Haze scattering environment degraded image restoration method, system, equipment and medium

Abstract

The invention provides a haze scattering environment degraded image restoration method, system and device and a medium, and belongs to the technical field of degraded image restoration. The method comprises the following steps: acquiring an original haze scattering environment degradation image; obtaining an intensity value, a global atmospheric light value and an atmospheric transmissivity of the original haze scattering environment degradation image by using the obtained original haze scattering environment degradation image; and restoring the original haze scattering environment degraded image by using the original haze scattering environment degraded image intensity value, the global atmospheric light value and the atmospheric transmissivity to obtain a restored haze scattering environment degraded image. The problem that in the prior art, when the point spread function measurement is inaccurate, the restoration effect on the degraded image in the haze scattering environment is poor is effectively solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of degraded image restoration, and in particular relates to a method, system, device and medium for restoring a degraded image in a haze scattering environment. Background Art

[0002] Atmospheric scattering environments such as clouds, smoke, fog and haze often lead to traffic accidents, blurred security monitoring and shortened visibility, which greatly disturb and damage people's lives. For example, satellite remote sensing images are blurred under cloud and fog scattering, highway visibility is short under foggy haze in winter, and rescue is difficult under thick smoke from fires. The above phenomena prevent researchers from understanding or exploring the scenes behind the scattering environment, and what is presented to them is often a degraded image that has been severely scattered.

[0003] In order to learn as much scene information as possible from degraded images, it is necessary not only to collect more scattering scenes, but also to explore the mechanism of degraded image generation in scattering environments and then restore clear scene information. However, it is difficult to collect degraded images under different scattering medium concentrations in natural environments.

[0004] Moreover, traditional scattering environment simulation often involves filling a confined space with scattering media such as smoke and fog to simulate a haze scattering environment. However, this method is difficult to effectively control the concentration of the filled medium and is prone to cause non-uniform distribution of the medium, affecting the exploration of the mechanism of degraded image generation.

[0005] At present, when restoring images degraded in haze scattering environments, the existing technology measures the point spread function of the imaging system and then performs deconvolution to solve it. However, this method has high labor costs, and when the point spread function is not measured accurately, the effect of restoring images degraded in haze scattering environments is not good. Summary of the invention

[0006] The object of the present invention is to provide a method, system, device and medium for restoring an image degraded in a haze scattering environment, so as to solve the problem in the prior art that when the point spread function is measured inaccurately, the restoration effect of the image degraded in the haze scattering environment is poor.

[0007] In order to achieve the above object, the present invention adopts the following technical solution:

[0008] In a first aspect, the present invention provides a method for restoring an image degraded in a haze scattering environment, comprising the following steps:

[0009] Get the original haze scattering environment degraded image;

[0010] Using the obtained original haze scattering environment degraded image, the original haze scattering environment degraded image intensity value, global atmospheric light value and atmospheric transmittance are obtained;

[0011] The original haze scattering environment degraded image is restored by using the original haze scattering environment degraded image intensity value, global atmospheric light value and atmospheric transmittance to obtain a restored haze scattering environment degraded image.

[0012] A further improvement of the present invention is that, in the step of obtaining the original haze scattering environment degraded image, the original haze scattering environment degraded image under different haze concentrations is obtained specifically by using a haze simulation device and an image acquisition system.

[0013] A further improvement of the present invention is that, in the step of restoring the original haze scattering environment degraded image by using the original haze scattering environment degraded image intensity value, the global atmospheric light value and the atmospheric transmittance to obtain the restored haze scattering environment degraded image, the calculation formula for restoring the original haze scattering environment degraded image is:

[0014]

[0015] Wherein, J(x) is the restored haze scattering environment degraded image, I(x) is the original haze scattering environment degraded image intensity value, t0 is the lower limit value set to prevent the restored haze scattering environment degraded image from being distorted due to the small transmittance at infinity, t(x) is the atmospheric transmittance, A is the global atmospheric light value, and max(·) represents the maximum value operation.

[0016] A further improvement of the present invention is that the calculation formula of the global atmospheric light value A is:

[0017]

[0018] in, It is the average intensity value of all pixel intensity values ​​in the convergence area obtained by quadtree decomposition of the original haze scattering environment degraded image.

