Image detection device, method and computer readable storage medium

Abstract

The present invention provides an image detection device, method and computer-readable storage medium, which belong to the field of camera testing technology and solve the problems of low detection efficiency, low detection accuracy and poor consistency in the prior art when performing clarity detection on a camera. An image detection device includes a camera, a relay mirror, a control device and an image analysis device; the relay mirror is arranged in front of the lens of the camera; the control device is electrically connected to the relay mirror, and the control device is used to control the position switching of the relay mirror so that the relay mirror is located in front of the lens of the camera or moves away from the front of the lens of the camera; the image analysis device is connected to the camera via a network interface, and the image analysis device is used to perform clarity detection on the picture collected by the camera.

Description

Technical Field

[0001] The present invention relates to the technical field of camera testing, and in particular to an image detection device, method and computer-readable storage medium. Background Art

[0002] As the application demand for camera products in the current market continues to grow, the efficiency requirements for their production and debugging links are becoming increasingly higher, among which clarity detection is the core detection content in the camera production and debugging link.

[0003] At present, clarity detection is basically done manually, that is, people use their naked eyes to check the camera's presentation of the clarity test card. If black and white are clearly distinguished, it is clear; if black and white are not clearly distinguished, it is blurry. However, there are many levels of clarity of black and white. Therefore, when performing clarity detection manually, there are problems such as overly subjective evaluation, poor consistency, and low efficiency.

[0004] Therefore, the existing technology has the problems of low detection efficiency, low detection accuracy and poor consistency when performing clarity detection on cameras. Summary of the invention

[0005] The object of the present invention is to provide an image detection device, method and computer-readable storage medium to alleviate the technical problems of low detection efficiency, low detection accuracy and poor consistency in the prior art when performing clarity detection on a camera.

[0006] In a first aspect, the present invention provides an image detection device, comprising a camera, a relay mirror, a control device and an image analysis device;

[0007] The relay lens is arranged in front of the lens of the camera;

[0008] The control device is electrically connected to the relay mirror, and the control device is used to control the position switching of the relay mirror so that the relay mirror is located in front of the lens of the camera or is moved away from the front of the lens of the camera;

[0009] The image analysis device is connected to the camera via a network interface, and the image analysis device is used to perform clarity detection on the pictures collected by the camera.

[0010] Furthermore, the image analysis device is a computer integrated with a CPU processor.

[0011] Further, the control device includes a main control board, a relay and a solenoid valve;

[0012] The signal input end of the main control board is connected to the computer via a serial port, and the signal output end of the main control board is connected to the input end of the relay;

[0013] The output end of the relay is connected to the solenoid valve;

[0014] The relay mirror module is fixed to the solenoid valve.

[0015] Furthermore, it also includes an image test chart and a light averaging board;

[0016] The image test card is attached to the surface of the light-homogenizing plate, and the camera shoots the image test card, and the shot image is used for clarity detection.

[0017] In a second aspect, the present invention further provides an image detection method, which is applied to the image detection device provided in the first aspect, and the method comprises:

[0018] Receiving a detection image;

[0019] Preprocessing the detection image to obtain a pattern image;

[0020] Calculating the histogram peak distance of the pattern image to obtain the histogram peak distance value;

[0021] Calculate the standard deviation of the pattern image to obtain the image standard deviation value;

[0022] The image clarity score is obtained by performing linear weighted calculation using the histogram peak distance value and the image standard deviation value;

[0023] Compare the image clarity score with the preset threshold and obtain the clarity detection result.

[0024] Furthermore, the step of calculating the histogram peak distance of the pattern image to obtain the histogram peak distance value includes:

[0025] The difference between the first peak and the second peak in the histogram of the pattern image is calculated to obtain a histogram peak distance value.

[0026] Furthermore, the step of performing linear weighted calculation using the histogram peak distance value and the image standard deviation value to obtain the image clarity score includes:

[0027] The histogram peak distance value and the image standard deviation value are used to perform linear weighted calculation to obtain a weighted value;

[0028] The weighted values ​​are normalized to obtain the image clarity score.

[0029] Furthermore, the step of preprocessing the detection image to obtain the pattern area includes:

[0030] Positioning the detection area of ​​the detection image to obtain a positioned detection image;

[0031] The detected image after positioning is subjected to pattern interception to obtain a pattern image.

[0032] Furthermore, the step of positioning the detection area of ​​the detection image to obtain the positioned detection image includes:

[0033] Performing rough positioning of the detection area on the detection image to obtain a rough positioning image;

[0034] The detection area is precisely positioned on the coarse positioning image to obtain a positioned detection image.

[0035] In a third aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method provided in the second aspect are implemented.

