CN115484455A - Camera image out-of-focus detection method, device, electronic equipment and storage medium - Google Patents

Abstract

The application discloses a camera image out-of-focus detection method and device, electronic equipment and a storage medium. Firstly, acquiring a video image acquired by a target camera, and calculating the horizontal and longitudinal gradient strength in the current frame video image to obtain a gradient strength map; calculating the mean value of the gradient intensity image to obtain the definition index of the current frame video image; then extracting a consistency characteristic diagram of the current frame video image and the previous frame video image; carrying out average value calculation on the consistency characteristic images of the current frame video image and the previous frame video image to obtain a consistency index of the current frame video image to the previous frame video image; and finally, obtaining an image out-of-focus detection result based on the definition index and the consistency index. The method and the device have the advantages that the gradient intensity index and the consistency characteristic index of the front frame and the back frame of the image are cooperatively detected, so that the detection accuracy is improved; and the number of dynamic images for carrying out consistency characteristic index calculation is 2, and the detection speed is improved.

Description

Camera image out-of-focus detection method, device, electronic equipment and storage medium

technical field

The present invention relates to the technical field of video image processing, in particular to a camera image out-of-focus detection method, device, electronic equipment and storage medium.

Background technique

Surveillance cameras are installed in many scenes at home and abroad for public security, transportation and other fields. In some cases, criminals use abnormal means to interfere, or the image of the surveillance camera is out of focus due to weather. The existing solution is to manually check whether the camera is out of focus by manually checking the video image of the camera.

However, the workload of manual real-time monitoring of a large number of cameras is enormous, and it is greatly affected by factors such as the environment, which is likely to cause misjudgment.

Contents of the invention

Based on this, the embodiment of the present application provides a camera image out-of-focus detection method, device, electronic equipment, and storage medium. Through image processing technology, it can automatically detect whether the camera image is out of focus, and can make an alarm response within milliseconds. , which greatly reduces the maintenance workload of the camera, greatly shortens the alarm response time, and improves the detection accuracy.

In the first aspect, a camera image out-of-focus detection method is provided, the method comprising:

Obtain the video image collected by the target camera, calculate the horizontal and vertical gradient strengths in the current frame video image, and obtain the gradient strength map;

Carry out mean value calculation to described gradient intensity map, obtain the sharpness index dft of described current frame video image;

Extracting the consistency feature map of the current frame video image and the previous frame video image;

Carry out average value calculation to the consistency feature map of described current frame video image and described last frame video image, obtain the consistency index sim of current frame video image contrast with last frame video image;

An image out-of-focus detection result is obtained based on the sharpness index dft and the consistency index sim.

Optionally, the method also includes:

The image data of the current frame video image is saved for out-of-focus detection of the next frame video image.

Optionally, the obtaining the image out-of-focus detection result based on the sharpness index dft and the consistency index sim includes:

Verifying the definition index dft and the consistency index sim according to the preset definition index threshold and consistency index threshold;

When the sharpness index dft is lower than the sharpness index threshold and the consistency index sim is higher than the consistency index threshold, it is determined that the image of the target camera is out of focus, and through a predetermined communication channel Carry out out-of-focus alarm.

Optionally, the calculation of the horizontal and vertical gradient strengths in the current frame video image to obtain a gradient strength map includes:

Calculate the grayscale value of all pixels in the current frame video image, and convert the current frame video image into a grayscale image;

The approximate gradient of each pixel is calculated by using the forward difference quotient to obtain the gradient intensity map.

Optionally, performing mean calculation on the gradient intensity map to obtain the definition index dft of the current frame video image, including:

Determine the definition index dft according to the first formula, and the first formula specifically includes:

表示当前图像某个像素点对应的x方向的梯度强度值，

表示当前图像某个像素点对应的y方向的梯度强度值，k表示图像中像素点的索引值。Among them, w represents the width of the image, h represents the height of the image,

Indicates the gradient strength value in the x direction corresponding to a certain pixel in the current image,

Indicates the gradient strength value in the y direction corresponding to a certain pixel in the current image, and k indicates the index value of the pixel in the image.

