Image processing device, imaging system, image processing method, and program

Abstract

To improve image visibility while reducing human costs.SOLUTION: An image processing device has image processing means for performing high image quality processing that reduces image quality deterioration for a captured image acquired by imaging means and adjustment means for adjusting at least one parameter related to the imaging means and the high image quality processing means on the basis of the analysis result of the high image quality processed image.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present invention relates to an image processing technique for reducing image quality problems. [Background technology]

[0002] Generally, surveillance cameras perform dynamic range adjustment and brightness adjustment. In addition, when the illumination is low or foggy, high-quality processing such as noise reduction and fog removal is applied to the images captured by the camera as necessary. In recent years, by utilizing deep learning (DL), high-quality processing that exceeds conventional performance has been achieved.

[0003] However, in poor environments such as extremely low light such as starlight or dense fog where distant objects cannot be seen, applying high image quality processing using deep learning to images does not necessarily ensure good visibility of the desired part. In such cases, it has been common to manually change parameters such as the camera lens aperture and shutter speed or adjust image processing parameters to improve visibility. However, with manual adjustments, it is not easy to determine which parameter changes are most effective in improving visibility, and multiple parameters must be adjusted while visually checking whether image quality improves, which requires human labor.

[0004] Patent Document 1 discloses a technology for detecting a moving object within a monitored area and transmitting control information to a monitoring camera to change the brightness of an area including the object to a predetermined value, thereby clearly displaying the moving object. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2014-146979 A Summary of the Invention [Problem to be solved by the invention]

[0006] However, in the technique disclosed in Patent Document 1, while the brightness of a moving object in a captured image can be automatically adjusted and displayed, the moving object may become blurred, or image quality defects such as noise and artifacts may be emphasized. In such cases, it is necessary to manually adjust the parameters of the camera and image processing, and it is very time-consuming to visually check the results each time the parameters are adjusted. Also, such adjustment is not something that needs to be done only once after the camera is installed; it is required every time after operation, which is time-consuming. The present invention aims to improve the visibility of an image while suppressing human costs.

Means for Solving the Problem

[0007] An image processing apparatus according to the present invention includes image processing means for performing high-image-quality processing to reduce image quality defects on a captured image acquired by imaging means, and adjustment means for adjusting at least one parameter of a parameter related to the imaging means and a parameter related to the high-image-quality processing based on an analysis result of the captured image that has undergone the high-image-quality processing.

Effect of the Invention

[0008] According to the present invention, it is possible to improve the visibility of an image while suppressing human costs.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Mode for Carrying Out the Invention

[0010] Hereinafter, embodiments of the present invention will be described with reference to the drawings. The following embodiments do not limit the present invention, and not all combinations of the features described in this embodiment are essential for the solution means of the present invention. The configuration of the embodiment can be appropriately modified or changed according to the specifications of the applied device and various conditions (usage conditions, usage environment, etc.). Also, a configuration may be formed by appropriately combining a part of each of the following embodiments. In the following embodiments, the same configuration will be described with the same reference numerals.

[0011] 〔Embodiment 1〕 In Embodiment 1, high-quality processing according to imaging conditions and the scene of the captured image is performed, and when image quality defects are detected by analyzing the result or when there is room for improving visibility, correction parameters are calculated to update the parameters of the camera or edge device. A method will be described.

[0012] <System Configuration> FIG. 1(A) is a diagram showing a configuration example of an imaging system according to Embodiment 1. The imaging system shown in FIG. 1(A) is connected with a camera 10 responsible for imaging, an edge device 20 responsible for high-quality processing and analysis processing of the captured image, and a display device 30 responsible for screen display of the high-quality processed image and the like.

