WO2020107196A1 - Photographing quality evaluation method and apparatus for photographing apparatus, and terminal device - Google Patents

Abstract

A photographing quality evaluation method and apparatus for photographing apparatus, and a terminal device. The method comprises: acquiring image data obtained by a photographing apparatus that photographs an evaluation graphic card comprising at least two evaluation sub-graphic cards; identifying a calibration point in the image data based on a calibration point pattern; and determining at least two regions to be evaluated in the image data based on layout rules of at least two evaluation sub-graphic cards at the identified calibration points in the evaluation card; finally, using evaluation rules corresponding to the at least two regions to be evaluated to evaluate each region to be evaluate separately so as to obtain a photographing quality evaluation result of the photographing apparatus. By using the embodiment of the present invention, multiple evaluation indexes for measuring photographing quality can be evaluated in one go, and regions to be evaluated corresponding to each evaluation index are automatically identified, thereby saving on evaluation time and improving evaluation efficiency.

Description

Method, device and terminal equipment for evaluating shooting quality of shooting device Technical field

The present invention relates to the field of communication technology, and in particular, to a method, device, and terminal device for evaluating a shooting quality of a shooting device.

Background technique

In general, before shooting with the camera, you need to adjust the configuration of the camera to make the camera reach a better shooting state, so as to shoot a higher quality picture. Before adjusting the shooting state of the shooting device, it is necessary to test the shooting quality of the shooting device in the current shooting state to determine how to adjust the shooting device to achieve the best shooting state. In the evaluation of the shooting quality of the shooting device, in addition to the subjective perception of the human eye, objective assessment indicators such as color accuracy, color saturation, sharpness, and signal-to-noise ratio are often used to quantitatively analyze the shooting quality of the shooting device. A test chart is required to evaluate the evaluation index of the shooting device.

Under normal circumstances, the method step of quantitative analysis of the shooting quality of the shooting device through the evaluation chart is that the shooting device shoots multiple single test charts one by one, manually selects the area to be detected, and then the terminal device calls professional analysis software The test area is tested one by one, and the test efficiency is low. In addition, before each measurement of the shooting device, the relative position of the shooting device and the test chart card needs to be readjusted, and the operation is complicated.

To sum up, in the field of evaluation of the front-end shooting quality of the shooting device, an efficient evaluation method is urgently needed.

Summary of the invention

Embodiments of the present invention provide a method, device, and terminal device for evaluating the shooting quality of a shooting device, which can improve the evaluation efficiency.

In a first aspect, an embodiment of the present invention provides a method for evaluating shooting quality of a shooting device, including:

Acquiring image data obtained by shooting an evaluation picture card by a shooting device, the evaluation picture card including at least two evaluation sub-picture cards;

Identifying the calibration point in the image data based on the calibration point pattern;

Determine at least two regions to be evaluated in the image data based on the identified calibration points and the layout rules of the at least two evaluation sub-picture cards in the evaluation picture card;

The evaluation rules corresponding to the at least two areas to be evaluated are respectively evaluated for each area to be evaluated to obtain a shooting quality evaluation result of the shooting device.

In a second aspect, an embodiment of the present invention provides a shooting quality evaluation device for a shooting device, including:

An obtaining unit, configured to obtain image data obtained by shooting the evaluation picture card by the shooting device, the evaluation picture card including at least two evaluation sub-picture cards;

A processing unit, configured to identify the calibration point in the image data based on the calibration point pattern;

The processing unit is further configured to determine at least two areas to be evaluated in the image data based on the identified calibration points and the layout rules of the at least two evaluation sub-picture cards in the evaluation picture card;

The processing unit is further configured to respectively evaluate each area to be evaluated using evaluation rules corresponding to the at least two areas to be evaluated to obtain a shooting quality evaluation result of the shooting device.

A third invention, an embodiment of the present invention provides an evaluation card, characterized in that the evaluation card is used to evaluate the shooting quality of a shooting device, and the evaluation card includes five evaluation sub-cards and twenty Calibration point:

The five evaluation sub-picture cards are respectively: resolution analysis hypotenuse picture card for evaluating sharpness, 24-color card for evaluating color accuracy and saturation, gray card for evaluating average brightness of the screen, and Dead leaf maps for evaluating loss of detail, and grayscale cards for evaluating signal-to-noise ratio or contrast;

The twenty calibration points are used to divide the five evaluation sub-picture cards;

The analytical force hypotenuse card is arranged at the center of the evaluation card, the 24-color card is arranged at the lower left corner of the evaluation card, and the gray card is arranged at the upper left corner of the evaluation card Position, the dead leaf map is arranged at the upper right corner of the evaluation chart card, and the grayscale card is arranged at the bottom position of the evaluation chart card.

According to a fourth aspect, an embodiment of the present invention provides a terminal device including a processor and a memory. The processor is connected to the memory. The memory stores a computer program. The computer program includes program instructions. The program instructions are used to execute:

Acquiring image data obtained by shooting the evaluation card by the shooting device, the evaluation card includes at least two evaluation sub-cards;

Identifying the calibration point in the image data based on the calibration point pattern;

Determine at least two regions to be evaluated in the image data based on the identified calibration points and the layout rules of the at least two evaluation sub-picture cards in the evaluation picture card;

The evaluation rules corresponding to the at least two areas to be evaluated are respectively evaluated for each area to be evaluated to obtain a shooting quality evaluation result of the shooting device.

Correspondingly, an embodiment of the present invention provides a computer-readable storage medium that stores computer program instructions, and when the computer program instructions are executed, they are used to implement the above-mentioned first aspect. Method for evaluating shooting quality of shooting device.

In the embodiment of the present invention, the image data obtained by shooting the evaluation card is acquired, and the calibration points included in the image data are identified based on the preset calibration point pattern, and further based on the identified calibration points and the layout of the evaluation card The rules can automatically determine the area to be evaluated in the image data, and finally use the evaluation rule corresponding to the area to be evaluated to evaluate the evaluation area. The evaluation card includes at least two evaluation sub-picture cards, so the captured evaluation picture is taken The obtained image data includes at least two areas to be evaluated, and each area to be evaluated corresponds to a category of evaluation indicators, which realizes the evaluation of multiple categories of evaluation indicators at one time, and automatically identifies the areas to be evaluated corresponding to each evaluation indicator To save evaluation time and improve evaluation efficiency.

BRIEF DESCRIPTION

In order to more clearly explain the embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some of the present invention. For the embodiment, for those of ordinary skill in the art, without paying any creative labor, other drawings may be obtained based on these drawings.

1 is a schematic diagram of using a single picture card to evaluate shooting quality according to an embodiment of the present invention;

2 is a schematic diagram of using a composite graphics card to evaluate shooting quality according to an embodiment of the present invention;

3 is a schematic flowchart of a method for evaluating a shooting quality of a shooting device according to an embodiment of the present invention;

4a is a schematic diagram of a calibration point pattern provided by the implementation of the present invention;

4b is a schematic diagram of another calibration point style provided by an embodiment of the present invention;

4c is a schematic diagram of another calibration point pattern provided by an embodiment of the present invention;

5 is a schematic flowchart of another method for evaluating the shooting quality of a shooting device according to an embodiment of the present invention;

6 is a schematic flowchart of a calibration point recognition provided by an embodiment of the present invention;

7 is a schematic flowchart of a region to be evaluated identification provided by an embodiment of the present invention;

8 is a schematic structural diagram of a shooting quality evaluation device for a shooting device provided by an embodiment of the present invention;

9 is a schematic structural diagram of a terminal device according to an embodiment of the present invention;

10 is a schematic structural diagram of an evaluation card provided by an embodiment of the present invention.

detailed description

The technical solutions in the embodiments of the present invention will be described clearly and completely in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by a person of ordinary skill in the art without making creative efforts fall within the protection scope of the present invention.

An embodiment of the present invention proposes a method for evaluating the shooting quality of a shooting device, which can be used to quickly detect the shooting quality of the shooting device, so as to facilitate the shooting of the shooting device according to the configuration or shooting parameters of the shooting quality State, so that a higher quality image is taken. The shooting quality evaluation method of the shooting device may include subjective evaluation and objective evaluation, where the subjective evaluation refers to the user observing the image quality of the shooting device through the human eye to determine the shooting quality of the shooting device, for example, the human eye passes the judgment Whether the brightness of the image captured by the shooting device is appropriate, whether each subject is clear in the image, etc. The objective evaluation refers to the quantitative analysis of the image data captured by the shooting device by using various evaluation indicators, so as to realize the shooting quality evaluation of the shooting device.