Optionally, extracting the consistency feature map of the current frame video image and the previous frame video image includes:

Determine the consistent feature value of the pixel based on the grayscale value of the pixel in the current frame video image and the grayscale value of the corresponding pixel in the previous frame of video image;

Traverse all the pixels in the video image to get the consistent feature map.

Optionally, performing average calculation on the consistency feature map of the current frame video image and the previous frame video image to obtain the consistency index sim of the current frame video image compared with the previous frame video image, including:

Determine the consistency index sim according to the second formula, and the second formula specifically includes:

Among them, w represents the width of the image, h represents the height of the image, and simP represents the consistent feature value of the current frame video image at the pixel (x, y) position.

In a second aspect, a camera image out-of-focus detection device is provided, the device comprising:

The gradient calculation module is used to obtain the video image collected by the target camera, calculate the horizontal and vertical gradient strengths in the current frame video image, and obtain the gradient strength map;

The first calculation module is used to calculate the mean value of the gradient intensity map to obtain the definition index dft of the current frame video image;

An extraction module, used to extract the consistency feature map of the current frame video image and the previous frame video image;

The second calculation module is used to calculate the average value of the consistency feature map of the current frame video image and the previous frame video image, and obtain the consistency index sim of the current frame video image compared with the previous frame video image;

The detection module obtains an image out-of-focus detection result based on the sharpness index dft and the consistency index sim.

In a third aspect, an electronic device is provided, including a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the camera image defocus detection method described in any one of the above first aspects is implemented.

In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the camera image defocus detection method described in any one of the above-mentioned first aspects is implemented.

In the technical solution provided by the embodiment of the present application, first obtain the video image collected by the target camera, calculate the horizontal and vertical gradient strengths in the current frame video image, and obtain the gradient strength map; perform mean calculation on the gradient strength map to obtain the current frame video The sharpness index of the image; then extract the consistency feature map of the current frame video image and the previous frame video image; calculate the average value of the consistency feature map of the current frame video image and the previous frame video image to obtain the current frame video image Compared with the consistency index of the previous frame video image; finally, the image out-of-focus detection result is obtained based on the sharpness index and the consistency index.

The beneficial effects brought by the technical solutions provided by the embodiments of the present application at least include:

(1) The detection algorithm uses the gradient strength index of the image and the consistency feature index of the front and rear frames of the image to jointly detect, and the accuracy is greatly improved.

(2) The number of dynamic images for the calculation of the consistency characteristic index is 2, the automatic alarm response time of time detection reaches the millisecond level, and the detection reaction speed is particularly fast.

Description of drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the accompanying drawings that are required in the description of the embodiments or the prior art. Apparently, the drawings in the following description are only exemplary, and those skilled in the art can obtain other implementation drawings according to the provided drawings without creative effort.

FIG. 1 is a flow chart of the steps of a camera image out-of-focus detection method provided by an embodiment of the present application;

FIG. 2 is a flow chart of the steps of a camera image out-of-focus detection method provided in an optional embodiment of the present application;

FIG. 3 is a block diagram of a camera image out-of-focus detection device provided by an embodiment of the present application;

FIG. 4 is a schematic diagram of an electronic device provided by an embodiment of the present application.

detailed description

In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

In the description of the present invention, the terms "comprising", "having" and any variations thereof are intended to cover a non-exclusive inclusion, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to Those steps or units that have been explicitly listed, but may also include other steps or units that are not explicitly listed but inherent to these processes, methods, products or equipment, or are added based on the further optimization scheme of the present invention. steps or units.

In order to solve the real-time detection problem of manual maintenance camera image out-of-focus existing in the prior art, the present invention automatically detects whether the camera image is out of focus through image processing technology, and can make an alarm response within milliseconds, greatly reducing the The maintenance workload of the camera is reduced, and the alarm response time is greatly shortened, and the detection accuracy is improved. The present invention automatically detects whether the image of the camera is out of focus through the image processing technology, and can make an alarm response within millisecond level. Please refer to FIG. 1, which shows a flow chart of a camera image out-of-focus detection method provided by an embodiment of the present application. The method may include the following steps:

In step 101, the video image collected by the target camera is obtained, and the horizontal and vertical gradient strengths in the current frame of the video image are calculated to obtain a gradient strength map.

