Image processing device, image processing method

Abstract

To provide a technology that corrects the reduction in contrast of captured images caused by atmospheric particulate matter, while suppressing a decrease in the effectiveness of the correction and achieving this with lighter processing. [Solution] As a correction process to compensate for the reduction in contrast of captured images due to particulate matter in the atmosphere, it is determined, based on the parameters of the imaging device that captured the image, whether to perform a first correction process that performs different contrast correction for each local area of ​​the captured image, or a second correction process that performs contrast correction by tone curve correction. Depending on the result of this determination, either the first correction process or the second correction process is executed.

Description

[Technical Field]

[0001] This invention relates to a technique for correcting the reduction in contrast of captured images caused by particulate matter in the atmosphere. [Background technology]

[0002] In the fields of surveillance cameras and in-vehicle cameras, the reduced visibility of captured images due to the presence of fog and other elements between the camera and the subject is a problem. This is because light is scattered by fine particulate matter in the atmosphere as it passes through it, resulting in a decrease in the contrast of the captured image. Since the degree of scattering changes depending on the distance to the subject, in scenes where distances to subjects are mixed, the degree of contrast reduction will differ from one local area to another. One method to correct this decrease in contrast is to assume that black levels are raised due to the effects of fog, estimate the atmospheric transmittance distribution from the minimum pixel value of the color channel in the region (hereinafter referred to as the dark channel), and remove the effects of the fog based on an atmospheric model (hereinafter referred to as the DCP method). This makes it possible to correct the different contrast reductions in each local area.

[0003] However, fog removal using dark channels results in halos near distance boundaries, leading to reduced visibility. Therefore, the method disclosed in Patent Document 1 compensates for insufficient correction by first correcting using the DCP method at an intensity that does not produce halos, and then performing tone curve correction. [Prior art documents] [Patent Documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2020-195127 [Overview of the Initiative] [Problems that the invention aims to solve]

[0005] The method disclosed in Patent Document 1 only removes fog to the extent that no halo occurs. Therefore, the effect of contrast correction is reduced compared to when fog removal is applied to the maximum extent. In addition, since it is necessary to operate both DCP method correction and tone curve correction separately, the processing becomes heavy. The present invention provides a technology to correct the reduction in contrast of captured images caused by atmospheric particulate matter with lighter processing while suppressing the reduction in the correction effect. [Means for solving the problem]

[0006] One aspect of the present invention is characterized by comprising: a determination means for determining, based on the parameters of the imaging device that captured the image, whether to perform a first correction process that performs different contrast correction for each local region of the captured image, or a second correction process that performs contrast correction by tone curve correction, as a correction process to correct the reduction in contrast of the captured image due to particulate matter in the atmosphere; and a processing means for performing either the first correction process or the second correction process according to the result of the determination by the determination means. [Effects of the Invention]

[0007] According to the present invention, it is possible to provide a technology for correcting the reduction in contrast of captured images caused by airborne particles with lighter processing while suppressing a reduction in the correction effect. [Brief explanation of the drawing]

[0008] [Figure 1] A diagram showing an example of the system configuration. [Figure 2] A block diagram showing an example of the hardware configuration of the image processing device 100. [Figure 3] A block diagram showing an example of the functional configuration of the image processing unit 207. [Figure 4] A flowchart of the processing performed by the image processing device 100. [Figure 5] A diagram showing an example of the table configuration for determining contrast correction processing. [Figure 6]A diagram for explaining the contrast of each of a captured image of a scene with fog and a captured image of a scene without fog. [Figure 7] A diagram showing a configuration example of a tone curve correction table. [Figure 8] A block diagram showing a functional configuration example of the image processing unit 207. [Figure 9] A flowchart of the processing performed by the image processing apparatus 100. [Figure 10] A diagram showing a configuration example of the GUI. [Figure 11] A block diagram showing a functional configuration example of the image processing unit 207. [Figure 12] A flowchart of the processing performed by the image processing apparatus 100. [Figure 13] A diagram showing a configuration example of the GUI. [Figure 14] A diagram showing a configuration example of the GUI. [Mode for Carrying Out the Invention]

[0009] Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. Note that the following embodiments do not limit the invention according to the claims. Although a plurality of features are described in the embodiments, not all of these plurality of features are essential for the invention, and the plurality of features may be arbitrarily combined. Further, in the accompanying drawings, the same or similar configurations are denoted by the same reference numerals, and redundant descriptions are omitted.