The method for evaluating the shooting quality of the shooting device described in the embodiment of the present invention mainly performs quantitative analysis on the shooting device through objective evaluation indexes. The method for evaluating the shooting quality of the shooting device may be applied to a terminal device, and the terminal device may be a device such as a mobile phone, a tablet, a notebook computer, or a smart wearable device.

In one embodiment, the evaluation index for measuring the shooting quality of the shooting device may include one or more of the following: color saturation, color accuracy, contrast, dynamic range, sharpness, and loss of detail. Among them, the color saturation refers to the color purity. The higher the purity, the brighter the performance, and the lower the purity, the darker; the color accuracy refers to whether the color in the image is different from the color of the subject; the dynamic range indicates the The darkest to brightest range that can be included in the captured picture. The larger the dynamic range, the richer the gradation that can be expressed, and the wider the color space included. That is, the larger the dynamic range of the camera, the higher the recorded range. The darker and brighter the richer the details; the contrast refers to the contrast of the grayscale in the image, the greater the contrast indicates the greater the range of difference; the sharpness refers to the clarity of each detail in the image and its boundaries; the loss of detail refers Some edges, corners, and intersections of light in the image are unclear or damaged.

In one embodiment, the above-mentioned evaluation indicators can be classified according to the evaluation category of each evaluation indicator. The same evaluation category is classified as the same category of evaluation indicators. For example, color saturation and color accuracy both belong to the evaluation of color, then The two belong to the same category of evaluation indicators, that is, the two categories of evaluation indicators are the same. Similarly, contrast, dynamic range, and signal-to-noise ratio belong to the same category of evaluation indicators.

In one embodiment, an evaluation chart may be used to evaluate the evaluation indicators of the above categories. The evaluation chart may include: a 24-color card, a gray card, a gray-scale card, a analytic power hypotenuse chart card, and a dead leaf chart. Among them, the 24-color card is used to calculate color accuracy and color saturation, the gray card is used to calculate the average brightness of the image screen, and the gray-scale card is used to calculate the image signal-to-noise ratio, dynamic range or contrast, the The analytic force hypotenuse graph card is used to calculate sharpness, and the dead leaf graph is used to calculate sharpness. In summary, it can be seen that each evaluation indicator corresponds to one evaluation card, that is, each evaluation card is used to evaluate one evaluation indicator. For example, the 24-color card is used to evaluate the color accuracy, and the analytical hypotenuse graph card is used to evaluate the clarity. In summary, the evaluation index of each category corresponds to a graphics card used to evaluate the evaluation index of the category. For example, the evaluation index of the color category corresponds to a 24-color card, and the definition evaluation index corresponds to a resolution-beveled edge card.

In one embodiment, the steps of evaluating various types of evaluation indicators of the shooting quality through the evaluation card are usually: first select the evaluation indicators to be evaluated, and for convenience of description, the selected evaluation indicators are hereinafter referred to as target evaluation indicators; Control the shooting device to shoot the evaluation chart corresponding to the target evaluation index to obtain the image data obtained from the shooting; determine the area to be evaluated in the image data, and then call evaluation software to evaluate the evaluation area to obtain the shooting device The evaluation result of the target evaluation index. For example, assuming that the selected target evaluation index is color accuracy, the evaluation step may be: acquiring image data obtained by shooting a 24-color card from the shooting device, and determining the image area containing the 24-color graphic card in the image data as the area to be evaluated By calling the software to analyze and evaluate the area to be evaluated in the image data, the evaluation result of the color accuracy of the shooting device can be obtained.

In one embodiment, the method for evaluating various types of evaluation indicators of the shooting quality by evaluating the graphic card may include single image card evaluation and composite image card evaluation. The single picture card evaluation refers to that each picture card can only be used to evaluate one category of evaluation indicators, for example, a 24-color card is a picture card used to evaluate a color category (color accuracy and color saturation). In the evaluation process of a single picture card, the shooting device shoots one evaluation picture card at a time, and after acquiring the image data obtained by shooting, it is necessary to manually select the area to be evaluated in the image data, and then call the evaluation software to The area to be evaluated is evaluated. For example, referring to FIG. 1 is a schematic diagram of a single picture card evaluation provided in an embodiment of the present invention. A composite graphic card evaluation means that at least two single evaluation graphic cards are integrated on one composite graphic card (each single evaluation graphic card is called a evaluation sub-graphic card), that is, a composite graphic card can be used for at least one evaluation card at a time. Two types of evaluation indicators are evaluated. In the evaluation process of the composite graphic card, the shooting device photographs the composite graphic card, and after acquiring the image data obtained by the shooting, calls the region to be evaluated identification algorithm to automatically detect at least two regions in the image data to be evaluated, and finally calls the evaluation The software evaluates the at least two areas to be evaluated. For example, referring to FIG. 2, a schematic diagram of a composite graphics card evaluation is provided according to an embodiment of the present invention.

In the case of using a single picture card for evaluation, if you want to evaluate multiple categories of evaluation indicators, you need to shoot multiple single picture cards one by one. Since the size of each single picture card is different, the shooting The requirements of the environment are different. Before shooting a single picture card, the shooting device needs to rearrange the shooting environment and readjust the relative position of the shooting device and the single picture card. In addition, in the evaluation process of a single picture card, it is necessary to manually select areas to be detected in multiple image data. In summary, the evaluation of a single picture card consumes more time and the evaluation efficiency is low.

In the case of using a composite graphics card for evaluation, it realizes the evaluation of multiple categories of evaluation indicators at one time, and can automatically identify each area to be evaluated in the image data, saving evaluation time and improving evaluation efficiency. In the following, in the implementation of the present invention, a method for evaluating the shooting quality of a shooting device using a composite graphics card will be described in detail.

Please refer to FIG. 3, which is a method for evaluating the shooting quality of a shooting device according to an embodiment of the present invention. The method described in FIG. 3 may be executed by a terminal device, and specifically may be executed by a processor of the terminal device. It can be a mobile phone, tablet, laptop, smart wearable device, etc., or a shooting device with image evaluation function.

Step S301: Acquire image data obtained by the shooting device shooting the evaluation card.

In one embodiment, the evaluation picture card is a composite picture card, and the evaluation picture card includes at least two evaluation sub-picture cards, and the evaluation sub-picture card includes any one of the following: used to evaluate color accuracy and saturation 24-color card for degree, gray card for evaluating the average brightness of the picture, dead leaf map for evaluating the loss of detail, gray scale card for evaluating the signal-to-noise ratio or contrast, and the analytical hypotenuse chart for evaluating the clarity card.

In one embodiment, the method of acquiring image data obtained by the photographing device photographing the evaluation card may include: the photographing device is configured on a terminal device, and the terminal device calls the photographing device to perform evaluation on the evaluation card The image data can be obtained by shooting; or, the shooting device and the terminal device are independent devices, and when the shooting device detects a shooting operation, the evaluation card is shot, and the shot image is saved Data; the terminal device sends an image acquisition instruction to the shooting device; when the shooting device receives the image acquisition instruction, the saved image data is sent to the terminal device.

In one embodiment, in order to ensure the accuracy of the evaluation, before the shooting device shoots the evaluation card, the shooting environment needs to be arranged first, such as setting the light in the shooting environment and the shooting background, and then adjusting the shooting The relative position of the device and the evaluation card ensures that the shooting device is parallel to the evaluation card.

In one embodiment, the image data includes images of at least one evaluation card. In the embodiment of the present invention, when the user instructs the shooting device to shoot the evaluation card, the user can select the evaluation requirements of the shooting device The shooting device shoots the shooting area of the evaluation picture card, and controls the shooting device to shoot the selected shooting area. The evaluation requirements refer to which evaluation indexes the user wants to evaluate the shooting device, such as color saturation, sharpness, or contrast; the shooting area may be the entire evaluation card, or may include a certain one in the evaluation card Or some areas of some evaluation sub-cards. For example, assuming that the evaluation card includes a 24-color card, a resolution hypotenuse card, a grayscale card, and a gray card, the four evaluation sub-picture cards, and the shooting area may be the entire evaluation card including four evaluation sub-picture cards, Or the shooting area may also be a partial area including only two evaluation sub-picture cards of a 24-color card and a gray-scale card.