[0013] <Hardware Configuration of the System> FIG. 2 is a block diagram for explaining a hardware configuration example of the imaging system according to Embodiment 1. The camera 10 of the present embodiment is a camera that images a target area, and the captured image (RAW image) acquired by the camera 10 is sent to the edge device 20. The camera 10 is, for example, a surveillance camera that images a surveillance target area. The camera 10 includes an optical unit 201, an image sensor 202, a CPU 203, a RAM 204, a ROM 205, and a general-purpose interface (I / F) 206, and each component is interconnected by a system bus 207. Also, the camera 10 is connected to the edge device 20 via the general-purpose I / F 206.

[0014] The optical unit 201 is a lens barrel composed of a zoom lens, a focus lens, an anti-shake lens, a diaphragm, and a shutter, and condenses the light information of the subject. The image sensor 202 is a CMOS sensor or a SPAD (Single Photon Avalanche Diode) sensor, and includes a color filter having a predetermined arrangement such as a Bayer array and an image pickup device. The CMOS sensor converts the light beam condensed by the optical unit 201 into an analog electrical signal including the color information of the subject by receiving it with the image pickup device through the color filter. While the CMOS sensor measures the amount of light accumulated in the pixels over a certain period of time, the SPAD sensor is configured to count each individual particle of light (photon = photon) that enters the pixel. Then, an analog electrical signal is converted into a digital signal by an A / D converter (not shown) to generate RAW image data.

[0015] The CPU 203 uses the RAM 204 as a work memory, executes the program stored in the ROM 205, and comprehensively controls each component of the camera 10 via the system bus 207. The general-purpose I / F 206 is a serial bus interface such as USB, IEEE 1394, HDMI (registered trademark), SDI, etc.

[0016] The edge device 20 of the present embodiment acquires the RAW image data (Bayer array) output from the camera 10 as an input image to be subjected to high-image-quality processing. Then, the edge device 20 performs high-image-quality processing on the input image to be subjected to high-image-quality processing, and transmits the output image (the image subjected to high-image-quality processing) to the display device 30. Further, the edge device 20 performs analysis processing on the output image, calculates correction parameters related to the camera 10 or the edge device 20 as necessary based on the analysis result, and transmits them to update the high-image-quality processing. As a result, the output image output from the edge device 20 is also updated. In the present embodiment, two types of correction parameters, that is, the camera parameters transmitted to the camera 10 and the image processing parameters transmitted to the edge device 20, are handled. The camera parameters are mainly parameters for setting the imaging conditions of the camera, and the image processing parameters are parameters related to high-image-quality processing.

[0017] The edge device 20 includes a CPU 211, a RAM 212, a ROM 213, a mass storage device 214, and a general-purpose I / F 215, and each component is interconnected by a system bus 216. Further, the edge device 20 is also connected to the camera 10, the display device 30, the input device 90, and the external storage device 100 via the general-purpose I / F 215.

[0018] The CPU 211 uses the RAM 212 as a working memory, executes the programs stored in the ROM 213, and comprehensively controls each component of the edge device 20 via the system bus 216. The mass storage device 214 is, for example, an HDD (hard disk drive) or an SSD (solid state drive), and stores various data handled by the edge device 20. The CPU 211 writes data to the mass storage device 214 and reads data stored in the mass storage device 214 via the system bus 216. The general-purpose I / F 215 is, for example, a serial bus interface such as USB, IEEE 1394, HDMI, SDI, etc. The edge device 20 acquires data from an external storage device 100 (for example, various storage media such as a memory card, a CF card, an SD card, a USB memory, etc.) via the general-purpose I / F 215. Also, the edge device 20 receives user instructions from an input device 90 such as a mouse or a keyboard via the general-purpose I / F 215. Further, the edge device 20 outputs image data and the like processed by the CPU 211 to a display device 30 (for example, various image display devices such as a liquid crystal display) via the general-purpose I / F 215. Also, the edge device 20 acquires data of a captured image (RAW image) from the camera 10 via the general-purpose I / F 215.