[0010] [First Embodiment] The image processing apparatus according to the present embodiment determines which of tone curve correction and DCP method correction is to be executed as correction processing (contrast correction processing) for correcting a decrease in contrast of a captured image of a scene with fog, according to the focal length at the time of capturing the captured image and the distance to the focus position. Then, the image processing apparatus executes one of the tone curve correction and the DCP method correction determined as the contrast correction processing to be executed for the captured image, for the captured image.

[0011] First, a configuration example of the system according to this embodiment will be described with reference to FIG. 1. As shown in FIG. 1, the system according to this embodiment includes a camera 101, which is an example of a photographing device, an image processing device 100 that performs contrast correction processing on a photographed image captured by the camera 101 to generate an output image, and a display device 104 capable of displaying the output image.

[0012] The camera 101 and the image processing device 100 are connected via a control cable 102 such as a USB (Universal Serial Bus). Thereby, for example, the image processing device 100 can control the photographing by the camera 101 and acquire parameters such as photographing conditions and lens information from the camera 101.

[0013] Also, the camera 101 and the image processing device 100 are connected via a video transmission cable 103 such as an Ethernet cable, an HDMI (registered trademark), or an SDI (Serial Digital Interface) cable. Thereby, for example, the image processing device 100 can acquire the photographed image captured by the camera 101.

[0014] Also, the image processing device 100 and the display device 104 are connected via the above video transmission cable 103. Thereby, for example, the image processing device 100 can output the output image generated by the following processing to the display device 104 and display the output image on the display device 104.

[0015] Next, a hardware configuration example of the image processing device 100 will be described with reference to the block diagram of FIG. 2. As the image processing device 100, for example, a computer device such as a PC, a smartphone, or a tablet device can be applied.

[0016] The CPU 201 executes various processes using computer programs and data stored in the RAM 202. Thereby, the CPU 201 controls the operation of the entire image processing device 100 and executes or controls various processes described as the processes performed by the image processing device 100.

[0017] RAM 202 has areas for storing computer programs and data loaded from ROM 203 and storage device 204, and areas for storing data received from the outside via communication I / F 205. Furthermore, RAM 202 has work areas used by the CPU 201, image input unit 206, image processing unit 207, control unit 208, image output unit 210, etc., when they perform various processes. In this way, RAM 202 can provide various areas as appropriate.

[0018] ROM203 stores configuration data for the image processing device 100, computer programs and data related to the startup of the image processing device 100, computer programs and data related to the basic operation of the image processing device 100, and so on.

[0019] The storage device 204 is a non-volatile memory such as a hard disk drive or SSD. The storage device 204 stores the OS, computer programs and data for the CPU 201 to execute or control various processes described as being performed by the image processing device 100, etc. The storage device 204 may also be a memory device that can be attached to or removed from the image processing device 100, such as a USB memory stick or SD card.

[0020] The communication I / F205 is an interface such as HDMI®, SDI, or USB, and in this embodiment, it functions as an interface for data communication via the control cable 102 and the video transmission cable 103.

[0021] The operation of the image input unit 206, image processing unit 207, control unit 208, and image output unit 210 will be described later. In this embodiment, the case in which the image input unit 206, image processing unit 207, control unit 208, and image output unit 210 are all implemented in hardware will be described, but one or more of these functional units may be implemented in software (computer program). In the latter case, the CPU 201 executes such a computer program to realize the function of the corresponding functional unit.