In summary, in the embodiment of the present invention, the user can select a shooting area according to actual evaluation requirements, and control the shooting device to shoot the shooting area to obtain image data. At this time, all image elements included in the image data are for evaluation The shooting quality of the shooting device is useful. In this way, while satisfying the user's evaluation needs, the energy consumption of the terminal device can also be reduced.

Step S302: Identify the calibration point in the image data based on the calibration point pattern.

In one embodiment, in addition to at least two evaluation sub-picture cards, the evaluation picture card also includes calibration points, the calibration points are used to divide at least two evaluation sub-picture cards, and one of the four calibration points determines one Evaluation sub-picture card. The embodiment of the present invention can realize the evaluation of multiple categories of evaluation indexes of the shooting device at one time, and can automatically identify each area to be evaluated in the image data. The method of automatically identifying each area to be evaluated in the image data may be identifying the calibration points in the image data, and determining each area to be evaluated according to the positional relationship between the calibration points and the layout rules of the evaluation card.

In one embodiment, the method of identifying the calibration points in the image data is to identify the calibration points included in the image data according to the calibration point pattern, the calibration point pattern may include the shape characteristics of the calibration points and the structural characteristics of the calibration points, For example, the shape feature of the calibration point may be a square, or the shape feature of the calibration point may also be a circle and a square, and the structural feature of the calibration point may be a black and white block at 90 degrees to each other. The calibration point style may be designed when the evaluation chart is designed. In one embodiment, the rule for designing the calibration point style is to avoid the calibration point style and any evaluation sub-picture in the evaluation chart. The style of the card is the same.

For example, referring to FIG. 4a, FIG. 4b, and FIG. 4c are three calibration point patterns provided by the implementation of the present invention. As shown in the calibration point pattern shown in FIG. 4a, the shape features of the calibration points are circles and squares, and the square is located inside the circle. In the calibration point pattern shown in FIG. 4b, the shape features of the calibration points are circles. In the calibration point pattern shown in 4c, the shape characteristic of the calibration point is a square. In the calibration point patterns shown in FIGS. 4a, 4b, and 4c, the structural characteristics of the calibration point are black and white blocks that are 90 degrees from each other.

In one embodiment, the identification of the calibration points in the image data based on the calibration point pattern includes: converting the image data into grayscale image data; performing edge detection processing on the grayscale image data to obtain edges Image data; identify the calibration points in the image data based on the shape characteristics of the calibration points, the structural characteristics of the calibration points, and the edge image data.

In one embodiment, the image data obtained by the shooting device shooting the evaluation card is a color image, the color image is also referred to as a 3-channel image, and the grayscale image is a 1-channel image, so the image data is converted It is gray-scale image data, that is, converting 3-channel images to 1-channel images. In one embodiment, the method for converting image data into grayscale image data may be an average method. The average method refers to averaging the 3-channel pixel values of the same pixel in the image data to obtain the operation result. That is the pixel value of the pixel in the grayscale image. According to this method, the pixel value of each pixel point in the grayscale image in the image data can be calculated, and then the image rendering is performed with the pixel value of each pixel point in the grayscale image, and the grayscale image data can be obtained. In other embodiments, the method of converting image data into grayscale image data may also be a weighting method and a maximum value method, etc., which are not enumerated in the embodiments of the present invention.

In one embodiment, after converting the image data into grayscale image data, the terminal device performs edge detection processing on the grayscale image data to obtain edge image data, so that the terminal device analyzes the edge image data Shape characteristics of calibration points. The edge refers to the most significant part of the local change in an image. The edge image can reflect the discontinuity of the local characteristics in the image, such as the abrupt change of grayscale, the abrupt change of texture structure, and the abrupt change of color. The edge image data refers to an image obtained by performing edge extraction on the original image (in the embodiment of the present invention, the original image data refers to grayscale image data), and the edge image data is helpful for analyzing the shape characteristics of the image.

In one embodiment, the edge detection algorithm may include a first-order detection algorithm and a second-order detection algorithm, wherein the commonly used algorithms in the first-order detection algorithm include Canny operator, Robert (cross-difference) operator, compass operator, etc. Commonly used in order detection algorithms include Marr-Hildreth. In the embodiment of the present invention, the Canny operator is preferably used to perform edge detection on the grayscale image data obtained above. The implementation steps of the Canny operator may include noise reduction processing, finding gradients, tracking edges, adjusting parameters, etc. The specific implementation process of the Canny operator will not be specifically described in the embodiments of the present invention.

In one embodiment, after obtaining the edge image data, the terminal device recognizes the calibration point in the image data based on the shape feature of the calibration point, the structural feature of the calibration point, and the edge image data. Specifically, the embodiment in which the terminal device recognizes the calibration point in the image data based on the shape feature of the calibration point, the structural feature of the calibration point, and the edge image data may be: based on the calibration point Shape features and edge image data find image elements in the image data that have the same shape features as the shape features of the calibration points, and then, based on the structural features of the calibration points, filter out structural features and calibration points from the found image elements The image elements with the same structural characteristics are determined as the identified calibration points.

Step S303: Determine at least two regions to be evaluated in the image data based on the identified calibration points and the layout rules of the at least two evaluation sub-picture cards in the evaluation picture card.

In one embodiment, before identifying the area to be evaluated in the image data, the terminal device first determines the layout rules of the evaluation card. In still another embodiment, the determining of the layout rules of the evaluation card includes: when the terminal device detects image data of the evaluation area to be identified, the evaluation card layout rule acquisition request is output; the user outputs The acquisition request submits the layout rules of the evaluation graphic card to the terminal device. In other embodiments, the determining the layout rules of the evaluation graphic card includes: the terminal device preselects and stores at least one evaluation graphic card and its corresponding layout rules; when image data of the evaluation area to be identified is detected, The terminal device obtains an evaluation chart ID corresponding to the image data, that is, which image capture card the image data was acquired from, and at least one evaluation map is stored from the stored evaluation map ID The evaluation picture card is found in the card, and then the typesetting rules corresponding to the evaluation picture card are obtained. The above are only two possible methods for obtaining the layout rules of the evaluation card listed in the embodiments of the present invention. In other embodiments, the terminal device may also obtain the layout rules of the evaluation card by other methods.

In an embodiment, the implementation of determining at least two regions to be evaluated in the image data based on the identified calibration points and the layout rules of the at least two evaluation sub-picture cards in the evaluation picture card may be Yes: Obtain the distribution rule of the calibration points in the layout rules of the evaluation picture card and the distance between the calibration points used to divide each evaluation sub-picture card to determine at least two regions to be evaluated in the image data. Specifically, the distribution rule of the calibration points may refer to the distance between the calibration points and the positions of the calibration points.

In other embodiments, the implementation of determining at least two areas to be evaluated in the image data based on the identified calibration points and the typesetting rules of the at least two evaluation sub-picture cards in the evaluation picture card further It may be: determining the positional relationship of each identified calibration point in the horizontal and vertical directions, adding a serial number to each identified calibration point according to a preset rule; obtaining the evaluation card under the layout rules of the evaluation card Correspondence between the serial number of each calibration point and the evaluation sub-picture card; according to the identified serial number of the calibration point and the corresponding relationship between the obtained serial number of each calibration point and the evaluation sub-picture card, determine the Describe the area to be evaluated in the image data.

For example, assuming that a base point is set in the evaluation card, the preset rule is to use the base point as the basis, and the calibration point in the horizontal direction of the base point according to its distance from the base point, Labeling starts from 1 in sequence. When the numbering of the first line of the calibration point is completed, the sequence number is added again from the left of the second line. For example, there are 5 calibration points in the horizontal direction where the base point is located. The serial number of the nearest calibration point is added as 1, and the serial number of the calibration point furthest from the base point is added as 5. The second line includes 3 calibration points, and the serial numbers from left to right are 6, 7, 8; The correspondence between the serial number of each calibration point pre-stored by the terminal device and the evaluation sub-picture card is: the serial numbers 0, 1, 6, 7 correspond to the evaluation sub-picture card is a gray card, then the terminal device can be based on The serial number of the fixed point determines the serial number 0,1,6,7, and the rectangle formed is an area to be evaluated.

Step S304: Use the evaluation rules corresponding to the at least two areas to be evaluated to evaluate each area to be evaluated separately to obtain a shooting quality evaluation result of the shooting device.