In the embodiment of the present application, the grayscale values of all pixels in the current frame video image are calculated, and the current frame video image is converted into a grayscale image. The approximate gradient of each pixel is calculated by using the forward difference quotient to obtain the gradient intensity map.

In this step, the horizontal and vertical gradient strengths of the video image at the current moment of the camera are calculated to obtain the gradient strength map,

The gray level of the image refers to the intensity of the image pixel, black is the darkest, white is the brightest, black is represented by 0, and white is represented by 255.

A pixel is basically represented by three color components of RGB. R (0-255), G (0-255), B (0-255).

The grayscale of the image is what is left after removing the color, which represents the lightness and darkness of the image.

The gray value f(x,y) of the pixel is calculated by the following method.

Method: f(x,y)=(R(x,y)+G(x,y)+B(x,y))/3

x, y represent the coordinates of the pixels in the image.

Through the above method, the image is converted into a grayscale image, which is actually the binary function f(x, y) of the pixel position, but it is discrete, and the image gradient is the partial derivative of this binary discrete function. The image gradient is calculated pixel by pixel.

The partial derivatives of continuous binary functions are:

But the image is a discrete function, there is no way for Δx to tend to 0, and the minimum can only be an interval of 1, so it is necessary to use finite difference to calculate the approximate gradient. This method uses the forward difference quotient to calculate the approximate gradient. Therefore, the image partial derivative formula is transformed into the following formula:

x, y represent the coordinates of the pixels in the image.

Step 102, performing mean calculation on the gradient intensity map to obtain the sharpness index dft of the current frame video image.

In the embodiment of the present application, the average value calculation is performed on the horizontal and vertical gradient intensity maps of the video image to obtain the image definition index dft, including:

Determine the definition index dft according to the first formula, the first formula specifically includes:

表示当前图像某个像素点对应的x方向的梯度强度值，

表示当前图像某个像素点对应的y方向的梯度强度值，k表示图像中像素点的索引值。Among them, w represents the width of the image, h represents the height of the image,

Indicates the gradient strength value in the x direction corresponding to a certain pixel of the current image,

Indicates the gradient strength value in the y direction corresponding to a certain pixel in the current image, and k indicates the index value of the pixel in the image.

Step 103, extracting the consistency feature map between the video image of the current frame and the video image of the previous frame.

In the embodiment of the present application, the consistency feature map of the current frame video image and the previous frame video image is extracted, including:

Determine the consistent feature value of the pixel based on the gray value of the pixel in the current frame video image and the gray value of the corresponding pixel in the previous frame video image; traverse all the pixels in the video image to obtain the consistent feature map.

Specifically, through:

simP(x,y)=abs(f(x,y)-fp(x,y))

Determine, where x, y represent the coordinates of a pixel in the image, f(x, y) is the gray value of the current image, fp(x, y) is the gray value of the previous frame of the current image, simP (x, y) is the pixel consistency feature value of the current image at the pixel point (x, y), and the abs function means to calculate the absolute value of the input parameters.

Step 104: Perform average calculation on the consistency feature map of the current frame video image and the previous frame video image to obtain the consistency index sim of the current frame video image compared with the previous frame video image.

In the embodiment of the present application, the consistency index sim is determined according to the second formula, and the second formula specifically includes:

Among them, w represents the width of the image, h represents the height of the image, and simP represents the consistent feature value of the current frame video image at the pixel (x, y) position.

In step 105, an image out-of-focus detection result is obtained based on the definition index dft and the consistency index sim.

Wherein, the sim value and the dft value are checked, the higher the sim value, the greater the difference between the front and back frame images, and the lower the sim value, the smaller the difference between the front and back frame images. The higher the dft index value, the clearer the image, and the lower the dft index value, the blurrier the image.

In the embodiment of the present application, the clarity index dft and the consistency index sim are verified according to the preset clarity index threshold and consistency index threshold; when the clarity index dft is lower than the clarity index threshold, and the consistency index When the sim is higher than the consistency index threshold, it is determined that the image of the target camera is out of focus, and an out-of-focus alarm is issued through a predetermined communication channel.