[0022] The operation unit 209 is a user interface such as a keyboard, mouse, or touch panel, which allows the user to input various instructions to the image processing device 100 through operation.

[0023] The CPU 201, RAM 202, ROM 203, storage device 204, communication interface 205, image input unit 206, image processing unit 207, control unit 208, operation unit 209, and image output unit 210 are all connected to the system bus 212.

[0024] Next, the processing performed by the image processing device 100 to correct and output the contrast reduction of the captured image (contrast reduction of the captured image due to airborne particles) in the image captured by the camera 101 will be explained according to the flowchart in Figure 4. In addition, an example of the functional configuration of the image processing unit 207 is shown in the block diagram in Figure 3.

[0025] In step S401, the image processing unit 207 obtains the focal length and subject distance (distance to the focus position) from the camera 101 via the communication interface 205 and control cable 102 as lens information of the camera 101 when it captures an image.

[0026] In step S402, the image input unit 206 acquires the image captured by the camera 101 as input image I from the camera 101 via the communication I / F 205 and the control cable 102. Hereinafter, I(x,y,c) represents the pixel value (luminance value) of color channel c at coordinate position (x,y) in the input image I. In this embodiment, as an example, the input image is assumed to be an RGB image, so in this case, c = R,G,B.

[0027] Furthermore, the lens information acquired in step S401 is the lens information of camera 101 at the time of shooting the captured image acquired in step S402. However, the execution order of steps S401 and S402 is not limited to the order described above; they may also be executed in the order of S402, then S401, or these steps may be executed in parallel.

[0028] In step S403, the determination unit 301 in the image processing unit 207 determines, based on the lens information acquired in step S401, which contrast correction process to perform on the captured image acquired in step S402: a DCP method correction process that performs different contrast correction for each local area of ​​the captured image, or a tone curve correction process that performs contrast correction using tone curve correction.

[0029] Generally, when photographing a foggy scene, the degree of contrast reduction varies depending on the distance to the subject. However, if the distance to each subject is roughly the same, the degree of contrast reduction due to the fog remains constant in the captured image. In other words, if the distribution of subject distances in the captured image is not constant, DCP correction processing is applied to the image. However, if the distribution of subject distances in the captured image is constant, a uniform contrast correction process such as tone curve correction is sufficient for the image.

[0030] Therefore, in this embodiment, the determination unit 301 refers to the table in Figure 5 to identify a contrast correction process corresponding to the combination of focal length and subject distance acquired as lens information in step S401, and determines that the identified contrast correction process will be executed on the captured image acquired in step S402.

[0031] When the focal length is short, the angle of view tends to be wide and the distribution of distances to the subject tends to be wide. Similarly, when the distance to the subject is close, the distribution of distances to the subject also tends to be wide. Therefore, the table in Figure 5 is configured so that, depending on the combination of focal length and subject distance, DCP method correction processing is used when the lens conditions tend to result in a wide distribution of distances to the subject, and tone curve correction processing is used otherwise.

[0032] The method for determining the contrast correction process based on the focal length and subject distance is not limited to the method described above. For example, the determination unit 301 uses a function (which is created in advance) that represents the relationship between the focal length and subject distance and a value representing the distribution of distances to the subject, to calculate a value representing the distribution of distances to the subject that corresponds to the focal length and subject distance. If the calculated value is greater than or equal to a threshold, the determination unit 301 determines that the lens conditions tend to have a wide distribution of distances to the subject and decides to perform the DCP method correction process on the captured image as the contrast correction process. On the other hand, if the calculated value is less than a threshold, the determination unit 301 determines that the lens conditions tend to have a narrow distribution of distances to the subject and decides to perform the tone curve correction process on the captured image as the contrast correction process.