In one embodiment, before using the evaluation rules corresponding to the at least two evaluation areas to evaluate each area to be evaluated, the terminal device needs to determine the evaluation rules corresponding to the at least two areas to be evaluated. In one embodiment, the determining the evaluation rule corresponding to the at least two areas to be evaluated includes: determining, according to the positions of the respective evaluation sub-picture cards, to which each of the at least two areas to be evaluated belongs to the area to be evaluated Categories of evaluation indicators; the evaluation rules corresponding to the categories of evaluation indicators are respectively used as the evaluation rules corresponding to each area to be evaluated.

The evaluation index category may include any one of color, sharpness, loss of detail, dynamic range/signal-to-noise ratio/contrast ratio, etc. The evaluation rule may be a rule for analyzing each evaluation index, for example, for analyzing clarity Rules, rules for analyzing contrast. The implementation manner of using the evaluation rules corresponding to the at least two areas to be evaluated to separately evaluate each area to be evaluated may be: extracting feature information in the at least two areas to be evaluated; using respective corresponding evaluation rules The characteristic information of each evaluation area is analyzed, and the obtained analysis result is the evaluation result.

In the embodiment of the present invention, after the image data obtained by the shooting device shooting the evaluation picture card including a plurality of evaluation sub-picture cards is acquired, the calibration points in the image data can be identified based on the preset calibration point patterns, further , Determine each area to be evaluated in the image data according to the identified calibration points and the layout rules of each evaluation sub-picture card in the evaluation card, and finally use the evaluation rules corresponding to each evaluation area to carry out each evaluation area Evaluation, to obtain the shooting quality evaluation results of the shooting device, can evaluate multiple evaluation indexes at one time, and automatically identify the areas to be evaluated corresponding to each evaluation index, saving evaluation time and improving evaluation efficiency.

Please refer to FIG. 5, which is another method for evaluating the shooting quality of a shooting device according to an embodiment of the present invention. The method shown in FIG. 5 may include:

Step S501: Acquire image data obtained by the photographing device photographing the evaluation card.

Step S502: Convert the image data into grayscale image data, and perform edge detection processing on the grayscale image data to obtain edge image data.

In an embodiment, some feasible implementation manners included in the step S501 and the step S502 have been specifically described in the embodiment shown in FIG. 3, and will not be repeated here.

Step S503: Identify the calibration points in the image data based on the shape features of the calibration points, the structural features of the calibration points, and the edge image data.

In an embodiment, the shape feature included in the calibration point pattern may be one or more, and when the shape feature included in the calibration point pattern is one, as shown in FIGS. 4b and 4c, the The shape feature of the calibration point, the structural feature of the calibration point and the edge image data identifying the calibration point in the image data include: detecting the shape feature in the image data and the calibration point based on the edge image data The first image element with the same shape feature; the first image element with the same structural feature as the structural feature of the calibration point from the detected first image element; and the identified first image element is determined as the identified target Fixed point.

In one embodiment, the terminal device may pre-store a plurality of evaluation graphic cards, and the calibration point patterns corresponding to the evaluation graphic cards may be the same or different, or it may be understood that multiple sets of evaluation graphic cards are pre-stored in the terminal device Corresponding relationship with the calibration point, before detecting the calibration point pattern in the image data, the terminal device first obtains the calibration point pattern corresponding to the evaluation card, and then extracts the acquired shape characteristic of the calibration point And structural features, assuming that the shape feature is a square, and the structural feature is a black and white block with 90 degrees to each other. The terminal device recognizes the edge image according to the shape and structural characteristics of the extracted calibration point, for example, detects all square features in the edge image data, and determines all image elements with square features in the edge image data as The first image element. Further, according to the extracted structural features of the calibration point, the first image elements whose structural features are black and white blocks with a mutual star of 90 degrees are selected from the first image elements, and the filtered first image elements are selected Determine the calibration point.

In yet another embodiment, when the calibration point pattern includes multiple shape features, as shown in FIG. 4a, the shape feature based on the calibration point, the structural feature of the calibration point, and the edge image data A method for identifying calibration points in the image data includes: identifying the calibration points in the image data based on the structural features of the calibration points, the edge image data, the first shape feature, and the second shape feature Fixed point.

In one embodiment, the identifying the calibration point in the image data based on the structural feature of the calibration point, the edge image data, the first shape feature, and the second shape feature includes: The edge image data detects a first image element in the image data that has the same shape feature as the first shape feature; and filters the first image elements that have the same structural features as the calibration points from the detected first image elements Image element; identifying the second image element with the same shape feature and the second shape feature from the selected first image element by contour recognition; filtering the structural feature and the structure of the calibration point from the second image element The second image element with the same characteristics; the selected second image element is determined as the identified calibration point.

In short, if the calibration point pattern includes the first shape feature and the second shape feature, the terminal device identifying the calibration point means that the terminal device searches the image data for image elements that satisfy the following three conditions: including both A shape feature also includes a second shape feature, and an image element whose structural feature is the same as the structural feature of the calibration point. The terminal device uses the image element that satisfies the above three conditions at the same time as the identified calibration point. If any one of the conditions is not met, the terminal device determines that the identified image element is not the calibration point. For example, assuming that the calibration point pattern is shown in Figure 4a, which includes both circular features and square features, and the structural features are black and white blocks of 90 degrees to each other, first detect all circular features in the image data, and then In the shape feature, find the structural feature as a circle of 90 degrees black and white blocks. Further, perform square feature detection in the found circle, use the contour recognition to find the circle that contains the square, and then finally find the circle that contains the square. Among the circles, the shape of the middle square is selected to be a circle of black and white blocks with 90 degrees to each other, and the final screen is used to identify the calibration point.

In one embodiment, if the calibration point pattern includes a first shape feature and a second shape feature, the structural features based on the calibration point, the edge image data, the first shape feature, and the first After the two shape features identify the calibration points in the image data (this identification is hereinafter referred to as the initial identification), the method further includes: acquiring the number of identified calibration points; if the number of calibration points is less than the number of calibration points The threshold value is to identify the calibration point in the image data based on the structural feature of the calibration point, the edge image data, and the first shape feature or the second shape feature.

In one embodiment, the threshold value of the number of calibration points is determined by the user according to the number of evaluation sub-picture cards in the evaluation picture cards captured by the shooting device. In the embodiment of the present invention, it is provided that one determination point is determined for every 4 calibration points Evaluation sub-picture card, assuming that the evaluation picture card includes five evaluation sub-picture cards, and when the shooting device is used to shoot the evaluation picture card, the user controls the shooting device to shoot all five evaluation sub-picture cards, then calibrate the points The number threshold of can be set to 20; and assuming that the user controls the shooting device to shoot only two evaluation sub-picture cards in the evaluation card, the threshold of the number of calibration points can be set to 8.

In one embodiment, if the number of identified calibration points is less than the threshold of the calibration points, the area to be detected identified by the terminal device will be inaccurate, resulting in an inaccurate evaluation result of the shooting quality of the shooting device. In one embodiment, the reason that the number of identified calibration points is less than the threshold of the calibration point number may be that the shooting device is affected by the shooting environment when shooting the evaluation card, so that the contour or shape of a part of the calibration points The features are not clear. In order to ensure the accuracy of the shooting quality evaluation results of the shooting device, when the number of identified calibration points is less than the threshold of the calibration points, the calibration points in the image data are identified again (hereinafter referred to as re-identification) , Unlike the above-mentioned initial recognition, the recognition method adopted this time is: recognizing the image data based on the structural feature of the calibration point, the edge image data, and the first shape feature or the second shape feature Calibration point in. It can be understood that when the number of calibration points is less than the calibration point threshold, the terminal device lowers the identification standard and performs calibration point identification again.

In one embodiment, the identifying the calibration point in the image data based on the structural feature of the calibration point, the edge image data, and the first shape feature or the second shape feature includes: The image data detects a third image element in the image data whose shape feature is the same as the first shape feature or the second shape feature; screening structural features and the structure of the calibration point from the detected third image element The third image element with the same characteristics; the selected third image element is determined as the identified calibration point.

Based on the above description, it can be known that when the calibration point pattern includes the first shape feature and the second shape feature, when the terminal device first recognizes the calibration point in the image data, the terminal device selects from the image data Find image elements that meet the following three conditions: image elements that include both the first shape feature and the second shape feature, and whose structural features are the same as those of the calibration point; when the number of calibration points identified for the first time is less than the calibration point When the number threshold is used, when the terminal device recognizes the calibration point in the image data again, the terminal device searches the image data for image elements that satisfy the following two conditions: including the first shape feature and the structural feature The structural feature is the same as the calibration point, or includes the second shape feature and the structural feature is the same as the structural feature of the calibration point.