[0019] <Functional Configuration of the System> Next, with reference to FIG. 3, the functional configuration of the imaging system in Embodiment 1 will be described. FIG. 3 is a block diagram for explaining a functional configuration example of the imaging system according to Embodiment 1. As shown in FIG. 3, the camera 10 has an imaging unit 301 and a parameter update unit 302. Also, the edge device 20 has a scene discrimination unit 311, an image processing unit 312, an analysis processing unit 313, a parameter calculation unit 314, and a parameter update unit 315. The camera 10 is an example of an imaging means, and the edge device 20 is an example of an image processing device. Each functional unit shown in FIG. 3 is realized, for example, by the CPU 203 or the CPU 211 executing a computer program for realizing each function. Note that all or part of the functional units shown in FIG. 3 may be implemented in hardware.

[0020] Note that the configuration shown in FIG. 3 can be appropriately modified or changed. For example, one functional unit may be divided into a plurality of functional units, or two or more functional units may be integrated into one functional unit. Further, the configuration shown in FIG. 3 may be realized by two or more devices. In this case, each device is connected via a circuit or a wired or wireless network, and performs data communication with each other to perform cooperative operations, thereby realizing each process according to the present embodiment.

[0021] Each functional unit of the camera 10 will be described. The imaging unit 301 images the target area and transmits the captured image SA and the imaging information SB to the edge device 20. The imaging information includes, for example, set values at the time of imaging such as an aperture value, a shutter speed, a gain (sensitivity), a focal length, and a white balance calculation mode. The parameter update unit 302 receives the camera parameter PA from the edge device 20 and updates the set value of the camera 10 based on the received camera parameter PA. The camera parameter includes set values of the camera such as an aperture value, a shutter speed, a gain (sensitivity), a focal length, and a white balance calculation mode.

[0022] Next, each functional unit of the edge device 20 will be described. The scene discrimination unit 311 receives the captured image SA and the imaging information SB from the camera 10, and discriminates a scene such as the overall location and situation from the object shown in the captured image SA based on the received imaging information SB. The scene discrimination unit 311 outputs the captured image SA and the imaging information SB and the result of the scene discrimination to the image processing unit 312. The scene discrimination unit 311 performs scene discrimination using, for example, a convolutional neural network (CNN) that has learned a huge number of labeled images and information at the time of imaging. This CNN takes the captured image SA and the imaging information SB as inputs and outputs which category among the learned scenes it is classified into.

[0023] The image processing unit 312 performs high-quality processing to reduce image quality degradation on the captured image SA based on the scene discrimination result output by the scene discrimination unit 311 and the imaging information SB. The result of the high-quality processing is sent to, for example, the display device 30 and displayed as an output image. The image processing unit 312 is an example of image processing means. The high-quality processing includes processes such as noise reduction processing, haze removal processing, super-resolution processing, and HDR (High Dynamic Range) processing, and one or more processes are selected. For example, when the gain is greater than a predetermined value, the image processing unit 312 performs noise reduction processing, and when the contrast of the entire image is less than a predetermined value, the image processing unit 312 performs haze removal processing. Also, for example, when the moving object is smaller than a predetermined size, the image processing unit 312 performs super-resolution processing, and when there is a saturated area in the image, the image processing unit 312 performs HDR processing. The selection of the high-quality processing performed by the image processing unit 312 is not limited to the above-described method, and the user may set in advance which processing to perform.

[0024] The analysis processing unit 313 analyzes the output image (the image that has been subjected to high-quality processing by the image processing unit 312) to determine whether image quality degradation has occurred or whether there is room for further improvement in visibility. The analysis processing unit 313 is an example of analysis processing means. The analysis processing performed by the analysis processing unit 313 varies depending on, for example, the imaging conditions, the type of the image sensor 202, the type of the high-quality processing, whether deep learning (DL) is used in the high-quality processing, and the scene of the captured image. Specifically, as shown in the list in FIG. 4, correction parameters are calculated based on the analysis processing to be applied according to these conditions and the method of calculating the correction parameters described later.