[0036] The present invention provides an image detection device, comprising a camera, a relay mirror, a control device and an image analysis device; the relay mirror is arranged in front of the camera lens, and the relay mirror is used to simulate the actual shooting object distance of the camera, and can simulate the object distance of more than several meters within a very close object distance range. It is convenient to test the clarity of the camera and save the test space. The control device is electrically connected to the relay mirror, and the control device is used to control the position switching of the relay mirror, so that the relay mirror is located in front of the camera lens or moved away from the front of the camera lens; the camera will switch the filter in the day and night mode, and when the filter function is detected, the relay mirror needs to be moved away from the front of the lens. The position switching of the relay mirror is controlled by the control device, and when the image is collected, the relay mirror is located in front of the lens, and when the filter function is detected, the relay mirror is moved away from the front of the lens, so that the camera can not only collect images, but also meet the operation requirements of the day and night mode. The image analysis device is connected to the camera through a network interface, and the image analysis device is used to detect the clarity of the pictures collected by the camera. The image analysis device obtains the detection image from the camera through the network port, and performs clarity detection on the detection image using a clarity algorithm, thereby obtaining a clarity detection result.

[0037] By adopting the image detection device provided by the present invention, a relay lens is used to simulate the object distance, and the position switching of the relay lens is controlled by a control device. The camera is compatible with image acquisition operations in day and night modes. The image analysis device obtains the detection image collected by the camera through the network port, and uses an algorithm to perform clarity detection on the detection image, thereby realizing automatic clarity detection of the camera, improving the clarity detection efficiency, and effectively avoiding the problems of overly subjective evaluation and poor consistency during manual clarity detection, unifying the clarity detection standard, and optimizing the clarity detection effect.

[0038] Correspondingly, an image detection method and a computer-readable storage medium provided by the present invention also have the above-mentioned technical effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 A schematic diagram of an image detection device provided in Example 1 of the present invention;

[0041] Figure 2 This is a schematic diagram of an image test card in Embodiment 1 of the present invention;

[0042] Figure 3 A flow chart of an image detection method provided in Example 2 of the present invention;

[0043] Figure 4 is a detailed flow chart of step S5 in embodiment 2 of the present invention;

[0044] Figure 5 is a detailed flow chart of step S2 in embodiment 2 of the present invention;

[0045] Figure 6 This is a detailed flow chart of step S22 in embodiment 2 of the present invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] The terms "including" and "having" and any variations thereof mentioned in the embodiments of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0048] At present, clarity detection is basically done manually, that is, people use their naked eyes to check the camera's presentation of the clarity test card. If black and white are clearly distinguished, it is clear; if black and white are not clearly distinguished, it is blurry. However, there are many levels of clarity of black and white. Therefore, when performing clarity detection manually, there are problems such as overly subjective evaluation, poor consistency, and low efficiency.

[0049] Therefore, the existing technology has the problems of low detection efficiency, low detection accuracy and poor consistency when performing clarity detection on cameras.

[0050] In order to solve the above problems, an embodiment of the present invention provides an image detection device.

[0051] Embodiment 1:

[0052] like Figure 1 As shown, an image detection device provided by an embodiment of the present invention includes a camera 1, a relay lens 2, a control device 3 and an image analysis device 4; the relay lens 2 is arranged in front of the lens of the camera 1, for example, the relay lens 2 is located 2CM in front of the lens, and the relay lens 2 is used to simulate the actual shooting object distance of the camera 1, and can simulate an object distance of more than several meters in a very close object distance range. It is convenient to test the clarity of the camera 1 and save the test space. The control device 3 is electrically connected to the relay lens 2, and the control device 3 is used to control the position switching of the relay lens 2, so that the relay lens 2 is located in front of the lens of the camera 1 or is moved away from the front of the lens of the camera 1; the camera 1 will switch the filter in the day and night mode, and when the filter function is detected, the relay lens 2 needs to be moved away from the front of the lens. The position switching of the relay lens 2 is controlled by the control device 3, and when the image is collected, the relay lens 2 is located in front of the lens, and when the filter function is detected, the relay lens 2 is moved away from the front of the lens, so that the camera 1 can not only collect images, but also meet the operation requirements of the day and night mode. The image analysis device 4 is connected to the camera 1 through a network interface, and is used to perform clarity detection on the image captured by the camera 1. The image analysis device 4 obtains the detection image in the camera 1 through the network port, and performs clarity detection on the detection image using a clarity algorithm, thereby obtaining a clarity detection result.

[0053] By adopting the image detection device provided by the embodiment of the present invention, the relay lens 2 is used to simulate the object distance, and the position switching of the relay lens 2 is controlled by the control device 3. The camera 1 is compatible with the image acquisition operation in the day and night mode. The image analysis device 4 obtains the detection image collected by the camera 1 through the network port, and uses the algorithm to perform clarity detection on the detection image, thereby realizing automatic clarity detection of the camera 1, improving the clarity detection efficiency, and effectively avoiding the problem of overly subjective evaluation and poor consistency during manual clarity detection, unifying the clarity detection standard, and optimizing the clarity detection effect.