In one embodiment, before the terminal device recognizes the calibration point in the image data again, the terminal device may also mark the calibration point obtained in the initial recognition in the image data, the label is used to indicate that the point has been determined In order to calibrate the point, the terminal device is prevented from recognizing the identified calibration point repeatedly, and the accuracy of the calibration point identification is ensured, and the power consumption of the terminal device is also saved. In this way, the re-recognition of the image data means recognizing the calibration points of the other parts of the image data except for the calibration points identified for the first time.

In one embodiment, the calibration point recognized by the terminal device for the first time is exactly the same as the preset calibration point pattern, so it can be determined that the accuracy level of the calibration point obtained by the initial recognition is the first level, and the terminal device recognizes again The obtained calibration point may not be exactly the same as the preset calibration point style, so the calibration point obtained by re-identification may be marked as the accuracy level is the second level, the accuracy of the first level is higher than the second level, The accuracy is the second level, indicating that the accuracy needs to be verified.

For example, referring to FIG. 6 is a schematic diagram of a calibration point recognition process provided by an embodiment of the invention. In FIG. 6, it is assumed that the calibration point pattern is shown in FIG. 4a, and the first shape feature included in the calibration point pattern is a circle. , The second shape feature is a square, and the structural feature of the calibration point is a black and white block at 90 degrees to each other; it is assumed that the edge detection algorithm used is the Canny operator; it is assumed that the evaluation card includes five evaluation sub-cards, and the user controls the shooting device to The five evaluation sub-picture cards in the evaluation picture card are taken, and the threshold value of the number of calibration points is set to 20. Based on the above assumption, FIG. 6 includes the initial recognition and re-identification of the calibration points in the image data.

Step S504: Determine at least two regions to be evaluated in the image data based on the identified calibration points and the layout rules of the at least two evaluation sub-picture cards in the evaluation picture card.

In one embodiment, the determining at least two areas to be evaluated in the image data based on the calibration and the layout rules of the at least two evaluation sub-picture cards in the evaluation picture card includes: determining the The pixel coordinates of each calibration point in the identified calibration points; determining the positional relationship between the calibration points according to the pixel coordinates of the calibration points; based on the positional relationship between the calibration points and the at least two The layout rules of the evaluation sub-picture cards in the evaluation picture card determine at least two areas to be evaluated in the image data.

In one embodiment, the pixel coordinate refers to the position of the pixel in the image. The pixel coordinate is related to the resolution. Assuming that the resolution of an image is 1024x768, it means that the image includes 768 rows and 1024 columns. The pixel coordinates at row 400 and column 300 are 400x300. For the same pixel in the same image, if the image resolution does not change, the pixel coordinates of the pixel will not change, but for the same pixel in the same image, if the resolution is not changed, if it is used to display the When the size of the image display device changes, the position of the pixel in the display device changes. In other words, if the resolution of an image is assumed to be 1024x800, regardless of the size of the display device used, such as 14 inches or 21 inches, the screen of the display device will be divided into 800 columns in the horizontal direction and 1024 lines in the vertical direction. This image, but for display devices of different sizes, the same pixel has a different position on the screen.

Therefore, determining the pixel coordinates of the identified calibration points cannot accurately determine the positional relationship between the calibration points on the screen of the display device related to the terminal device, that is, it is impossible to determine the display between the calibration points The vertical relationship and horizontal relationship are displayed on the screen, so the terminal device needs to determine the positional relationship between the identified calibration points according to the pixel coordinates between the calibration points, so that the terminal device can follow up The area to be evaluated is determined according to the positional relationship between the various calibration points.

In an embodiment, the implementation manner of the terminal device determining the positional relationship between each calibration point according to the identified pixel coordinates of each calibration point can be seen in FIG. 7, which is a Schematic diagram of the process of identifying the area to be evaluated. In FIG. 7, the terminal device first finds the calibration point 1 whose pixel coordinate is closest to the origin in each calibration point, and uses the calibration point 1 as the coordinate origin to identify each calibration point in the first group in the horizontal direction. Assume that there is a horizontal direction The 6 calibration points are labeled in sequence according to the distance from the origin, and then the calibration point 1 is used as the coordinate origin to identify the first group of vertical points. Further, the calibration point 6 is used as the coordinate origin to identify the second group of vertical The calibration points in the direction, and so on, can identify the positional relationship between all 20 calibration points in the horizontal direction and the vertical direction.

After identifying the positional relationship between each calibration point, the terminal device may determine the positional relationship between each calibration point and the typesetting rules of the at least two evaluation sub-picture cards in the evaluation picture card At least two areas to be evaluated in the image data. In an embodiment, the typesetting rules of the at least two evaluation sub-picture cards in the evaluation picture card include positions of the at least two evaluation sub-picture cards and sizes of the at least two evaluation sub-picture cards, The determining at least two areas to be evaluated of the image data based on the positional relationship between the respective calibration points and the layout rules of the at least two evaluation sub-picture cards in the evaluation picture card includes: Determining the rectangular area included in the image data by the size of at least two evaluation sub-picture cards, the positions of the at least two evaluation sub-picture cards, and the positional relationship between the respective calibration points;

In one embodiment, it is assumed that each evaluation card is arranged on the evaluation card in a rectangular area, and the size of the at least two evaluation sub-picture cards may refer to the rectangular area corresponding to each evaluation sub-picture card Length and width, the length and width may be in units of pixels, or may be in units of centimeters or other length units. The distance between each calibration point can be determined according to the positional relationship of each calibration point and the position of at least two evaluation sub-picture cards in the evaluation picture card, and which calibration points can form a rectangular area, for example, assuming evaluation The graphic card includes a 24-color card, the size of the rectangular area where the 24-color card is located is known, and the location of the 24-color card is known as the lower left corner of the evaluation graphic card, then the terminal device is in the lower left corner of the image data Position, according to the positional relationship between the various calibration points, determine the horizontal calibration point and vertical calibration point in the lower left corner, and then obtain the rectangular area composed of the calibration points in the lower left corner and the size of each rectangular area , Determine the rectangular area whose size is equal to the 24-color card as the area to be evaluated.

Step S505: Determine, according to the position of each evaluation sub-picture card in the evaluation picture card, the evaluation indicator category to which each of the at least two areas to be evaluated belongs.

Step S506: Use the evaluation rules corresponding to the evaluation indicator categories as the evaluation rules corresponding to each area to be evaluated.

Step 507: Use the evaluation rules corresponding to the at least two areas to be evaluated to evaluate each area to be evaluated separately to obtain a shooting quality evaluation result of the shooting device.

In an embodiment, some feasible implementation manners included in the steps S505-S507 have been described in detail in the embodiment shown in FIG. 3, and will not be repeated here.

In the embodiment of the present invention, after the image data obtained by the shooting device shooting the evaluation picture card including a plurality of evaluation sub-picture cards is acquired, the calibration points in the image data can be identified based on the preset calibration point patterns, further , Determine each area to be evaluated in the image data according to the identified calibration points and the layout rules of each evaluation sub-picture card in the evaluation card, and finally use the evaluation rules corresponding to each evaluation area to carry out each evaluation area Evaluation, to obtain the shooting quality evaluation results of the shooting device, can evaluate multiple evaluation indexes at one time, and automatically identify the areas to be evaluated corresponding to each evaluation index, saving evaluation time and improving evaluation efficiency.

Please refer to FIG. 8, which is a schematic structural diagram of a shooting quality evaluation device for a shooting device according to an embodiment of the present invention. As shown in FIG. 8, the shooting quality evaluation device for a shooting device includes an acquisition unit 801 and a processing unit 802:

The acquiring unit 801 is configured to acquire image data obtained by shooting an evaluation picture card by a shooting device, the evaluation picture card including at least two evaluation sub-picture cards;

The processing unit 802 is configured to identify the calibration point in the image data based on the calibration point pattern;

The processing unit 802 is further configured to determine at least two areas to be evaluated in the image data based on the identified calibration points and the layout rules of the at least two evaluation sub-picture cards in the evaluation picture card;

The processing unit 802 is further configured to respectively evaluate each area to be evaluated using evaluation rules corresponding to the at least two areas to be evaluated to obtain a shooting quality evaluation result of the shooting device.