[0025] FIG. 4 is a diagram for explaining an example of an analysis process and a correction parameter calculation method. Taking the case of No. 1 as an example, when the image sensor 202 is a CMOS sensor and the high-image-quality process is noise reduction (NR) and DL is not used, the analysis process shows whether color shift occurs in the output image. And when it is determined that color shift has occurred in the output image, it shows that the white balance calculation mode of the camera 10 is changed to the spot mode, and a correction parameter is calculated so that the white balance calculation area matches the color shift occurrence area. Details of No. 2 to No. 6 including No. 1 will be described later.

[0026] Based on the result of the analysis process in the analysis processing unit 313, the parameter calculation unit 314 calculates correction values of the camera parameter PA and the image processing parameter PB so as to improve the visibility of the output image. The parameter calculation unit 314 sends the calculated camera parameter PA to the parameter update unit 302 of the camera 10, and sends the calculated image processing parameter PB to the parameter update unit 315 in the edge device 20. The image processing parameters include parameters for adjusting the intensity of high-image-quality processes such as the offset of the captured image, white balance, brightness, color, contrast, dynamic range, and blur. The parameter update unit 315 updates the parameters related to the high-image-quality process in the image processing unit 312 based on the image processing parameter PB calculated by the parameter calculation unit 314. The parameter calculation unit 314 and the parameter update unit 315 are examples of adjustment means. Also, the parameter calculation unit 314 is an example of calculation means, and the parameter update unit 315 is an example of update means.

[0027] <Overall system processing flow> Next, with reference to FIG. 5, various processes performed in the imaging system according to Embodiment 1 will be described. FIG. 5 is a flowchart showing an example of processing in the imaging system according to Embodiment 1. Hereinafter, the overall flow of processing will be described along the flowchart of FIG. 5, and after describing the overall flow of processing, details of the analysis process and the correction parameter calculation method will be described. In the following description, the symbol "S" means a processing step.

[0028] In S501, the imaging unit 301 of the camera 10 images the imaging target area to obtain an imaging image SA, and transmits the imaging image SA and imaging information SB including the setting values at the time of imaging in the camera 10 to the edge device 20. In S502, the scene discrimination unit 311 of the edge device 20 discriminates the scene of the imaging image SA acquired and transmitted by the camera 10 in S501. The scene discrimination unit 311 receives the imaging image SA and the imaging information SB transmitted from the camera 10, and discriminates the scene such as the overall location and situation from the objects shown in the imaging image SA based on the received imaging information SB.

[0029] In S503, the image processing unit 312 of the edge device 20 performs high-quality processing on the imaging image SA based on the result of the scene discrimination in S502 and the imaging information SB. Then, the image processing unit 312 outputs the image subjected to the high-quality processing as an output image. In S504, the analysis processing unit 313 of the edge device 20 analyzes the output image that is the result of the high-quality processing in S503.

[0030] In S505, the analysis processing unit 313 determines whether it is necessary to correct the camera parameters regarding the camera 10 and the image processing parameters regarding the high-quality processing based on the result of the analysis processing in S504. The analysis processing unit 313 determines whether there is an image quality defect in the output image or whether there is room for further improving the visibility based on the result of the analysis processing in S504. As a result, if it is determined that there is an image quality defect or there is room for further improving the visibility, the analysis processing unit 313 determines that it is necessary to correct the camera parameters and the image processing parameters. When the analysis processing unit 313 determines that it is necessary to correct the camera parameters and the image processing parameters (YES), the process proceeds to S506. When the analysis processing unit 313 determines that it is not necessary to correct the camera parameters and the image processing parameters (NO), the process shown in FIG. 5 ends.