[0033] If, in step S403, it is determined that tone curve correction processing should be performed on the captured image acquired in step S402, the process proceeds to step S404. On the other hand, if, in step S403, it is determined that DCP method correction processing should be performed on the captured image acquired in step S402, the process proceeds to step S405.

[0034] In step S404, the correction unit 303 in the image processing unit 207 performs tone curve correction processing on the input image I acquired in step S402 to generate an output image O. Hereinafter, O(x,y,c) represents the pixel value (luminance value) of color channel c at coordinate position (x,y) in the output image O.

[0035] Meanwhile, in step S405, the correction unit 302 in the image processing unit 207 performs DCP correction processing on the input image I acquired in step S402 to generate the output image O.

[0036] In step S406, the image output unit 210 outputs the output image O generated in step S404 or step S405 to the display device 104 via the communication interface 205 and the video transmission cable 103.

[0037] Note that the output destination of the output image O by the image output unit 210 is not limited to the display device 104. For example, the image output unit 210 may transmit the output image O to an external device via a network such as LAM or the Internet, or it may save the output image O to the storage device 204.

[0038] Then, in step S407, the control unit 208 determines whether the termination conditions for the process, according to the flowchart in Figure 4, have been met. The termination conditions are not limited to specific conditions. For example, the control unit 208 determines that the termination conditions have been met if it detects that the user has entered a termination instruction by operating the operation unit 209.

[0039] If, as a result of this assessment, it is determined that the termination condition has been met, the process according to the flowchart in Figure 4 will terminate. On the other hand, if it is determined that the termination condition has not been met, the process will proceed to step S401.

[0040] Next, an example of the processing performed by the correction unit 303 in step S404 described above will be explained. As shown in Figure 6, generally, the contrast of an image taken of a scene with fog is lower than the contrast of an image taken of a scene without fog. Therefore, the distribution of brightness values ​​in the brightness histogram, which is a histogram of the brightness values ​​of pixels in an image taken of a scene with fog, is concentrated in a range of brightness values, and the variance of brightness values ​​in the brightness histogram is small. On the other hand, the variance of brightness values ​​in the brightness histogram of an image taken of a scene without fog is large.

[0041] Therefore, if the variance of luminance values ​​in the luminance histogram is small, the contrast reduction due to fog can be corrected by performing tone curve correction on the captured image so that the variance of luminance values ​​in the luminance histogram becomes larger. The correction unit 303 generates a luminance histogram of the input image and the variance of luminance values ​​in the generated luminance histogram σ 2 This is calculated according to the following equation (1).

[0042]

number

[0043] Here, Y i represents the value of the i-th luminance bin, N represents the total number of bins, and f i σ represents the frequency value corresponding to the i-th luminance value bin, μ represents the average value of the luminance values, and n represents the total number of pixels. Note that the variance of the luminance histogram is σ. 2 The method for calculating this is not limited to the method described above.

[0044] Then, the correction unit 303 calculates the variance σ 2 When the variance σ is large (for example, variance σ) 2 If the value is above the threshold, the input image is likely to be an image of a scene where no fog is present, so no contrast correction processing is performed on the input image. On the other hand, the correction unit 303 calculates the variance σ 2As the value of decreases, tone curve correction processing is performed on the input image using tone curve correction tables with a large correction effect, such as those shown in Figure 7(a) and Figure 7(b).

[0045] Next, an example of the processing performed by the correction unit 302 in step S405 described above will be explained. First, the correction unit 302 converts the input image to a luminance linear image to generate a linear image I', and then calculates ambient light using the generated linear image I'. Ambient light is the light component that is scattered by fog from light from the sun or sky. Here, the method described in Non-Patent Literature 1 is used to calculate the ambient light. Specifically, the correction unit 302 extracts a region from the dark channel image in which the pixel value is in the top 0.1%, and calculates ambient light A from the average luminance value of the linear image I' for the extracted region. Then, the correction unit 302 generates a dark channel image D using the following equation (2).