[0019] A further improvement of the present invention is that the calculation formula of the atmospheric transmittance t(x) is:

[0020] t(x)=αt1(x)+(1-α)t2(x)

[0021] Among them, α is the brightness adjustment factor, t1(x) is the fine block optimized transmittance, and t2(x) is the atmospheric transmittance estimated by the dark channel method;

[0022] The calculation formula of atmospheric transmittance t2(x) estimated by dark channel method is:

[0023]

[0024] Where w is the fog retention degree in the haze scattering environment; A cis the atmospheric light value of the RGB channel of the original haze scattering environment degraded image, I c is the intensity value of the RGB color channel of the original haze scattering environment degraded image, min(·) represents the minimum operation, and y is the pixel position of the original haze scattering environment degraded image.

[0025] A further improvement of the present invention is that the specific steps of obtaining the fine block optimization transmittance t1(x) are as follows:

[0026] All sub-block transmittances are concatenated to obtain a rough block-optimized transmittance t1′(x);

[0027] The coarse block-optimized transmittance t1′(x) is filtered to obtain a fine block-optimized transmittance t1(x).

[0028] A further improvement of the present invention is that the calculation formula for the transmittance of all sub-blocks is:

[0029]

[0030] Among them, t i ' _j (x) is the transmittance of the i-th row and j-th column sub-block in the original haze scattering environment degraded image, i is the row sub-block index, i∈[1,m], m is the number of row sub-blocks after the original haze scattering environment degraded image is segmented, j is the column sub-block index, j∈[1,n], n is the number of column sub-blocks after the original haze scattering environment degraded image is segmented, is the maximum value of all pixel intensities in the dark channel of the original haze scattering environment degraded image, x is the position coordinate of the pixel in the i-th row and j-th column sub-block, is the minimum intensity value of all pixels in the dark channel of the original haze scattering environment degraded image, I dark (x) is the dark channel value of the original haze scattering environment degraded image, U is the unit matrix, which is used to convert the real-valued atmospheric light value into a matrix form, o represents the Hadamard product, and A is the global atmospheric light value;

[0031] Dark channel value I of the original haze scattering environment degraded image dark The calculation formula for (x) is:

[0032]

[0033] Among them, I c is the color channel intensity value of the original haze scattering environment degraded image RGB, Ω(x) is the local area centered on x, c is the r / g / b channel, y is an element or subset in the position coordinate x, and min(·) represents the minimum value operation.

[0034] In a second aspect, the present invention provides a haze scattering environment degraded image restoration system, comprising a data acquisition module, a parameter acquisition module and a restored haze scattering environment degraded image acquisition module;

[0035] The data acquisition module acquires the original haze scattering environment degraded image;

[0036] The parameter acquisition module is used to obtain the original haze scattering environment degraded image intensity value, global atmospheric light value and atmospheric transmittance by using the obtained original haze scattering environment degraded image;

[0037] The restored haze scattering environment degraded image acquisition module is used to restore the original haze scattering environment degraded image by using the original haze scattering environment degraded image intensity value, global atmospheric light value and atmospheric transmittance to obtain the restored haze scattering environment degraded image.

[0038] In a third aspect, the present invention provides an electronic device including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned method for restoring an image degraded in a haze scattering environment when executing the computer program.

[0039] In a fourth aspect, the present invention provides a storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the above-mentioned method for restoring an image degraded in a haze scattering environment.

[0040] Compared with the prior art, the present invention has the following beneficial effects:

[0041] The present invention belongs to an improved invention. Compared with the existing haze scattering environment degraded image restoration method, the haze scattering environment degraded image restoration method proposed by the present invention utilizes the original haze scattering environment degraded image intensity value, global atmospheric light value and atmospheric transmittance to restore the original haze scattering environment degraded image to obtain the restored haze scattering environment degraded image. It can be seen that when restoring the original haze scattering environment degraded image, the present invention performs restoration based on some mathematically related parameters (the original haze scattering environment degraded image intensity value, global atmospheric light value and atmospheric transmittance), and does not need to measure the imaging system point spread function or perform a deconvolution solution operation, thereby effectively solving the problem in the prior art that when the point spread function measurement is inaccurate, the haze scattering environment degraded image restoration effect is poor.