In one embodiment, the implementation of the processing unit 802 for identifying the calibration point in the image data based on the calibration point pattern is: converting the image data into grayscale image data; Perform edge detection processing to obtain edge image data; identify the calibration points in the image data based on the shape characteristics of the calibration points, the structural characteristics of the calibration points, and the edge image data.

In an embodiment, the processing unit 802 is configured to identify the calibration points in the image data based on the shape characteristics of the calibration points, the structural characteristics of the calibration points, and the edge image data: The edge image data detects a first image element in the image data whose shape feature is the same as the shape feature of the calibration point; from the detected first image element, a structural feature that is the same as the structural feature of the calibration point is selected The first image element; the selected first image element is determined as the identified calibration point.

In an embodiment, the shape features of the calibration point include a first shape feature and a second shape feature, and the processing unit 802 is configured to be based on the shape feature of the calibration point, the structural feature of the calibration point, and the The embodiment of the edge image data identifying the calibration points in the image data is: identifying the image data based on the structural features of the calibration points, the edge image data, the first shape feature and the second shape feature Calibration point in.

In one embodiment, the processing unit 802 is used to identify the calibration point in the image data based on the structural feature of the calibration point, the edge image data, the first shape feature and the second shape feature The implementation method is: detecting a first image element in the image data having the same shape feature as the first shape feature based on the edge image data; filtering structural features and the calibration points from the detected first image element The first image element with the same structural feature; the second image element whose shape feature is determined to be the same as the second shape feature from the selected first image element by contour recognition; and the structural feature is selected from the second image element A second image element having the same structural characteristics as the calibration point; the filtered second image element is determined as the identified calibration point.

In one embodiment, the obtaining unit 801 is further used to obtain the number of identified calibration points; the processing unit 802 is also used to determine the number of calibration points based on the calibration points if the number of calibration points is less than the threshold of the number of calibration points Structural features of the image, the edge image data, and the first shape feature or the second shape feature identify calibration points in the image data.

In one embodiment, the processing unit 802 is used to identify the calibration point in the image data based on the structural feature of the calibration point, the edge image data, and the first shape feature or the second shape feature Is implemented by: detecting a third image element in the image data whose shape features are the same as the first shape feature or the second shape feature based on edge image data; filtering structural features from the detected third image element The third image element having the same structural characteristics as the calibration point; the filtered third image element is determined as the identified calibration point.

In one embodiment, the processing unit 802 is further configured to add marks to the calibration points identified based on the structural features of the calibration points, the edge image data, and the first shape feature or the second shape feature , The mark is used to indicate that the accuracy of the calibration point needs to be verified.

In one embodiment, the processing unit 802 is configured to determine at least two of the image data to be evaluated based on the identified calibration points and the layout rules of the at least two evaluation sub-picture cards in the evaluation picture card The embodiment of the area is: determining the pixel coordinates of each of the identified calibration points; determining the positional relationship between the calibration points according to the pixel coordinates of the calibration points; based on the calibration points The positional relationship between them and the layout rules of the at least two evaluation sub-picture cards in the evaluation picture card determine at least two areas to be evaluated in the image data.

In one embodiment, the layout rules of the at least two evaluation sub-picture cards in the evaluation picture card include the positions of the at least two evaluation sub-picture cards and the sizes of the at least two evaluation sub-picture cards; The processing unit 802 is configured to determine the at least two areas of the image data to be evaluated based on the positional relationship between the respective calibration points and the layout rules of the at least two evaluation sub-picture cards in the evaluation picture card An implementation manner is: determining a rectangular area included in the image data according to the sizes of the at least two evaluation sub-picture cards, the positions of the at least two evaluation sub-picture cards, and the positional relationship between the respective calibration points ; Determine the rectangular area as the area to be evaluated.

In an embodiment, the processing unit 802 is further configured to: determine the evaluation indicator category to which each of the at least two areas to be evaluated belongs to according to the positions of the respective evaluation sub-picture cards; The evaluation rules corresponding to the index categories are respectively used as the evaluation rules corresponding to each area to be evaluated.

In one embodiment, the evaluation sub-picture card includes any one of the following: a 24-color card for evaluating color accuracy and saturation, a gray card for evaluating average brightness of the picture, and a dry card for evaluating loss of detail Leaf maps, grayscale cards for evaluating signal-to-noise ratio or contrast, and analytical beveled edge cards for evaluating clarity.

In the embodiment of the present invention, after the acquiring unit 801 acquires the image data obtained by shooting the evaluation card including a plurality of evaluation sub-picture cards, the processing unit 802 recognizes the image data based on the preset calibration point pattern. Calibration point, further, the processing unit 802 determines each area to be evaluated in the image data according to the identified calibration point and the layout rules of each evaluation sub-picture card in the evaluation card, and finally the processing unit 802 uses the evaluation corresponding to each evaluation area The rules for carpooling each carpool area separately to obtain the shooting quality evaluation results of the shooting device, you can evaluate multiple categories of evaluation indicators at one time, and automatically identify the areas to be evaluated corresponding to each evaluation indicator to save evaluation time, Improve the evaluation efficiency.

Please refer to FIG. 9, which is a schematic structural diagram of a terminal device according to an embodiment of the present invention. The terminal device shown in FIG. 9 includes a processor 901 and a memory 902, and the memory 902 and the processor 901 are connected through a bus 903 The memory 902 is used to store program instructions.

The memory 902 may include volatile memory (volatile memory), such as random-access memory (RAM); the memory 902 may also include non-volatile memory (non-volatile memory), such as flash memory (flash memory), solid-state drive (SSD), etc.; the memory 902 may also include a combination of the aforementioned types of memory.

The processor 901 may be a central processing unit (Central Processing Unit, CPU). The processor 901 may further include a hardware chip. The above-mentioned hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (programmable logic device, PLD), or the like. The PLD may be a field-programmable gate array (field-programmable gate array, FPGA), general-purpose array logic (generic array logic, GAL), or the like. The processor 901 may also be a combination of the above structures.

In the embodiment of the present invention, the memory 902 is used to store a computer program, and the computer program includes program instructions, and the processor 901 is used to execute the program instructions stored in the memory 902 to implement the above-described embodiment shown in FIG. 3 Steps of the corresponding method.

In one embodiment, the processor 901 is used to execute the program instructions stored in the memory 902, and the processor 901 is configured to execute when the program instructions are called: acquiring an image obtained by the shooting device shooting the evaluation card Data, the evaluation chart includes at least two evaluation sub-picture cards; identifying calibration points in the image data based on calibration point patterns; based on the identified calibration points and the at least two evaluation sub-picture cards in the evaluation The typesetting rules in the graphics card determine at least two areas to be evaluated in the image data; each evaluation area is evaluated using evaluation rules corresponding to the at least two areas to be evaluated to obtain the shooting quality of the shooting device Evaluation results.

In one embodiment, the processor 901 performs the following operations when recognizing the calibration point in the image data based on the calibration point pattern: converting the image data into gray-scale image data; Perform edge detection processing to obtain edge image data; identify the calibration points in the image data based on the shape characteristics of the calibration points, the structural characteristics of the calibration points, and the edge image data.

In one embodiment, the processor 901 performs the following operations when identifying the calibration points in the image data based on the shape characteristics of the calibration points, the structural characteristics of the calibration points, and the edge image data: The edge image data detects a first image element in the image data whose shape feature is the same as the shape feature of the calibration point; from the detected first image element, a structural feature that is the same as that of the calibration point The first image element; the selected first image element is determined as the identified calibration point.

In one embodiment, the shape feature of the calibration point includes a first shape feature and a second shape feature, the processor 901 is based on the shape feature of the calibration point, the structural feature of the calibration point, and the edge When the image data identifies the calibration point in the image data, the following operation is performed: identifying the image data based on the structural feature of the calibration point, the edge image data, the first shape feature, and the second shape feature Calibration point in.

In one embodiment, the processor 901 recognizes the calibration point in the image data based on the structural feature of the calibration point, the edge image data, the first shape feature, and the second shape feature , Performing the following operations: detecting a first image element in the image data having the same shape feature as the first shape feature based on the edge image data; filtering structural features and the calibration points from the detected first image element The first image element with the same structural feature; the second image element whose shape feature is determined to be the same as the second shape feature from the selected first image element by contour recognition; A second image element having the same structural characteristics as the calibration point; the filtered second image element is determined as the identified calibration point.