[0046]

number

[0047] Here, Ω(h,v) is a rectangular local region for calculating the dark channel, and h and v represent the horizontal and vertical ranges of the local region, respectively. In this embodiment, as an example, the correction unit 302 calculates the minimum values ​​of R, G, and B for a 3x3 pixel region centered on the pixel of interest (i.e., h=3, v=3), and replaces the R, G, and B luminance values ​​of the pixel of interest with the minimum values ​​of R, G, and B, respectively. Then, the correction unit 302 converts the dark channel image D into a transmittance distribution T according to the following equation (3).

[0048]

number

[0049] Here, ω is a parameter for controlling the excessive increase in the transmittance of a distant subject between 0 and 1.0. The larger the value, the greater the correction effect can be set. Here, in the transmittance distribution T converted by Equation (3), the shape of the rectangle at the time of dark channel calculation remains. Therefore, it is necessary to reduce this rectangular shape. The correction unit 302 calculates a reduced transmittance distribution T’ by applying a Laplacian filter to the transmittance distribution T as in Non-Patent Document 1. Then, the correction unit 302 generates a haze-removed image J by performing an operation according to the following Equation (4) using the linear image I’, the ambient light A, and the transmittance distribution T’.

[0050] [Equation]

[0051] Here, t min is a coefficient for preventing division by zero. In this embodiment, as an example, t min = 0. How to Use the Invention

[0052] Thus, in this embodiment, as a result of the determination process according to the focal length at the time of shooting and the distance to the focus position, in a condition where the distance to the subject is likely to be constant, the contrast correction process (haze removal process) by the tone curve correction process is executed. Thereby, it is possible to switch the contrast correction process without performing scene analysis such as subject distance estimation.

[0053] [Second Embodiment] In each of the following embodiments including this embodiment, the differences from the first embodiment will be described, and unless otherwise particularly mentioned below, it is assumed to be the same as the first embodiment. In this embodiment, whether to execute the tone curve correction process or the DCP method correction process as the contrast correction process for the captured image is determined according to "whether the operation mode of the camera 101 is set to the mode of tracking the subject (tracking mode)".

[0054] The process performed by the image processing device 100 to correct and output the contrast reduction of the captured image (contrast reduction of the captured image due to airborne particles) captured by the camera 101 will be explained according to the flowchart in Figure 9. Furthermore, an example of the functional configuration of the image processing unit 207 is shown in the block diagram in Figure 8.

[0055] In step S902, the determination unit 801 in the image processing unit 207 determines whether the operation mode parameter of the camera 101 is set to tracking mode. There are various methods for making this determination. One example of this determination method is described below.

[0056] For example, the CPU 201 displays a GUI on the display device 104, as illustrated in Figure 10(a). The display of the GUI is controlled by the CPU 201. Button 1001 is used to select whether to enable or disable tracking mode. In Figure 10(a), button 1001 indicates that tracking mode is disabled (off state).

[0057] When the user operates the control unit 209 and presses button 1001 in the GUI of Figure 10(a), the display color of button 1001 changes as shown in Figure 10(b), and the CPU 201 sets the operating mode of camera 101 to tracking mode. In Figure 10(b), button 1001 indicates that tracking mode is set (on state). Camera 101, with tracking mode set, operates to track the subject.

[0058] When the user operates the control unit 209 and presses button 1001 in the GUI of Figure 10(b), the display color of button 1001 changes as shown in Figure 10(a), and the CPU 201 sets the operating mode of the camera 101 from tracking mode to another mode (for example, normal operating mode). The camera 101, now set to another mode, performs operations according to that other mode.

[0059] Therefore, if button 1001 is ON, the determination unit 801 determines that the operating mode of camera 101 is set to tracking mode, and proceeds to step S404. On the other hand, if button 1001 is OFF, the determination unit 801 determines that the operating mode of camera 101 is not tracking mode, and proceeds to step S405.