[0042] Furthermore, the present invention also discloses the step of obtaining the original haze scattering environment degraded image, specifically obtaining the original haze scattering environment degraded image under different haze concentrations through the haze simulation device and the image acquisition system. It can be seen that the present invention can obtain the original haze scattering environment degraded image under different haze concentrations through the haze simulation device and the image acquisition system, without waiting until there is a haze environment to collect images, which lays a good foundation for exploring the image degradation process and degraded image acquisition in the haze scattering environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 This is a flow chart of the method for restoring degraded images in a haze scattering environment of the present invention;

[0044] Figure 2 It is a schematic diagram of the haze scattering environment degradation image restoration system of the present invention;

[0045] Figure 3 It is a schematic diagram of the original haze scattering environment degradation image under different haze concentrations of the present invention;

[0046] Figure 4 It is a schematic diagram of the haze simulation device and image acquisition system of the present invention;

[0047] Figure 5 This is a schematic diagram of the uniform gas distribution system inside the smoke box of the haze simulation device of the present invention;

[0048] Figure 6 This is a flow chart of simulating haze scattering environment and degraded image acquisition by the haze simulation device of the present invention;

[0049] Figure 7 It is a schematic diagram of the principle of block transmittance estimation of the present invention;

[0050] Figure 8 It is a schematic diagram of the principle of simulating the distance from the binocular vision camera to the target of the present invention;

[0051] Fig. 9 This is a comparison diagram of the effects of the present invention before and after restoration of a degraded image in a haze scattering environment under different haze concentrations;

[0052] Fig.10 It is a structural schematic diagram of the electronic device of the present invention;

[0053] In the figure: 1. Haze simulation device; 11. Smoke box; 12. Haze concentration detection channel; 13. Ventilation channel; 14. Haze injection channel; 15. Particle concentration detector; 16. Smoke machine; 17. Uniform air distribution system inside the smoke box; 171. Air inlet nozzle; 172. Air inlet channel; 173. Jet nozzle; 18. Target; 19. Temperature detector; 110. Heating spoiler device; 111. Pressure detector; 112. Light source; 2. Image acquisition system; 21. Camera; 22. Data cable; 23. Computer. DETAILED DESCRIPTION

[0054] In order to further understand the content of the present invention, the present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the embodiments are only for explaining the present invention and are not intended to limit it.

[0055] The method for restoring a degraded image in a haze scattering environment proposed by the present invention uses the original haze scattering environment degraded image intensity value, the global atmospheric light value and the atmospheric transmittance to restore the original haze scattering environment degraded image to obtain a restored haze scattering environment degraded image. Compared with the prior art, the present invention effectively solves the problem in the prior art that the restoration effect of the haze scattering environment degraded image is poor when the point spread function measurement is inaccurate.

[0056] Embodiment 1:

[0057] The flowchart of the method for restoring degraded images in a haze scattering environment of the present invention is as follows: Figure 1 As shown, the method for restoring an image degraded in a haze scattering environment of the present invention comprises the following steps:

[0058] S1. Obtain the original haze scattering environment degraded image.

[0059] S2. Using the obtained original haze scattering environment degraded image, the original haze scattering environment degraded image intensity value, global atmospheric light value and atmospheric transmittance are obtained.

[0060] S3. Using the original haze scattering environment degraded image intensity value, global atmospheric light value and atmospheric transmittance, the original haze scattering environment degraded image is restored to obtain a restored haze scattering environment degraded image.

[0061] Embodiment 2:

[0062] The schematic diagram of the haze scattering environment degradation image restoration system of the present invention is as follows Figure 2 As shown, the array induction logging instrument structural parameter determination system of the present invention includes a data acquisition module, a parameter acquisition module and a restored haze scattering environment degradation image acquisition module.

[0063] The data acquisition module obtains the original haze scattering environment degraded image.

[0064] The parameter acquisition module is used to obtain the original haze scattering environment degraded image intensity value, global atmospheric light value and atmospheric transmittance by using the obtained original haze scattering environment degraded image.

[0065] The restored haze scattering environment degraded image acquisition module is used to restore the original haze scattering environment degraded image by using the original haze scattering environment degraded image intensity value, global atmospheric light value and atmospheric transmittance to obtain the restored haze scattering environment degraded image.

