values ​​include the overall average brightness of the ideal image, the average brightness of the dark areas of the ideal image, the average brightness of the mid-section of the ideal image, the average brightness of the bright areas of the ideal image, and the contrast value of the ideal image. In step S102, multiple different ideal image index values ​​are calculated for each image in the image set, and the average value is taken according to the number of images in the image set to obtain the ideal image index values ​​of the image sample set. (See also...) Figure 2 The flowchart for step S102 provided in this application embodiment is as follows: Steps S1021-S1024 involve calculating multiple different ideal image index values ​​from the image data of the image sample set.

[0027] Step S1021: Calculate the overall average brightness of the ideal image based on each image in the image sample set.

[0028] In step S1021, each image in the image sample set is in RGB (RGB color mode) format. The R, G, and B values ​​corresponding to each image are acquired simultaneously with the acquisition of each image in the image sample set. In this embodiment, the average brightness of each image is calculated based on the images in the image sample set.

[0029] Specifically, the overall average brightness of the image is calculated using the first formula. The first formula is expressed as follows:

[0030] = 0.299 * + 0.587 * + 0.114 * (Formula 1)

[0031] In formula (1), R, G, and B represent the red, green, and blue color channels, respectively.

[0032] Step S1022: Match an image histogram for each image.

[0033] In step S1022, the image histogram is used to reflect the correspondence between image brightness and the pixel distribution at each image brightness level. The more pixels there are, the greater the proportion of the corresponding image brightness level in the image.

[0034] Step S1023: Calculate the average brightness of the dark areas of the ideal image, the average brightness of the middle section of the ideal image, and the average brightness of the bright areas of the ideal image based on the image histogram.

[0035] Step S1024: Calculate the contrast value of the ideal image based on the overall average brightness of the ideal image.

[0036] The image contrast value represents the difference or ratio between the brightest and darkest parts of an image. To a certain extent, a high contrast value corresponds to a low dynamic range. A good image requires a suitable dynamic range and contrast; neither a higher dynamic range nor a higher contrast value is always better. (See also...) Figure 3 This is a flowchart of sub-step S1024 provided in the embodiments of this application. Calculating the contrast value of the ideal image based on the overall average brightness of the ideal image includes steps S10241-S10244.

[0037] Step S10241: Divide each image into several image blocks, each image block being the same size.

[0038] For images, the brightness levels and corresponding pixel distribution are not uniform when calculating the image contrast value. In step S10241, to facilitate calculation, the image is divided into several equally sized image blocks. The contrast value of the entire image is calculated by weighting the contrast values ​​of each image block. For example, an image can be divided into m*n equally sized image blocks. The contrast values ​​of the m*n image blocks are calculated, and each image block is assigned a corresponding weight to calculate the weighted contrast value of the entire image.

[0039] Step S10242: Obtain the weight table generated by the preset weight model based on several image blocks in each image.

[0040] The preset weighting model is a Gaussian Mixed Model (GMM), used to reflect the correspondence between the position of an image patch in the image and its corresponding weight. GMM not only provides the probability that an image patch belongs to a certain class, but also estimates the probability density. The weight table includes multiple weights, each corresponding to an image patch. For each image patch, the weight reflects its position in the image. Specifically, the closer the image patch is to the image center, the larger its corresponding weight, and vice versa.

[0041] Step S10243: Calculate the local contrast value of each image block.

[0042] In step S10243, the local contrast value of each image patch is calculated based on its position in the image. (See also...) Figure 4 This is a flowchart of sub-step S10243 provided in the embodiments of this application. Calculating the local contrast value of each image block includes steps S102431-S102433.

[0043] Step S102431: Calculate the weight of each point in the image block relative to the center of the image block.

[0044] Specifically, the weight of each point relative to the center of the image patch is calculated according to the second formula, which is expressed as follows:

[0045]

[0046] In formula (2), ω i Let w and h represent the weight of any point relative to the center of the image patch, and let x0 and y0 represent the x and y coordinates of the center point of the image, respectively. i y i These represent the x-coordinate and y-coordinate of any point within the image block, respectively.

[0047] Step S102432: Calculate the weighted average value of the image block under the overall average brightness of the ideal image based on the weight of each point and the overall average brightness of the ideal image.