[0054] In one possible implementation, the image analysis device 4 is a computer integrated with a CPU processor 5, and the CPU processor 5 is used to execute the image detection method in Example 2. The CPU processor 5 adopts an Intel I7-7 generation processor with an integrated 3.6Ghz dual-core, has a fast processing speed, and can provide the advantages of efficient and abundant computing resources. The image processing speed is fast, thereby maximizing the efficiency of clarity detection.

[0055] In a possible implementation, the control device 3 includes a main control board (not shown in the figure), a relay (not shown in the figure) and a solenoid valve (not shown in the figure); the signal input end of the main control board is connected to the computer through a serial port, and the signal output end of the main control board is connected to the input end of the relay; the output end of the relay is connected to the solenoid valve; the relay mirror 2 is fixed to the solenoid valve. The signal input end of the main control board receives the control instruction of the computer through the serial port, the main control board receives and analyzes the control instruction, and controls the relay according to the control instruction, so that the relay drives the solenoid valve to open or close, thereby completing the position switching of the relay mirror 2.

[0056] In a possible implementation manner, the image detection device further includes: Figure 2 The image test card 6 and the light scattering plate 7 are shown; the image test card 6 is attached to the surface of the light scattering plate 7, and the camera 1 shoots the image test card 6, and the shot image is used for clarity detection. The image test card 6 is printed after the line pair pattern layout is carried out according to the line diameter density of the national standard clarity card. The image test card 6 is attached to the surface of the light scattering plate 7, so that the light in the shooting environment is sufficient and uniform, so that the camera 1 can capture images with normal brightness and normal clarity, which is conducive to the clarity analysis of the image.

[0057] Embodiment 2:

[0058] like Figure 3 As shown, an embodiment of the present invention provides an image detection method, which is applied to the image detection device provided in Example 1, and the method includes:

[0059] S1: Receive detection image.

[0060] S2: Preprocess the detection image to obtain a pattern image.

[0061] S3: Calculate the histogram peak distance of the pattern image to obtain a histogram peak distance value.

[0062] S4: Calculate the standard deviation of the pattern image to obtain a standard deviation value of the image.

[0063] S5: Perform linear weighted calculation using the histogram peak distance value and the image standard deviation value to obtain the image clarity score.

[0064] S6: Compare the image clarity score with a preset threshold value to obtain a clarity detection result.

[0065] By calculating the histogram peak distance of the pattern image, the histogram peak distance value is obtained to characterize the overall dynamic range of the image. The standard deviation of the pattern image is calculated to obtain the image standard deviation value. The standard deviation calculates the distance between each pixel and the overall mean, which is used to characterize the degree of divergence of the image pixel distribution. The histogram peak distance value and the image standard deviation value are used to perform linear weighted calculation to obtain the image clarity score of the area. The clarity score of each area is compared with the preset threshold. If the score is greater than the threshold, it means that the line number has passed the standard. All line number areas are analyzed, and the area with the highest line value greater than the threshold is the clarity line value of the device, thereby completing the automatic clarity detection of the camera.

[0066] In a possible implementation, step S3 includes:

[0067] S31: Calculate the difference between the first peak and the second peak in the histogram of the pattern image to obtain a histogram peak distance value.

[0068] The difference between the first peak value and the second peak value is the distance between the brightest pixel group and the lowest pixel group in the image, which is used to characterize the divergence of the pixel distribution in the image.

[0069] like Figure 4 As shown, in a possible implementation manner, step S5 includes:

[0070] S51: Perform linear weighted calculation using the histogram peak distance value and the image standard deviation value to obtain a weighted value.

[0071] S52: normalizing the weighted value to obtain an image clarity score.

[0072] Normalization can summarize the statistical distribution of unified samples.

[0073] like Figure 5 As shown, in a possible implementation manner, step S2 includes:

[0074] S21: Positioning the detection area of ​​the detection image to obtain a positioned detection image.

[0075] S22: performing pattern capture on the positioned detection image to obtain a pattern image.

[0076] The detected image after positioning has accurate key point positions, and the area where the clarity lines are located is accurately positioned through the key point positions, and the pattern area of ​​each line number is cut out for clarity analysis.

[0077] like Figure 6 As shown, in a possible implementation manner, step S22 includes:

[0078] S221: performing coarse positioning of the detection area on the detection image to obtain a coarse positioning image.

[0079] S222: Perform fine positioning of the detection area on the coarse positioning image to obtain a positioned detection image.