[0060] In step S407 of this embodiment, the control unit 208 determines whether the termination conditions for the process according to the flowchart in Figure 4 have been met. If it is determined that the termination conditions have been met, the process according to the flowchart in Figure 9 is terminated. On the other hand, if it is determined that the termination conditions have not been met, the process proceeds to step S402.

[0061] Here, subject tracking refers to the state in which the camera follows the subject being monitored. Generally, the subject being tracked is often at an equidistant distance, so if tracking mode is set, fog removal using tone curve correction processing is sufficient.

[0062] Thus, according to this embodiment, when tracking a subject to be monitored, the distance to the subject is determined to be uniform, and tone curve correction processing is applied to the contrast correction processing of the captured image. This makes it possible to switch processing without performing scene estimation such as distance estimation.

[0063] [Third Embodiment] In this embodiment, a detection process is performed on the output image obtained by applying DCP method correction processing to the input image to detect subjects to be monitored, such as people or ships. If a subject is detected in the output image by this detection process, a tone curve correction process is performed only on the image region of the detected subject.

[0064] The process performed by the image processing device 100 to correct and output the contrast reduction of the captured image (contrast reduction of the captured image due to particulate matter in the atmosphere) captured by the camera 101 will be explained according to the flowchart in Figure 12. An example of the functional configuration of the image processing unit 207 is shown in the block diagram in Figure 11.

[0065] In step S1203, the object detection unit 1101 in the image processing unit 207 determines whether or not object detection has been instructed for the output image O generated in step S405. The method of such determination is not limited to a specific method. An example of the method of determination in step S1203 is described below.

[0066] Under the control of the CPU 201, the display device 104 displays the GUI exemplified in Figure 13(a). The GUI in Figure 13(a) displays the output image O1308 generated in step S405. In the GUI of Figure 13(a), when the user operates the operation unit 209 to indicate list 1301, the CPU 201 displays a list of names of candidate objects to be detected, as shown in Figure 13(a). When the user operates the operation unit 209 to select one of the displayed names and then indicates button 1302, the CPU 201 sets the object with the selected name as the object to be detected.

[0067] In this case, if the object to be detected is set via the GUI in Figure 13(a), the object detection unit 1101 determines that "object detection on the output image O generated in step S405 has been instructed."

[0068] On the other hand, if the object to be detected is not set via the GUI in Figure 13(a), the object detection unit 1101 determines that "object detection for the output image O generated in step S405 has not been instructed."

[0069] If, as a result of this judgment, it is determined that "object detection has been instructed for the output image O generated in step S405", the process proceeds to step S1204. On the other hand, if, as a result of this judgment, it is determined that "object detection has not been instructed for the output image O generated in step S405", the process proceeds to step S1206.

[0070] In step S1204, the object detection unit 1101 performs subject detection processing to detect the subject designated as the subject to be detected from the output image O generated in step S405. Various methods can be applied to detect a subject from an image; for example, subject detection using Deep Learning such as YOLO can be applied.

[0071] In step S1205, the correction unit 303 in the image processing unit 207 generates an output image O' in which tone curve correction processing is performed only on the image region of the subject detected in step S1204, using the output image O generated in step S405.

[0072] Figure 14(a) shows the GUI before processing in step S1205. Figure 14(b) shows the GUI after processing in step S1205. As shown in Figure 14(a), a halo remains around the detected subject in the output image O1401 displayed in the GUI before processing in step S1205. If tone curve correction processing is applied only to the image area of ​​the detected subject, as shown in the output image O'1402 in Figure 14(b), fog removal is not performed outside the image area of ​​the detected subject, but fog removal is performed in the image area of ​​the detected subject without the occurrence of a halo.

[0073] In step S1206, the image output unit 210 outputs the output image O generated in step S405 or the output image O' generated in step S1205 to the display device 104 via the communication interface 205 and the video transmission cable 103.