[0066] Embodiment 3:

[0067] S1. Obtain the original haze scattering environment degraded image.

[0068] First, obtain the original haze scattering environment degraded image.

[0069] In this step, the original haze scattering environment degradation images under different haze concentrations are obtained by the haze simulation device and the image acquisition system. The schematic diagram of the original haze scattering environment degradation images under different haze concentrations obtained by the haze simulation device and the image acquisition system is shown in FIG. Figure 3 As shown. The haze simulation device is used to simulate haze scattering environments under different concentrations. The image acquisition system is used to acquire degraded images scattered by haze (original degraded images of haze scattering environments).

[0070] The schematic diagram of the haze simulation device and image acquisition system of the present invention is shown in FIG. Figure 4 As shown, the haze simulation device 1 includes a smoke box 11, a haze concentration detection channel 12, a ventilation channel 13, a haze injection channel 14, a particle concentration detector 15, a smoke machine 16, a uniform air distribution system 17 inside the smoke box, a target 18, a temperature detector 19, a heating spoiler device 110, a pressure detector 111 and an illumination light source 112.

[0071] The smoke box 11 in the haze simulation device 1 is constructed by gluing acrylic plates or applying a film to the poles. The haze generated by the water molecules in the smoke machine 16 being heated at high temperature is injected into the smoke box 11 after passing through the haze injection channel 14 and the uniform gas distribution system 17 inside the smoke box. The concentration of the injected haze is detected by the particle concentration detector 15, and feedback is given to the customer to decide whether to continue injecting haze. If it is a smoke box built with a film applied to the poles, it is necessary to cooperate with the pressure detector 111 to monitor the internal pressure of the smoke box to prevent the smoke box 11 from deforming due to excessive haze concentration. Turn on the heating spoiler 110 to maintain the internal temperature of the smoke box 11 within a certain range, so as to accelerate the uniform distribution of the haze inside the smoke box 11. At the same time, the temperature detector 19 is used to monitor the internal temperature of the smoke box 11 to ensure that the temperature inside the smoke box is appropriate. Turn on the illumination light source 112 to illuminate the target 18 to provide light source support for passive target imaging.

[0072] The image acquisition system 2 includes a camera 21, a data line 22 and a computer 23. The camera 21 in the image acquisition system 2 includes two cameras, which form a binocular vision camera, which is used to estimate the atmospheric scattering coefficient during the system calibration after ranging, and provide support for scene depth estimation. The data line 22 is used for communication and data transmission between the computer and the camera. The computer 23 is used to receive the degraded image collected by the camera.

[0073] The schematic diagram of the uniform gas distribution system inside the smoke box of the haze simulation device of the present invention is as follows Figure 5 As shown, the uniform air distribution system 17 inside the smoke box in the haze simulation device 1 includes an air inlet nozzle 171, an air inlet channel 172 and an air nozzle 173. The air inlet nozzle 171 is connected to the haze injection channel 14, and is used to receive the haze generated by the smoke machine 16 outside the smoke box. The air inlet channel 172 is distributed in an "S" shape inside the smoke box, and is used to quickly introduce haze into the smoke box. The air nozzle 173 is connected to the air inlet channel 172, and the haze in the air inlet channel 172 is uniformly sprayed into the smoke box 11.

[0074] In this step, the process of using a haze simulation device to simulate haze scattering environments at different concentrations and an image acquisition system to acquire degraded images is described in detail as follows:

[0075] The ventilation channel (also called ventilation valve) 13 is closed, and the fog machine 16 is turned on. The fog (also called fog scattering medium) is transported to the air inlet channel 172 through the air inlet nozzle 171 in the uniform air distribution system 17 inside the smoke box through the fog injection channel 14, and the fog in the air inlet channel 172 is filled into the smoke box 11 through the air nozzle 173. The heating spoiler device 110 is turned on to promote the fog inside the smoke box 11 to quickly reach a uniform distribution state. At the same time, the internal temperature of the smoke box 11 can be dynamically monitored by the temperature detector 19, and the temperature display of the temperature detector 19 is used to determine whether to turn off the heating spoiler device 110. If it is necessary to collect degraded images under non-uniform distribution of fog, the heating spoiler device 110 can be turned off. The fog particle concentration (also called scattering medium concentration) in the current smoke box 11 is determined according to the monitoring results of the particle concentration detector (also called particle concentration meter) 15, so as to determine whether to turn off the fog machine 16. The illumination light source 112 (also called illumination device) is turned on to illuminate the target 18. At this point, the haze scattering environment under different haze concentrations can be simulated, and the image acquisition system (specifically, a binocular vision camera, also called a binocular camera) can be used to collect degraded images. The process of simulating the haze scattering environment and degraded image acquisition by the haze simulation device is as follows: Figure 6 shown.