[0031] In S506, the parameter calculation unit 314 of the edge device 20 calculates correction parameters (camera parameter PA and image processing parameter PB), and sends them to the parameter update unit 302 of the camera 10 and the parameter update unit 315 of the edge device 20. Based on the result of the analysis process in S504, the parameter calculation unit 314 calculates correction values of the camera parameter PA and the image processing parameter PB so as to suppress image quality degradation and improve the visibility of the output image.

[0032] In S507, the parameter update unit 302 of the camera 10 receives the camera parameter PA from the edge device 20, and updates the setting value of the camera 10 based on the received camera parameter PA. Also, the parameter update unit 315 of the edge device 20 updates the intensity of the high image quality processing based on the image processing parameter PB calculated by the parameter calculation unit 314.

[0033] Hereinafter, with reference to FIGS. 4 and 6, specific examples in cases No. 1 to 6 will be sequentially described for the processes of S504 to S506 in FIG. 5. As shown in No. 1 in FIG. 4, when the image sensor is a CMOS sensor and the high image quality processing is noise reduction (NR) and deep learning (DL) is not used, the analysis processing unit 313 determines whether color shift occurs in the image as the analysis process. If the analysis processing unit 313 determines that color shift occurs, the parameter calculation unit 314 calculates correction parameters so as to change the camera parameters. A processing example in this case will be described with reference to the flowchart of FIG. 6(A).

[0034] In FIG. 6(A), in S601, the analysis processing unit 313 detects a low-luminance and flat region in the output image and sets it as the region to be analyzed. For example, the night sky at the time of imaging in an ultra-low illuminance environment becomes the region to be analyzed. In S602, the analysis processing unit 313 generates histograms of the R, G, and B components of the region detected as the analysis target in S601.

[0035] In S603, the analysis processing unit 313 calculates the similarity degrees Sim_RB, Sim_RG, and Sim_BG of the histograms of R and B, R and G, and B and G, respectively, based on the histograms of the respective components generated in S602. For calculating the similarity degree of histograms, for example, the histogram is made into a vector and the vector similarity degree is used, but it is not limited to this, and other methods may be used as long as the similarity degree or correlation of the histogram can be calculated.

[0036] In S604, the analysis processing unit 313 compares the similarity degrees calculated in S603 with the threshold values th1 and th2, and determines whether all the conditions of Sim_RB≧th1, Sim_RG<th2, and Sim_BG<th2 are satisfied. That is, the analysis processing unit 313 determines whether the similarity degree Sim_RB of the histograms of R and B is equal to or greater than the threshold value th1, and both the similarity degree Sim_RG of the histograms of R and G and the similarity degree Sim_BG of the histograms of B and G are less than the threshold value th2. When the analysis processing unit 313 determines that all the conditions of Sim_RB≧th1, Sim_RG<th2, and Sim_BG<th2 are satisfied (YES), it is determined that color shift has occurred in the detected area to be analyzed, and the process proceeds to S605. When the analysis processing unit 313 determines that at least one of the conditions of Sim_RB≧th1, Sim_RG<th2, and Sim_BG<th2 is not satisfied (NO), it is determined that color shift has not occurred in the detected area to be analyzed, and the analysis process ends. In this way, in S604, the analysis processing unit 313 determines whether correction of the parameters is necessary based on the similarity degrees calculated in S603.

[0037] In S605, the parameter calculation unit 314 calculates a correction parameter (correction value of the camera parameter) that adjusts the white balance calculation area to match the detected area to be analyzed.

[0038] As shown by No2 in FIG. 4, when the image sensor is a SPAD sensor and the high image quality processing is NR and DL is not used, the analysis processing unit 313 determines whether crosstalk occurs in the image as the analysis processing. When the analysis processing unit 313 determines that crosstalk occurs, the parameter calculation unit 314 calculates a correction parameter to change the image processing parameter. A processing example in this case will be described with reference to the flowchart of FIG. 6(B).

[0039] In FIG. 6(B), in S611, the analysis processing unit 313 applies a filter (filter size is, for example, 7×7) with increased weights in the cross direction to the output image.