[0048] Specifically, the contrast of each image patch is calculated according to the third formula. The third formula is expressed as follows:

[0049]

[0050] In formula (3), L represents the weighted average value of each image block under image brightness Y, where Y... i This represents the image brightness corresponding to any point.

[0051] Step S102433: Calculate the local contrast value based on the weighted average value.

[0052] Specifically, the local contrast value is calculated according to the fourth formula. The fourth formula is expressed as follows:

[0053]

[0054] In formula (4), LC represents the local contrast value.

[0055] Step S10244: Calculate the contrast value of each ideal image based on the local contrast value and the weight table.

[0056] See also Figure 5 The flowchart for step S10244 provided in the embodiments of this application is as follows. Calculating the contrast value of each ideal image based on the local contrast value and the weight table includes steps S102441-S102442.

[0057] Step S102441: Obtain the correspondence between the local contrast value in each image block and each weight in the weight table.

[0058] Step S102442: Calculate the contrast value of each ideal image based on the correspondence between the local contrast value and the weight.

[0059] Specifically, the image contrast value is calculated according to the fifth formula. The fifth formula is expressed as follows:

[0060]

[0061] In formula (5), LC final LC(i,j) represents a local contrast value, and GW(i,j) represents a weight in the weight table. Local contrast values ​​and weights with the same index correspond to each other.

[0062] Step S103: Use the target device to acquire the corresponding image to obtain the image to be tested.

[0063] The image to be tested is an image that requires dynamic range testing and is acquired from the target device. In some feasible embodiments, video can also be acquired from the target device for dynamic range testing; in this case, the image sample set is also video.

[0064] Step S104: Calculate multiple different image index values ​​for the image to be tested using the image data of the image to be tested. The image index values ​​for the image to be tested correspond one-to-one with the ideal image index values.

[0065] The measured image index values ​​include the overall average brightness of the measured image, the average brightness of the dark areas of the measured image, the average brightness of the mid-section of the measured image, the average brightness of the bright areas of the measured image, and the contrast value of the measured image. In step S104, the calculation process for the measured image index values ​​is the same as that for the ideal image index values, and will not be repeated here.

[0066] Step S105: Compare the multiple different ideal image index values ​​with the multiple different test image index values ​​one by one to calculate the dynamic range score of the test image.

[0067] The dynamic range score indicates whether the dynamic range of the image under test meets the standard. A higher dynamic range score indicates a more distinct distinction between shadow and highlight areas, resulting in richer detail and better display of content at each brightness level. In step S105, after acquiring multiple indicator values ​​for the images under test, the difference between the indicator values ​​of the ideal image and the image under test is used to measure the difference in dynamic range between the image under test and the image sample set. (See also...) Figure 6The flowchart for step S105 provided in this embodiment is as follows. Calculating the dynamic range score of each image in the second image sample set includes steps S1031-S1032.

[0068] Step S1051: Calculate the difference between each corresponding index value based on the plurality of different ideal image index values ​​and the plurality of different test image index values.

[0069] Step S1052: Obtain the percentage of the difference relative to the ideal image index value, and use it as the dynamic range score for each image under test.

[0070] In step S1032, a dynamic range score is calculated for each image under test based on the difference. Specifically, the dynamic range of each image under test is scored as a percentage of the difference relative to the ideal image index value, resulting in multiple different dynamic range scores. Understandably, a higher percentage corresponds to a higher score. The percentage is used as a quantitative standard for image testing. By using percentages, the dynamic range score of the image is obtained, thus constructing a scoring system suitable for images.

[0071] Please refer to Figure 7 This is a schematic diagram of a computer device for performing image dynamic range testing according to an embodiment of this application. The computer device 101 includes a memory 901 and a processor 902. The processor 902 is used to run the computer program stored in the memory 901.

[0072] The memory 901 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 901 can be an internal storage unit of a computer device, such as a hard disk. In other embodiments, the memory 901 can be an external storage device of a computer device, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc., configured in the computer device. Furthermore, the memory 901 can include both internal and external storage units of a computer device. The memory 901 can be used not only to store application software and various types of data installed on the computer device, such as code for dynamic testing of image ranges, but also to temporarily store data that has been output or will be output.

[0073] In the above embodiments, by acquiring an image sample set, calculating the corresponding image index values, and obtaining the difference between the corresponding image index values ​​to measure the dynamic range of the image, the method has a wide range of applications and is not limited to laboratory scenarios, and can more objectively measure the dynamic range of the image.