[0076] S2. Using the obtained original haze scattering environment degraded image, the original haze scattering environment degraded image intensity value, global atmospheric light value and atmospheric transmittance are obtained.

[0077] S3. Using the original haze scattering environment degraded image intensity value, global atmospheric light value and atmospheric transmittance, the original haze scattering environment degraded image is restored to obtain a restored haze scattering environment degraded image.

[0078] The original haze scattering environment degraded image is restored using the original haze scattering environment degraded image intensity value I(x), the global atmospheric light value A and the atmospheric transmittance t(x) to obtain the restored haze scattering environment degraded image.

[0079] Specifically, the calculation formula for restoring the original haze scattering environment degraded image is:

[0080]

[0081] Wherein, J(x) is the restored haze scattering environment degraded image, I(x) is the original haze scattering environment degraded image intensity value, t0 is the lower limit value set to prevent the restored haze scattering environment degraded image from being distorted due to the small transmittance at infinity, t(x) is the atmospheric transmittance, A is the global atmospheric light value, and max(·) represents the maximum value operation.

[0082] The calculation formula of the global atmospheric light value A is:

[0083]

[0084] in, It is the average intensity value of all pixel intensity values ​​in the convergence area obtained by quadtree decomposition of the original haze scattering environment degraded image.

[0085] The calculation formula of atmospheric transmittance t(x) is:

[0086] t(x)=αt1(x)+(1-α)t2(x)

[0087] Among them, α is the brightness adjustment factor, α∈[0,1], t1(x) is the fine block optimized transmittance, and t2(x) is the atmospheric transmittance estimated by the dark channel method.

[0088] The calculation formula of atmospheric transmittance t2(x) estimated by dark channel method is:

[0089]

[0090] Where w is the fog retention degree in the haze scattering environment; A c is the atmospheric light value of the RGB channel of the original haze scattering environment degraded image, I cis the intensity value of the RGB color channel of the original haze scattering environment degraded image, min(·) represents the minimum operation, and y is the pixel position of the original haze scattering environment degraded image.

[0091] The specific steps for fine block optimization of transmittance t1(x) are as follows:

[0092] A. Splice all sub-block transmittances to obtain a rough block-optimized transmittance t1′(x);

[0093] B. Filter the coarse block-optimized transmittance t1′(x) to obtain a fine block-optimized transmittance t1(x).

[0094] The calculation formula for the transmittance of all sub-blocks is:

[0095]

[0096] Among them, t i ' _j (x) is the transmittance of the i-th row and j-th column sub-block in the original haze scattering environment degraded image, i is the row sub-block index, i∈[1,m], m is the number of row sub-blocks after the original haze scattering environment degraded image is segmented, j is the column sub-block index, j∈[1,n], n is the number of column sub-blocks after the original haze scattering environment degraded image is segmented, is the maximum value of all pixel intensities in the dark channel of the original haze scattering environment degraded image, x is the position coordinate of the pixel in the i-th row and j-th column sub-block, is the minimum intensity value of all pixels in the dark channel of the original haze scattering environment degraded image, I dark (x) is the dark channel value of the original haze scattering environment degraded image, U is the unit matrix, which is used to convert the real-valued atmospheric light value into a matrix form, o represents the Hadamard product, A is the global atmospheric light value, and the principle of block transmittance estimation is as follows: Figure 7 shown.

[0097] Dark channel value I of the original haze scattering environment degraded image dark The calculation formula for (x) is:

[0098]

[0099] Among them, I c is the color channel intensity value of the original haze scattering environment degraded image RGB, Ω(x) is the local area centered on x, c is the r / g / b channel, y is an element or subset in the position coordinate x, and min(·) represents the minimum value operation.