[0040] In S612, the analysis processing unit 313 compares the pixel value after filter application with the threshold value th3, and determines whether the pixel value after filter application is greater than or equal to the threshold value th3. When the analysis processing unit 313 determines that the pixel value after filter application is greater than or equal to the threshold value th3 (YES), it is determined that the pixel where crosstalk has occurred, and the process proceeds to S613. When the analysis processing unit 313 determines that the pixel value after filter application is not greater than or equal to the threshold value th3 (NO), the analysis processing ends. In this way, in S612, the analysis processing unit 313 determines whether correction of the parameter is necessary based on the pixel value after filter application.

[0041] In S613, the parameter calculation unit 314 calculates a correction parameter (correction value of the image processing parameter) that increases the value of the noise intensity map at the pixel position where crosstalk is detected and increases the intensity of the NR process as the pixel value after filter application is larger.

[0042] As shown by No3 in FIG. 4, when the image sensor is a SPAD sensor and the high-image-quality processing is NR and DL is not used, the analysis processing unit 313 determines whether there is a lot of noise in the dark part of the image as the analysis processing. When the analysis processing unit 313 determines that there is a lot of noise in the dark part, the parameter calculation unit 314 calculates a correction parameter to change the camera parameter. A processing example in this case will be described with reference to the flowchart of FIG. 6(C).

[0043] In FIG. 6(C), in S621, the analysis processing unit 313 calculates the noise variance of the low-luminance and flat part with respect to the output image. In S622, the analysis processing unit 313 calculates the deviation amount by comparing the noise table with the noise variance calculated in S621. This noise table is a table showing how much noise variance there is after NR according to the luminance for each sensitivity, which is prepared in advance.

[0044] In S623, the analysis processing unit 313 compares the deviation amount calculated in S622 with the threshold value th4, and determines whether the deviation amount is equal to or greater than the threshold value th4. When the analysis processing unit 313 determines that the deviation amount calculated in S622 is equal to or greater than the threshold value th4 (YES), it is determined that there is a lot of noise in the low-luminance part, and the process proceeds to S624. When the analysis processing unit 313 determines that the deviation amount calculated in S622 is not equal to or greater than the threshold value th4 (NO), the analysis processing ends. In this way, in S623, the analysis processing unit 313 determines whether parameter correction is necessary based on the deviation amount calculated in S622.

[0045] In S624, the parameter calculation unit 314 calculates a correction parameter (correction value of the camera parameter) to increase the shutter speed of the camera. In the SPAD sensor, the dark current noise becomes dominant as the sensitivity is higher and the luminance is lower, but it can be suppressed by increasing the shutter speed.

[0046] As shown by No4 in FIG. 4, when the image sensor is a SPAD sensor and the high-image-quality processing is NR and DL is not used, the analysis processing unit 313 determines whether there are many regions in the image where there is no signal (pixel value 0) as the analysis processing. When the analysis processing unit 313 determines that there are many regions occupied by pixel value 0, the parameter calculation unit 314 calculates a correction parameter so as to change the image processing parameter. A processing example in this case will be described in detail with reference to the flowchart of FIG. 6(D).

[0047] In FIG. 6(D), in S631, the analysis processing unit 313 counts the pixels with pixel value 0 in the output image and calculates the ratio of the pixels with pixel value 0 in the whole image.

[0048] In S632, the analysis processing unit 313 compares the ratio of the pixels with pixel value 0 calculated in S631 with the threshold th5 and determines whether the ratio of the pixels with pixel value 0 is greater than or equal to the threshold th5. When the analysis processing unit 313 determines that the ratio of the pixels with pixel value 0 calculated in S631 is greater than or equal to the threshold th5 (YES), the process proceeds to S633. When the analysis processing unit 313 determines that the ratio of the pixels with pixel value 0 calculated in S631 is not greater than or equal to the threshold th5 (NO), the analysis processing ends. In this way, in S632, the analysis processing unit 313 determines whether it is necessary to correct the parameter based on the ratio of the pixels with pixel value 0 calculated in S631.