In one embodiment, the processor 901 is configured to execute when the program instruction is invoked: acquiring the number of identified calibration points; if the number of calibration points is less than the threshold of the number of calibration points, based on the The structural feature of the calibration point, the edge image data, and the first shape feature or the second shape feature identify the calibration point in the image data.

In one embodiment, the processor 901 recognizes the calibration point in the image data based on the structural feature of the calibration point, the edge image data, and the first shape feature or the second shape feature , Performing the following operations: detecting a third image element with the same shape feature in the image data as the first shape feature or the second shape feature based on the edge image data; filtering structural features from the detected third image element The third image element having the same structural characteristics as the calibration point; the filtered third image element is determined as the identified calibration point.

In one embodiment, the processor 901 is configured to execute when the program instruction is invoked: based on the structural feature of the calibration point, the edge image data, and the first shape feature or the first Marks are added to the calibration points identified by the two shape features, and the marks are used to indicate that the accuracy of the calibration points needs to be verified.

In one embodiment, the processor 901 determines at least two areas to be evaluated in the image data based on the identified calibration points and the layout rules of the at least two evaluation sub-picture cards in the evaluation picture card , Perform the following operations: determine the pixel coordinates of each of the identified calibration points; determine the positional relationship between the individual calibration points according to the pixel coordinates of the individual calibration points; based on the The positional relationship between them and the layout rules of the at least two evaluation sub-picture cards in the evaluation picture card determine at least two areas to be evaluated in the image data.

In one embodiment, the layout rules of the at least two evaluation sub-picture cards in the evaluation picture card include the positions of the at least two evaluation sub-picture cards and the sizes of the at least two evaluation sub-picture cards; When the processor 901 determines at least two areas to be evaluated of the image data based on the positional relationship between the respective calibration points and the layout rules of the at least two evaluation sub-picture cards in the evaluation picture card, Perform the following operations: determine the rectangular area included in the image data according to the sizes of the at least two evaluation sub-picture cards, the positions of the at least two evaluation sub-picture cards, and the positional relationship between the respective calibration points ; Determine the rectangular area as the area to be evaluated.

In an embodiment, the processor 901 is configured to execute when the program instruction is invoked: determine, according to the position of each evaluation sub-picture card, each of the at least two areas to be evaluated belongs to the area to be evaluated Categories of evaluation indicators; the evaluation rules corresponding to the categories of evaluation indicators are respectively used as the evaluation rules corresponding to each area to be evaluated.

In one embodiment, the evaluation sub-picture card includes any one of the following: a 24-color card for evaluating color accuracy and saturation, a gray card for evaluating average brightness of the picture, and a dry card for evaluating loss of detail Leaf maps, grayscale cards for evaluating signal-to-noise ratio or contrast, and analytical beveled edge cards for evaluating clarity.

Referring to FIG. 10, it is an evaluation card provided by an embodiment of the present invention. The evaluation card is used to evaluate the shooting quality of a shooting device. The evaluation card may be used in the method embodiment shown in FIG. The evaluation picture card includes five evaluation sub-picture cards and twenty calibration points; the five evaluation sub-picture cards are respectively: the analytical power hypotenuse picture card 1001 for evaluating the sharpness, and the color accuracy for evaluating the color accuracy And saturation 24 color card 1002, gray card 1003 for evaluating the average brightness of the picture, dead leaf map 1004 for evaluating the loss of detail, and gray scale card 1005 for evaluating the signal-to-noise ratio or contrast; One calibration point 1006 is used to divide the five evaluation sub-picture cards.

The resolving power hypotenuse card 1001 is arranged at the center of the evaluation card, the 24-color card 1002 is arranged at the lower left corner of the evaluation card, and the gray card 1003 is arranged at the evaluation card In the upper left corner of the image, the dead leaf map 1004 is configured at the upper right corner of the evaluation card, and the grayscale card 1005 is configured at the bottom of the evaluation card.

A person of ordinary skill in the art may understand that all or part of the processes in the method of the foregoing embodiments may be completed by instructing relevant hardware through a computer program, and the program may be stored in a computer-readable storage medium. During execution, the process of the above method embodiments may be included. Wherein, the storage medium may be a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM) or a random access memory (Random Access Memory, RAM), etc.

The above disclosure is only part of the embodiments of the present invention, and of course it cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention still fall within the scope of the present invention.

Claims (27)

1. A method for evaluating the shooting quality of a shooting device, characterized in that it includes:

   Acquiring image data obtained by shooting an evaluation picture card by a shooting device, the evaluation picture card including at least two evaluation sub-picture cards;

   Identifying the calibration point in the image data based on the calibration point pattern;

   Determine at least two regions to be evaluated in the image data based on the identified calibration points and the layout rules of the at least two evaluation sub-picture cards in the evaluation picture card;

   The evaluation rules corresponding to the at least two areas to be evaluated are respectively evaluated for each area to be evaluated to obtain a shooting quality evaluation result of the shooting device.
2. The method of claim 1, wherein the identifying the calibration point in the image data based on the calibration point pattern includes:

   Convert the image data into grayscale image data;

   Performing edge detection processing on the grayscale image data to obtain edge image data;

   The calibration points in the image data are identified based on the shape characteristics of the calibration points, the structural characteristics of the calibration points, and the edge image data.
3. The method according to claim 2, wherein the identifying the calibration points in the image data based on the shape features of the calibration points, the structural features of the calibration points, and the edge image data includes:

   Detecting, based on the edge image data, a first image element in the image data that has the same shape feature as that of the calibration point;

   Selecting first image elements with the same structural characteristics as the structural characteristics of the calibration point from the detected first image elements;

   The filtered first image element is determined as the identified calibration point.
4. The method according to claim 2, wherein the shape features of the calibration point include a first shape feature and a second shape feature, the shape feature based on the calibration point, the structural feature of the calibration point and The edge image data identifying the calibration points in the image data includes:

   The calibration points in the image data are identified based on the structural features of the calibration points, the edge image data, the first shape features, and the second shape features.
5. The method according to claim 4, wherein the identification of the image data based on the structural features of the calibration point, the edge image data, the first shape feature, and the second shape feature Calibration points, including:

   Detecting, based on the edge image data, a first image element in the image data that has the same shape feature as the first shape feature;

   Selecting first image elements with the same structural characteristics as the structural characteristics of the calibration point from the detected first image elements;

   Identifying the second image element with the same shape feature as the second shape feature from the filtered first image elements through contour recognition;

   Selecting second image elements with the same structural characteristics as the structural characteristics of the calibration point from the second image elements;

   The filtered second image element is determined as the identified calibration point.
6. The method of claim 4, wherein the method further comprises:

   Obtain the number of identified calibration points;

   If the number of calibration points is less than the threshold of calibration points, the calibration in the image data is identified based on the structural features of the calibration points, the edge image data, and the first shape feature or the second shape feature Fixed point.
7. The method according to claim 6, wherein the identification of the image data based on the structural feature of the calibration point, the edge image data, and the first shape feature or the second shape feature Calibration points, including:

   Detecting a third image element with the same shape feature in the image data as the first shape feature or the second shape feature based on the edge image data;

   Selecting third image elements with the same structural characteristics as the structural characteristics of the calibration point from the detected third image elements;

   The filtered third image element is determined as the identified calibration point.
8. The method according to claim 6 or 7, wherein the method further comprises:

   Adding marks to the calibration points identified based on the structural features of the calibration point, the edge image data, and the first shape feature or the second shape feature, the markers are used to indicate the accuracy of the calibration points To be verified.
9. The method according to claim 1, wherein the determination of at least two of the image data based on the identified calibration points and the layout rules of the at least two evaluation sub-picture cards in the evaluation picture card Areas to be evaluated, including:

   Determine the pixel coordinates of each of the identified calibration points;

   Determining the positional relationship between the calibration points according to the pixel coordinates of the calibration points;

   At least two regions to be evaluated in the image data are determined based on the positional relationship between the respective calibration points and the layout rules of the at least two evaluation sub-picture cards in the evaluation picture card.
10. The method according to claim 9, wherein the layout rules of the at least two evaluation sub-picture cards in the evaluation picture card include the positions of the at least two evaluation sub-picture cards and the at least two Evaluate the size of the sub-picture card;

    The determining at least two areas to be evaluated of the image data based on the positional relationship between the respective calibration points and the layout rules of the at least two evaluation sub-picture cards in the evaluation picture card includes:

    Determine the rectangular area included in the image data according to the size of the at least two evaluation sub-picture cards, the positions of the at least two evaluation sub-picture cards, and the positional relationship between the respective calibration points;

    The rectangular area is determined as the area to be evaluated.
11. The method according to claim 10, characterized in that, before each of the regions to be evaluated is evaluated using the evaluation rules corresponding to the at least two regions to be evaluated, the method further comprises:

    Determine the evaluation indicator category to which each area to be evaluated in the at least two areas to be evaluated belongs to the position of each evaluation sub-picture card;

    The evaluation rules corresponding to the evaluation indicator categories are respectively used as the evaluation rules corresponding to each area to be evaluated.
12. The method according to claim 1, wherein the evaluation sub-picture card includes any one of the following: a 24-color card for evaluating color accuracy and saturation, a gray card for evaluating the average brightness of the picture, A dead-leaf graph for evaluating loss of detail, a grayscale card for evaluating signal-to-noise ratio or contrast, and a resolution beveled edge card for evaluating sharpness.
13. A shooting quality evaluation device for a shooting device, characterized in that it includes:

    An obtaining unit, configured to obtain image data obtained by shooting the evaluation picture card by the shooting device, the evaluation picture card including at least two evaluation sub-picture cards;

    A processing unit, configured to identify the calibration point in the image data based on the calibration point pattern;

    The processing unit is further configured to determine at least two areas to be evaluated in the image data based on the identified calibration points and the layout rules of the at least two evaluation sub-picture cards in the evaluation picture card;

    The processing unit is further configured to separately evaluate each area to be evaluated using evaluation rules corresponding to the at least two areas to be evaluated to obtain a shooting quality evaluation result of the shooting device;

    The processing unit is further configured to execute the shooting quality evaluation method according to any one of claims 2-12.
14. An evaluation card, characterized in that the evaluation card is used to evaluate the shooting quality of a shooting device, and the evaluation card includes five evaluation sub-cards and twenty calibration points;

    The five evaluation sub-picture cards are respectively: resolution analysis hypotenuse picture card for evaluating sharpness, 24-color card for evaluating color accuracy and saturation, gray card for evaluating average brightness of the screen, and Dead leaf maps for evaluating loss of detail, and grayscale cards for evaluating signal-to-noise ratio or contrast;

    The twenty calibration points are used to divide the five evaluation sub-picture cards;

    The analytical force hypotenuse card is arranged at the center of the evaluation card, the 24-color card is arranged at the lower left corner of the evaluation card, and the gray card is arranged at the upper left corner of the evaluation card Position, the dead leaf map is arranged at the upper right corner of the evaluation chart card, and the grayscale card is arranged at the bottom position of the evaluation chart card.
15. A terminal device is characterized by comprising a processor and a memory:

    The memory is used to store a computer program, and the computer program includes program instructions;

    When the processor invokes the program instruction, it is used to execute:

    Acquiring image data obtained by shooting an evaluation picture card by a shooting device, the evaluation picture card including at least two evaluation sub-picture cards;

    Identifying the calibration point in the image data based on the calibration point pattern;

    Determine at least two regions to be evaluated in the image data based on the identified calibration points and the layout rules of the at least two evaluation sub-picture cards in the evaluation picture card;

    The evaluation rules corresponding to the at least two areas to be evaluated are respectively evaluated for each area to be evaluated to obtain a shooting quality evaluation result of the shooting device.
16. The terminal device according to claim 15, wherein the processor performs the following operations when identifying the calibration point in the image data based on the calibration point pattern:

    Convert the image data into grayscale image data;

    Performing edge detection processing on the grayscale image data to obtain edge image data;

    The calibration points in the image data are identified based on the shape characteristics of the calibration points, the structural characteristics of the calibration points, and the edge image data.
17. The terminal device according to claim 16, wherein the processor recognizes the calibration point in the image data based on the shape feature of the calibration point, the structural feature of the calibration point, and the edge image data When, do the following:

    Detecting, based on the edge image data, a first image element in the image data that has the same shape feature as that of the calibration point;

    Selecting first image elements with the same structural characteristics as the structural characteristics of the calibration point from the detected first image elements;

    The filtered first image element is determined as the identified calibration point.
18. The terminal device according to claim 16, wherein the shape feature of the calibration point includes a first shape feature and a second shape feature, and the processor is based on the shape feature of the calibration point, the calibration point When the structural features and the edge image data identify the calibration points in the image data, the following operations are performed:

    The calibration points in the image data are identified based on the structural features of the calibration points, the edge image data, the first shape features, and the second shape features.
19. The terminal device according to claim 18, wherein the processor recognizes the terminal based on the structural feature of the calibration point, the edge image data, the first shape feature, and the second shape feature When calibrating points in image data, perform the following operations:

    Detecting, based on the edge image data, a first image element in the image data that has the same shape feature as the first shape feature;

    Selecting first image elements with the same structural characteristics as the structural characteristics of the calibration point from the detected first image elements;

    Identifying the second image element with the same shape feature as the second shape feature from the filtered first image elements through contour recognition;

    Selecting second image elements with the same structural characteristics as the structural characteristics of the calibration point from the second image elements;

    The filtered second image element is determined as the identified calibration point.
20. The terminal device according to claim 18, characterized in that, when the processor calls the program instruction, it also executes:

    Obtain the number of identified calibration points;

    If the number of calibration points is less than the threshold of calibration points, the calibration in the image data is identified based on the structural features of the calibration points, the edge image data, and the first shape feature or the second shape feature Fixed point.
21. The terminal device according to claim 20, wherein the processor recognizes the terminal based on the structural feature of the calibration point, the edge image data, and the first shape feature or the second shape feature When calibrating points in image data, perform the following operations:

    Detecting a third image element with the same shape feature in the image data as the first shape feature or the second shape feature based on the edge image data;

    Selecting third image elements with the same structural characteristics as the structural characteristics of the calibration point from the detected third image elements;

    The filtered third image element is determined as the identified calibration point.
22. The terminal device according to claim 20 or 21, wherein when the processor calls the program instruction, it also executes:

    Adding marks to the calibration points identified based on the structural features of the calibration point, the edge image data, and the first shape feature or the second shape feature, the markers are used to indicate the accuracy of the calibration points To be verified.
23. The terminal device according to claim 15, wherein the processor determines the image data based on the identified calibration point and the typesetting rules of the at least two evaluation sub-picture cards in the evaluation picture card When there are at least two areas to be evaluated, perform the following operations:

    Determine the pixel coordinates of each of the identified calibration points;

    Determining the positional relationship between the calibration points according to the pixel coordinates of the calibration points;

    At least two regions to be evaluated in the image data are determined based on the positional relationship between the respective calibration points and the layout rules of the at least two evaluation sub-picture cards in the evaluation picture card.
24. The terminal device according to claim 23, wherein the typesetting rules of the at least two evaluation sub-picture cards in the evaluation picture card include positions of the at least two evaluation sub-picture cards and the at least two The size of the evaluation sub-card;

    The processor executes when determining at least two areas of the image data to be evaluated based on the positional relationship between the respective calibration points and the layout rules of the at least two evaluation sub-picture cards in the evaluation picture card Operate as follows:

    Determine the rectangular area included in the image data according to the size of the at least two evaluation sub-picture cards, the positions of the at least two evaluation sub-picture cards, and the positional relationship between the respective calibration points;

    The rectangular area is determined as the area to be evaluated.
25. The terminal device according to claim 24, wherein when the processor invokes the program instruction, it also executes:

    Determine, according to the position of each evaluation sub-picture card, the evaluation indicator category to which each of the at least two areas to be evaluated belongs to the area to be evaluated;

    The evaluation rules corresponding to the evaluation indicator categories are respectively used as the evaluation rules corresponding to each area to be evaluated.
26. The terminal device according to claim 15, wherein the evaluation sub-picture card includes any one of the following: a 24-color card for evaluating color accuracy and saturation, and a gray card for evaluating average brightness of the picture , A dead leaf graph for evaluating loss of detail, a grayscale card for evaluating signal-to-noise ratio or contrast, and a analytic force hypotenuse graph card for evaluating sharpness.
27. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program, and the computer program includes program instructions, which when executed by a processor causes the processor to execute as rights The method for evaluating the shooting quality of the shooting device according to any one of claims 1-12 is required.

Images