[0100] After the atmospheric scattering coefficient β is obtained by the haze scattering environment degraded image restoration method proposed in the present invention, the atmospheric scattering coefficient β is basically the same under the same scattering scene or weather. At this time, if the target in the scene moves, it is only necessary to use any camera 21 in the image acquisition system 2 to capture the degraded image to obtain the depth value d1 of the target scene. The calculation formula of the depth value d1 of the target scene is:

[0101]

[0102] Among them, d1 is the depth value of the target scene, t(x) is the atmospheric transmittance, and β is the atmospheric scattering coefficient.

[0103] The calculation formula of atmospheric scattering coefficient β is:

[0104]

[0105] Among them, t(x) is the atmospheric transmittance, and d2 is the distance from the binocular vision camera to the target.

[0106] The calculation formula of the distance d2 from the binocular vision camera to the target is:

[0107]

[0108] Among them, d2 is the distance from the binocular vision camera to the target (also called the depth of the target scene), f is the focal length of the camera, L is the distance between the two cameras at the same height, and y1 and y2 are the distances from the edge of the same object in the pictures taken by the left and right cameras. During the test, L can be measured directly with a ruler, and f can be obtained by checking the camera focal length parameters. The principle diagram of the simulation of the distance from the binocular vision camera to the target is shown in the figure. Figure 8 shown.

[0109] The comparison of the effects of the present invention before and after restoration of haze scattering environment degraded images under different haze concentrations is shown in the figure below. Fig. 9 As shown, Fig. 9 The row of images marked (a) represents the original haze scattering environment degraded images under different haze concentrations, and the row of images marked (c) represents the results of restoring the original haze scattering environment degraded images using the haze scattering environment degraded image restoration method proposed in the present invention (haze scattering environment degraded images restored under different haze concentrations). The row of images marked (b) represents the detail magnification comparison results of the original haze scattering environment degraded images under different haze concentrations and the restored haze scattering environment degraded images under different haze concentrations.

[0110] Embodiment 4:

[0111] See also Fig.10As shown, the present invention also provides an electronic device 100 for a method for restoring an image degraded in a haze scattering environment; the electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on the at least one processor 102, and at least one communication bus 104.

[0112] The memory 101 can be used to store the computer program 103. The processor 102 implements the steps of the haze scattering environment degradation image restoration method described in Example 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101. The memory 101 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data (such as audio data) created according to the use of the electronic device 100, etc. In addition, the memory 101 can include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices.

[0113] The at least one processor 102 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 may be a microprocessor or any conventional processor, etc. The processor 102 is the control center of the electronic device 100, and uses various interfaces and lines to connect various parts of the entire electronic device 100.

[0114] The memory 101 in the electronic device 100 stores a plurality of instructions to implement a method for restoring an image degraded in a haze scattering environment, and the processor 102 may execute the plurality of instructions to implement:

[0115] Get the original haze scattering environment degraded image;

[0116] Using the obtained original haze scattering environment degraded image, the original haze scattering environment degraded image intensity value, global atmospheric light value and atmospheric transmittance are obtained;

[0117] The original haze scattering environment degraded image is restored by using the original haze scattering environment degraded image intensity value, global atmospheric light value and atmospheric transmittance to obtain a restored haze scattering environment degraded image.

[0118] Embodiment 5:

[0119] If the module / unit integrated in the electronic device 100 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory and read-only memory (ROM, Read-Only Memory).

[0120] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0121] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0122] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0123] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0124] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for restoring degraded images in a haze scattering environment, characterized in that: The following steps are involved: Get the original haze scattering environment degraded image; Using the obtained original haze scattering environment degraded image, the original haze scattering environment degraded image intensity value, global atmospheric light value and atmospheric transmittance are obtained; The original haze scattering environment degraded image is restored by using the original haze scattering environment degraded image intensity value, global atmospheric light value and atmospheric transmittance to obtain a restored haze scattering environment degraded image.

2. The method for restoring degraded images in a haze scattering environment according to claim 1, characterized in that: In the step of obtaining the original haze scattering environment degraded image, the original haze scattering environment degraded image under different haze concentrations is obtained specifically by using a haze simulation device and an image acquisition system.