Specifically, the preset sharpness index threshold in this application may be any number between (7.0-10.0), and the consistency index threshold may be any number (3.0-5.0).

When the dft index is lower than the preset value (7.0-10.0), and the sim index is higher than the preset value (3.0-5.0), this method considers that the current frame video image of the camera is changing from the previous image, and the image is out of focus. That is, an out-of-focus alarm is performed through a predetermined communication channel. On the contrary, it is considered that there is no out-of-focus, and no alarm is issued.

Also include after step 105:

Step 106, saving the image data of the current frame of video image for defocus detection of the next frame of video image.

In the embodiment of the present application, the current image data is stored in the cache for defocus detection of subsequent video images.

As shown in Figure 2, the processing flow of camera image out-of-focus detection through the method of this application is given, which specifically includes:

Step 201, extracting the gradient strength of the current image;

Step 202, calculating the gradient strength index of the current image;

Step 203, extracting the consistency feature map between the current image and the previous frame image;

Step 204, calculating the consistency feature index between the current image and the previous frame image;

Step 205, using the gradient strength index and the consistency characteristic index to perform out-of-focus detection;

Step 206, updating or adding cached image data.

To sum up, it can be seen that this application uses the gradient intensity map of a single frame video image and the consistency feature map of the preceding and following frames of a multi-frame video image to perform image feature calculation. And a method based on calculating the gradient intensity map and a method of calculating the consistency feature map of the front and back frames of the image are proposed. The simultaneous detection algorithm uses the gradient strength index of the image and the consistency feature index of the front and rear frames of the image to jointly detect.

Please refer to FIG. 3 , which shows a block diagram of a camera image out-of-focus detection device 300 provided by an embodiment of the present application. As shown in FIG. 3 , the apparatus 300 may include: a gradient calculation module 301 , a first calculation module 302 , an extraction module 303 , a second calculation module 304 and a detection module 305 .

The gradient calculation module 301 is used to obtain the video image collected by the target camera, calculate the horizontal and vertical gradient strength in the current frame video image, and obtain the gradient strength map;

The first calculation module 302 is used to calculate the mean value of the gradient intensity map to obtain the definition index dft of the current frame video image;

The extraction module 303 is used to extract the consistency feature map of the current frame video image and the previous frame video image;

The second calculation module 304 is used to calculate the average value of the consistency feature map of the current frame video image and the previous frame video image, and obtain the consistency index sim of the current frame video image compared with the previous frame video image;

The detection module 305 obtains an image out-of-focus detection result based on the definition index dft and the consistency index sim.

For the specific limitations of the camera image out-of-focus detection device, refer to the above-mentioned definition of the camera image out-of-focus detection method, which will not be repeated here. Each module in the above camera image out-of-focus detection device can be fully or partially realized by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, and can also be stored in the memory of the computer device in the form of software, so that the processor can invoke and execute the corresponding operations of the above-mentioned modules.

In one embodiment, an electronic device is provided. The electronic device may be a computer, and its internal structure may be as shown in FIG. 4 . The electronic device includes a processor, memory and network interface connected by a system bus. Among them, the processor of the device is used to provide computing and control capabilities. The memory of the device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs and databases. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for camera image out-of-focus detection data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a camera image out-of-focus detection method is realized.

Those skilled in the art can understand that the structure shown in Figure 4 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation to the computer equipment on which the solution of the application is applied. The specific computer equipment More or fewer components than shown in the figures may be included, or certain components may be combined, or have a different arrangement of components.

In one embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned camera image out-of-focus detection method are implemented.

The implementation principle and technical effect of the computer-readable storage medium provided in this embodiment are similar to those of the above-mentioned method embodiments, and details are not repeated here.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented through computer programs to instruct related hardware, and the computer programs can be stored in a non-volatile computer-readable memory In the medium, when the computer program is executed, it may include the processes of the embodiments of the above-mentioned methods. Wherein, any references to memory, storage, database or other media used in the various embodiments provided in the present application may include non-volatile and/or volatile memory. Nonvolatile memory can include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in M forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Chain Road (SyMchliMk) DRAM (SLDRAM), memory bus (RaMbus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

The technical features of the above embodiments can be combined arbitrarily (as long as there is no contradiction in the combination of these technical features), for the sake of concise description, all possible combinations of the various technical features in the above embodiments are not described; these are not clear All the written examples should also be regarded as within the scope of the description in this specification.