[0074] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

[0075] The above-listed embodiments are merely preferred embodiments of this application and should not be construed as limiting the scope of this application. Therefore, any equivalent variations made in accordance with the claims of this application shall still fall within the scope of this application.

Claims

1. An image dynamic range test method, characterized by, The image dynamic range test method comprises: acquiring an image sample set comprising a set of images collected under simulated scenes and real scenes; calculating image data of the image sample set to obtain a plurality of different ideal image index values; collecting corresponding images by using a target device to obtain a to-be-tested image; calculating image data of the to-be-tested image to obtain a plurality of different to-be-tested image index values, the to-be-tested image index values and the ideal image index values corresponding to each other, wherein the calculation process of the to-be-tested image index values is the same as that of the ideal image index values; comparing and calculating the plurality of different ideal image index values and the plurality of different to-be-tested image index values to obtain a dynamic range score of the to-be-tested image, the dynamic range score being used to represent whether the dynamic range of the to-be-tested image meets a standard.

2. The image dynamic range test method of claim 1, wherein, The ideal image index values comprise an ideal image overall average brightness, an ideal image dark part average brightness, an ideal image middle section average brightness, an ideal image highlight area average brightness, and an ideal image contrast value, and the to-be-tested image index values comprise a to-be-tested image overall average brightness, a to-be-tested image dark part average brightness, a to-be-tested image middle section average brightness, a to-be-tested image highlight area average brightness, and a to-be-tested image contrast value.

3. The image dynamic range test method of claim 2, wherein, The ideal image dark part average brightness, the ideal image middle section average brightness, the ideal image highlight area average brightness, the to-be-tested image dark part average brightness, the to-be-tested image middle section average brightness, and the to-be-tested image highlight area average brightness are obtained according to image brightness level division; calculating image data of the image sample set to obtain a plurality of different ideal image index values comprises: calculating the ideal image overall average brightness according to each image in the image sample set; matching an image histogram to each image, the image histogram being used to reflect a corresponding relationship between image brightness and pixel distribution on each image brightness; calculating the ideal image dark part average brightness, the ideal image middle section average brightness, and the ideal image highlight area average brightness according to the image histogram; calculating the ideal image contrast value according to the ideal image overall average brightness.

4. The image dynamic range test method of claim 3, wherein, Calculating the ideal image contrast value according to the ideal image overall average brightness comprises: dividing each image into a plurality of image blocks, each image block having the same size; obtaining a weight table generated by a preset weight model according to the plurality of image blocks in each image, the preset weight model being used to reflect a corresponding relationship between the position and weight of an image block in an image, the weight table comprising a plurality of weights, each weight corresponding to an image block; calculating a local contrast value of each image block; calculating each ideal image contrast value according to the local contrast value and the weight table.

5. The image dynamic range test method of claim 4, wherein, Calculating a local contrast value of each image block comprises: calculating a weight of each point in the image block relative to the center of the image block; calculating a weighted average value of the image block under the ideal image overall average brightness according to the weight of each point and the ideal image overall average brightness; According to the weighted average value, the local contrast value is calculated.

6. The image dynamic range test method of claim 4, wherein, According to the local contrast value and the weight table, each of the ideal image contrast value is calculated, including: Obtaining the corresponding relationship between the local contrast value in each image block and each weight in the weight table; According to the corresponding relationship between the local contrast value and the weight, each of the ideal image contrast value is calculated.

7. The image dynamic range test method of claim 3, wherein, After obtaining the ideal image index value of each image in the image set, the ideal image index value of the image sample set is obtained by averaging according to the number of images in the image set.

8. The image dynamic range test method of claim 1, wherein, The dynamic range score of the test image is calculated by one-to-one comparison between the plurality of different ideal image index values and the plurality of different test image index values, specifically including: According to the plurality of different ideal image index values and the plurality of different test image index values, the difference value between each corresponding index value is calculated; Obtaining the percentage of the difference value in the ideal image index value as the dynamic range score of each test image.

9. A computer device for implementing image dynamic range testing, the computer device comprising: The computer device for realizing the image dynamic range test includes: a memory for storing a computer program; and a processor for executing the computer program and realizing the image dynamic range test method according to any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium is used to store a computer program, and the computer program is executed by a processor to realize the image dynamic range test method according to any one of claims 1-8.

Images