3. The method for restoring degraded images in a haze scattering environment according to claim 1, characterized in that: In the step of restoring the original haze scattering environment degraded image by using the original haze scattering environment degraded image intensity value, the global atmospheric light value and the atmospheric transmittance to obtain the restored haze scattering environment degraded image, the calculation formula for restoring the original haze scattering environment degraded image is: Wherein, J(x) is the restored haze scattering environment degraded image, I(x) is the original haze scattering environment degraded image intensity value, t0 is the lower limit value set to prevent the restored haze scattering environment degraded image from being distorted due to the small transmittance at infinity, t(x) is the atmospheric transmittance, A is the global atmospheric light value, and max(·) represents the maximum value operation.

4. The method for restoring an image degraded in a haze scattering environment according to claim 3, characterized in that: The calculation formula of the global atmospheric light value A is: in, It is the average intensity value of all pixel intensity values ​​in the convergence area obtained by quadtree decomposition of the original haze scattering environment degraded image.

5. The method for restoring degraded images in a haze scattering environment according to claim 3, characterized in that: The calculation formula of the atmospheric transmittance t(x) is: t(x)=αt1(x)+(1-α)t2(x) Among them, α is the brightness adjustment factor, t1(x) is the fine block optimized transmittance, and t2(x) is the atmospheric transmittance estimated by the dark channel method; The calculation formula of atmospheric transmittance t2(x) estimated by dark channel method is: Where w is the fog retention degree in the haze scattering environment; A c is the atmospheric light value of the RGB channel of the original haze scattering environment degraded image, I c is the intensity value of the RGB color channel of the original haze scattering environment degraded image, min(·) represents the minimum operation, and y is the pixel position of the original haze scattering environment degraded image.

6. The method for restoring an image degraded in a haze scattering environment according to claim 5, characterized in that: The specific steps of obtaining the fine block optimization transmittance t1(x) are as follows: All sub-block transmittances are concatenated to obtain a rough block-optimized transmittance t1′(x); The coarse block-optimized transmittance t1′(x) is filtered to obtain a fine block-optimized transmittance t1(x).

7. The method for restoring degraded images in a haze scattering environment according to claim 6, characterized in that: The calculation formula for the transmittance of all sub-blocks is: Among them, t i ' _j (x) is the transmittance of the i-th row and j-th column sub-block in the original haze scattering environment degraded image, i is the row sub-block index, i∈[1,m], m is the number of row sub-blocks after the original haze scattering environment degraded image is segmented, j is the column sub-block index, j∈[1,n], n is the number of column sub-blocks after the original haze scattering environment degraded image is segmented, is the maximum value of all pixel intensities in the dark channel of the original haze scattering environment degraded image, x is the position coordinate of the pixel in the i-th row and j-th column sub-block, is the minimum intensity value of all pixels in the dark channel of the original haze scattering environment degraded image, I dark (x) is the dark channel value of the original haze scattering environment degraded image, U is the unit matrix, which is used to convert the real-valued atmospheric light value into a matrix form, o represents the Hadamard product, and A is the global atmospheric light value; Dark channel value I of the original haze scattering environment degraded image dark The calculation formula for (x) is: Among them, I c is the color channel intensity value of the original haze scattering environment degraded image RGB, Ω(x) is the local area centered on x, c is the r / g / b channel, y is an element or subset in the position coordinate x, and min(·) represents the minimum value operation.

8. A haze scattering environment degraded image restoration system, characterized in that: It includes a data acquisition module, a parameter acquisition module and a restored haze scattering environment degradation image acquisition module; The data acquisition module acquires the original haze scattering environment degraded image; The parameter acquisition module is used to obtain the original haze scattering environment degraded image intensity value, global atmospheric light value and atmospheric transmittance by using the obtained original haze scattering environment degraded image; The restored haze scattering environment degraded image acquisition module is used to restore the original haze scattering environment degraded image by using the original haze scattering environment degraded image intensity value, global atmospheric light value and atmospheric transmittance to obtain the restored haze scattering environment degraded image.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for restoring an image degraded in a haze scattering environment according to any one of claims 1 to 7 are implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for restoring an image degraded in a haze scattering environment according to any one of claims 1 to 7 are implemented.

Images