[0074] In step S407 of this embodiment, the control unit 208 determines whether the termination conditions for the process according to the flowchart in Figure 12 have been met. If it is determined that the termination conditions have been met, the process according to the flowchart in Figure 12 is terminated. On the other hand, if it is determined that the termination conditions have not been met, the process proceeds to step S405.

[0075] Thus, according to this embodiment, the detected subject area is treated as having a constant subject distance, and tone curve correction processing is applied. This makes it possible to improve the visibility of the detected subject without causing halos.

[0076] [Fourth Embodiment] In the above embodiment, a case was described in which the camera 101 and the image processing device 100 are separate devices. However, the camera 101 may be configured to realize the above-mentioned functions of the image processing device 100 by incorporating the image processing device 100 into the camera 101.

[0077] Furthermore, although the above embodiment describes a case in which the image processing device 100 acquires lens information from the camera 101, the method of acquiring lens information is not limited to a specific method. For example, the image processing device 100 may use a model that has been trained to estimate lens information from captured images to estimate lens information from captured images, thereby estimating lens information from captured images acquired from the camera 101.

[0078] Furthermore, in the second embodiment, the DCP method correction process is applied first, and then the system switches to tone curve correction when tracking occurs. However, it is also acceptable to apply tone curve correction beforehand when tracking occurs, and then switch to the DCP method when tracking is released.

[0079] The numerical values, processing timing, processing order, processing entity, data (information) structure / acquisition method / destination / source / storage location, etc., used in the above embodiment are given as examples for the purpose of providing a concrete explanation, and are not intended to limit the scope to such examples.

[0080] Furthermore, some or all of the embodiments described above may be used in appropriate combinations. Alternatively, some or all of the embodiments described above may be used selectively.

[0081] (Other embodiments) The present invention can also be realized by supplying a program that implements one or more of the functions of the above-described embodiments to a system or device via a network or storage medium, and by having one or more processors in the computer of that system or device read and execute the program. It can also be realized by a circuit (e.g., an ASIC) that implements one or more functions.

[0082] The inventions described herein include the following image processing apparatus, image processing method, and computer program. (Item 1) A determination means determines, based on the parameters of the imaging device used to capture the image, which of the following correction processes—a first correction process that performs different contrast corrections for each local area of ​​the captured image, or a second correction process that performs contrast correction using tone curve correction—to compensate for the reduction in contrast of the captured image due to particulate matter in the atmosphere, Processing means to perform either the first correction process or the second correction process according to the result of the determination by the determination means. An image processing apparatus characterized by comprising: (Item 2) The image processing apparatus according to item 1, characterized in that the determination means determines whether to perform the first correction process or the second correction process based on the focal length of the captured image at the time of shooting and the distance to the focus position of the captured image at the time of shooting. (Item 3) The image processing apparatus according to item 1, characterized in that the determination means determines whether to perform the first correction process or the second correction process based on whether the operating mode of the imaging device is set to a mode for tracking a subject. (Item 4) The image processing apparatus according to any one of items 1 to 3, characterized in that the first correction process is a DCP method correction process. (Item 5) moreover, An image processing apparatus according to any one of items 1 to 4, characterized by comprising an acquisition means for acquiring a captured image taken by a shooting device. (Item 6) moreover, An image processing apparatus according to any one of items 1 to 5, characterized by comprising a means for taking photographs. (Item 7) A first processing means performs different contrast corrections for each local region of the captured image as a correction process to compensate for the reduction in contrast of the captured image due to particulate matter in the atmosphere, If a subject is detected in the captured image that has undergone contrast correction processing by the first processing means, a second processing means performs contrast correction on the image area of ​​the subject by tone curve correction. An image processing apparatus characterized by comprising: (Item 8) An image processing method performed by an image processing device, The determination means of the image processing apparatus determines, based on the parameters of the imaging device that captured the image, whether to perform a first correction process that performs different contrast correction for each local region of the captured image, or a second correction process that performs contrast correction by tone curve correction, as a correction process to correct the reduction in contrast of the captured image due to particulate matter in the atmosphere, The processing means of the image processing apparatus performs a processing step in which it executes either the first correction process or the second correction process according to the result of the determination in the determination step. An image processing method characterized by comprising: (Item 9) An image processing method performed by an image processing device, The first processing means of the image processing apparatus includes a first processing step of performing different contrast corrections for each local region of the captured image as a correction process to correct the reduction in contrast of the captured image due to particulate matter in the air, If the second processing means of the image processing apparatus detects a subject from the captured image that has undergone contrast correction processing in the first processing step, it performs a second processing step of performing contrast correction on the image region of the subject by tone curve correction. An image processing method characterized by comprising: (Item 10) A computer program that causes a computer to function as one of the means of an image processing device described in any one of items 1 through 5.