[0080] To locate the detected area, the positioning needs to be very accurate and achieve pixel-level accuracy. The deep learning method is used to locate the key points. The detection area is first roughly positioned, and then the detection area is finely positioned to achieve pixel-level accuracy.

[0081] For example, coarse positioning uses the HRnet network (a deep learning algorithm) to locate multiple key points and train the HRnet model. A total of more than 5,000 clarity image samples with different resolutions and focal lengths were collected, and six data enhancement methods including angle rotation, brightness, contrast, chroma, mirror and Gaussian filtering were used to enhance the data. The model was trained under the pytorch architecture.

[0082] Due to the characteristics of HRnet and the limitations of the receptive field, the detection results of large-resolution images cannot meet the pixel-level requirements, and there is a problem that the corner points cannot be accurately located. To solve the above problems, precise positioning is required. The training of the precise positioning model uses the YOLO network (a deep learning algorithm) to perform secondary positioning on key points that are not accurately located. In the same way, more than 6,000 images containing key points are randomly cropped as positive samples, and other positions are used as negative samples. Data enhancement is also performed for model training. The trained model can already meet the requirements of positioning accuracy for key point detection.

[0083] Embodiment 3:

[0084] An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method provided in Embodiment 2 are implemented.

[0085] The image detection method and computer-readable storage medium provided by the present invention have the same technical features as the image detection device provided in the above embodiments, and therefore can also solve the same technical problems and achieve the same technical effects.

[0086] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0087] In the description of the present invention, it should be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc. indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings, or are the directions or positional relationships in which the inventive product is usually placed when in use. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as a limitation on the present invention.

[0088] In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0089] The device provided in the embodiment of the present invention may be specific hardware on the device or software or firmware installed on the device. The implementation principle and technical effects of the device provided in the embodiment of the present invention are the same as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment. It can be clearly understood by those skilled in the art that for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above can all refer to the corresponding processes in the aforementioned method embodiment, and will not be repeated here.

[0090] In several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0091] For another example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For another example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some communication interface, device or unit, which can be electrical, mechanical or other forms.

[0092] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0093] In addition, each functional unit in the embodiment provided by the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0094] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0095] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention. They should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. An image detection method, characterized in that: Applied to an image detection device, the image detection device comprises a camera, a relay mirror, a control device and an image analysis device; the relay mirror is arranged in front of the lens of the camera; the control device is electrically connected to the relay mirror, and the control device is used to control the position switching of the relay mirror so that the relay mirror is located in front of the lens of the camera or is moved away from the front of the lens of the camera; The image analysis device is connected to the camera via a network interface, and the image analysis device is used to perform clarity detection on the image captured by the camera; The method comprises: Receiving a detection image; Preprocessing the detection image to obtain a pattern image; Calculating the histogram peak distance of the pattern image to obtain the histogram peak distance value; Calculate the standard deviation of the pattern image to obtain the image standard deviation value; The image clarity score is obtained by performing linear weighted calculation using the histogram peak distance value and the image standard deviation value; Compare the image clarity score with the preset threshold and obtain the clarity detection result.

2. The image detection method according to claim 1, characterized in that: The step of calculating the histogram peak distance of the pattern image to obtain the histogram peak distance value includes: The difference between the first peak and the second peak in the histogram of the pattern image is calculated to obtain a histogram peak distance value.

3. The image detection method according to claim 1, characterized in that: The step of performing linear weighted calculation using the histogram peak distance value and the image standard deviation value to obtain the image clarity score includes: The histogram peak distance value and the image standard deviation value are used to perform linear weighted calculation to obtain a weighted value; The weighted values ​​are normalized to obtain the image clarity score.

4. The image detection method according to claim 1, characterized in that: The step of preprocessing the detection image to obtain the pattern area includes: Positioning the detection area of ​​the detection image to obtain a positioned detection image; The detected image after positioning is subjected to pattern interception to obtain a pattern image.

5. The image detection method according to claim 4, characterized in that: The step of positioning the detection area of ​​the detection image to obtain the positioned detection image comprises: Performing rough positioning of the detection area on the detection image to obtain a rough positioning image; The detection area is precisely positioned on the coarse positioning image to obtain a positioned detection image.

6. The image detection method according to claim 1, characterized in that: The image analysis device is a computer integrated with a CPU processor.

7. The image detection method according to claim 6, characterized in that: The control device includes a main control board, a relay and a solenoid valve; The signal input end of the main control board is connected to the computer via a serial port, and the signal output end of the main control board is connected to the input end of the relay; The output end of the relay is connected to the solenoid valve; The relay mirror module is fixed to the solenoid valve.

8. The image detection method according to claim 1, characterized in that: Also includes image test chart and homogenizing plate; The image test card is attached to the surface of the light-homogenizing plate, and the camera shoots the image test card, and the shot image is used for clarity detection.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images