The present application has been described more specifically and in detail through general descriptions and specific examples above. It should be understood that based on the technical concept of the present application, some conventional adjustments or further innovations can also be made to these specific embodiments; Also fall within the protection scope of the claims of the present application.

Claims (10)

1. A camera image out-of-focus detection method is characterized by comprising the following steps:

acquiring a video image acquired by a target camera, and calculating the horizontal and longitudinal gradient strength in the current frame video image to obtain a gradient strength map;

performing mean value calculation on the gradient intensity image to obtain a definition index dft of the current frame video image;

extracting a consistency characteristic diagram of the current frame video image and the previous frame video image;

calculating the average value of the consistency characteristic graphs of the current frame video image and the previous frame video image to obtain a consistency index sim of the current frame video image compared with the previous frame video image;

and obtaining an image out-of-focus detection result based on the definition index dft and the consistency index sim.

2. The method of claim 1, further comprising:

and saving the image data of the current frame video image for the out-of-focus detection of the next frame video image.

3. The method according to claim 1, wherein the deriving an out-of-focus image detection result based on the sharpness index dft and the consistency index sim comprises:

verifying the definition index dft and the consistency index sim according to a preset definition index threshold and a consistency index threshold;

and when the definition index dft is lower than the definition index threshold value and the consistency index sim is higher than the consistency index threshold value, determining that the target camera is in the process of image defocusing, and performing defocusing alarm through a preset communication channel.

4. The method of claim 1, wherein the calculating the horizontal and vertical gradient strengths in the video image of the current frame to obtain a gradient strength map comprises:

calculating the gray values of all pixels in the current frame video image, and converting the current frame video image into a gray image;

and calculating the approximate gradient of each pixel point by adopting a forward difference quotient to obtain a gradient intensity graph.

5. The method according to claim 1, wherein the averaging the gradient intensity map to obtain the sharpness index dft of the current frame video image comprises:

determining a sharpness index dft according to a first formula, wherein the first formula specifically comprises:

wherein,w represents the width of the image, h represents the height of the image,

representing the gradient intensity value in the x direction corresponding to a certain pixel point of the current image,

and k represents an index value of a pixel point in the image.

6. The method of claim 1, wherein extracting the consistent feature map of the current frame video image and the previous frame video image comprises:

determining the consistency characteristic value of a pixel point based on the gray value of the pixel point in the current frame video image and the gray value of the pixel point corresponding to the previous frame video image;

and traversing all pixel points in the video image to obtain a consistency characteristic diagram.

7. The method of claim 1, wherein averaging the consistency feature maps of the current frame video image and the previous frame video image to obtain a consistency index sim of the current frame video image compared to the previous frame video image comprises:

determining a consistency index sim according to a second formula, wherein the second formula specifically comprises:

wherein w represents the width of the image, h represents the height of the image, and simP represents the consistency characteristic value of the current frame video image at the position of the pixel point (x, y).

8. A camera image out-of-focus detection apparatus, the apparatus comprising:

the gradient calculation module is used for acquiring a video image acquired by the target camera, and calculating the transverse and longitudinal gradient strength in the current frame video image to obtain a gradient strength map;

the first calculation module is used for calculating the mean value of the gradient intensity image to obtain the definition index dft of the current frame video image;

the extraction module is used for extracting the consistency characteristic graph of the current frame video image and the previous frame video image;

the second calculation module is used for carrying out average value calculation on the consistency characteristic images of the current frame video image and the previous frame video image to obtain a consistency index sim of the current frame video image compared with the previous frame video image;

and the detection module is used for obtaining an image out-of-focus detection result based on the definition index dft and the consistency index sim.

9. An electronic device, comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, implements the camera image out-of-focus detection method according to any one of claims 1 to 7.

10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the camera image out-of-focus detection method according to any one of claims 1 to 7.

Images