[0083] The invention is not limited to the embodiments described above, and various modifications and variations are possible without departing from the spirit and scope of the invention. Accordingly, claims are attached to disclose the scope of the invention. [Explanation of Symbols]

[0084] 201: CPU 202: RAM 203: ROM 204: Storage device 205: Communication interface 206: Image input unit 207: Image processing unit 208: Control unit 209: Operation unit 210: Image output unit 212: System bus

Claims

1. A determination means determines, based on the parameters of the imaging device used to capture the image, whether to perform a first correction process that performs different contrast corrections for each local area of ​​the captured image, or a second correction process that performs contrast correction using tone curve correction, as a correction process to compensate for the reduction in contrast of the captured image due to particulate matter in the atmosphere. Processing means to perform either the first correction process or the second correction process according to the result of the determination by the determination means. An image processing apparatus characterized by comprising:

2. The image processing apparatus according to claim 1, characterized in that the determination means determines whether to perform the first correction process or the second correction process based on the focal length of the captured image at the time of shooting and the distance to the focus position of the captured image at the time of shooting.

3. The image processing apparatus according to claim 1, characterized in that the determination means determines whether to perform the first correction process or the second correction process based on whether the operating mode of the shooting device is set to a mode for tracking a subject.

4. The image processing apparatus according to claim 1, characterized in that the first correction process is a correction process of the DCP method.

5. moreover, The image processing apparatus according to claim 1, further comprising acquisition means for acquiring a captured image taken by a shooting device.

6. moreover, The image processing apparatus according to claim 1, characterized by comprising a means for taking photographs.

7. A first processing means performs different contrast corrections for each local region of the captured image as a correction process to compensate for the reduction in contrast of the captured image due to particulate matter in the atmosphere, If a subject is detected in the captured image that has undergone contrast correction processing by the first processing means, a second processing means performs contrast correction on the image region of the subject by tone curve correction. An image processing apparatus characterized by comprising:

8. An image processing method performed by an image processing device, The determination means of the image processing apparatus determines, based on the parameters of the imaging device that captured the image, whether to perform a first correction process that performs different contrast corrections for each local region of the captured image, or a second correction process that performs contrast correction by tone curve correction, as a correction process to compensate for the reduction in contrast of the captured image due to particulate matter in the atmosphere, The processing means of the image processing apparatus performs a processing step in which it executes either the first correction process or the second correction process according to the result of the determination in the determination step. An image processing method characterized by comprising:

9. An image processing method performed by an image processing device, The first processing means of the image processing apparatus includes a first processing step of performing different contrast corrections for each local region of the captured image as a correction process to correct the reduction in contrast of the captured image due to particulate matter in the air, If the second processing means of the image processing apparatus detects a subject from the captured image that has undergone contrast correction processing in the first processing step, it performs a second processing step of performing contrast correction on the image region of the subject by tone curve correction. An image processing method characterized by comprising:

10. A computer program for causing a computer to function as one of the means of an image processing apparatus according to any one of claims 1 to 5.

Images