[0049] In S633, the parameter calculation unit 314 calculates a correction parameter (correction value of the image processing parameter) to increase the number of frames used for the high-image-quality processing.

[0050] As shown by No5 in FIG. 4, when the high image quality processing is NR and DL is used, the analysis processing unit 313 determines whether streak-like artifacts where noise is connected to the image occur as an analysis process. These artifacts often appear in the result of performing NR processing on unlearned noise when utilizing a deep neural network. When the analysis processing unit 313 determines that an artifact has occurred, the parameter calculation unit 314 calculates a correction parameter to change the camera parameter. A processing example in this case will be described with reference to the flowchart of FIG. 6(E).

[0051] In FIG. 6(E), in S641, the analysis processing unit 313 calculates the noise variance of the flat part for the output image.

[0052] In S642, the analysis processing unit 313 compares the noise variance calculated in S641 with the threshold th6 and determines whether the noise variance is equal to or greater than the threshold th6. When the analysis processing unit 313 determines that the noise variance calculated in S641 is equal to or greater than the threshold th6 (YES), it determines that an artifact has occurred and the process proceeds to S643. When the analysis processing unit 313 determines that the noise variance calculated in S641 is not equal to or greater than the threshold th6 (NO), the analysis process ends. In this way, in S642, the analysis processing unit 313 determines whether parameter correction is necessary based on the noise variance calculated in S641.

[0053] In S643, the parameter calculation unit 314 calculates a correction parameter (correction value of the camera parameter) to reduce the sensitivity of the camera (for example, reduce it by 3 to 5 steps) for NR and then return to the original sensitivity.

[0054] As shown by No6 in FIG. 4, when the high-image-quality processing is NR and DL is used, the analysis processing unit 313 determines whether a checkerboard-like artifact occurs in the image as the analysis processing. This artifact often appears when using a deconvolution layer or when specific learning data is insufficient when utilizing a convolutional neural network. When the analysis processing unit 313 determines that an artifact has occurred, the parameter calculation unit 314 calculates a correction parameter to change the image processing parameter. A processing example in this case will be described with reference to the flowchart of FIG. 6(F).

[0055] In FIG. 6(F), at S651, the analysis processing unit 313 applies a filter (filter size is, for example, 7×7) in which two types of weights of large and small are alternately set in a checkerboard pattern to the output image.

[0056] At S652, the analysis processing unit 313 compares the pixel value after filter application with the threshold value th7 and determines whether the pixel value after filter application is equal to or greater than the threshold value th7. If the analysis processing unit 313 determines that the pixel value after filter application is equal to or greater than the threshold value th7 (YES), it is determined that the pixel is a pixel where a checkerboard-like artifact has occurred, and the process proceeds to S653. If the analysis processing unit 313 determines that the pixel value after filter application is not equal to or greater than the threshold value th7 (NO), the analysis processing ends. In this way, at S652, the analysis processing unit 313 determines whether correction of the parameter is necessary based on the pixel value after filter application.

[0057] At S653, the parameter calculation unit 314 calculates a correction parameter (correction value of the image processing parameter) that increases the value of the noise intensity map at the pixel position where the artifact is detected and increases the intensity of the NR processing as the pixel value after filter application is larger.

[0058] The above is the flow of the processing performed by the imaging system according to Embodiment 1. In Embodiment 1, a method for updating parameters of the camera 10 that performs imaging so as to improve visibility by analyzing the result of the high-image-quality processing and the edge device 20 that performs the high-image-quality processing was described. Cameras such as surveillance cameras are adjusted for various parameters so as not to cause image quality degradation and to maximize their performance. However, it is difficult to cover all imaging conditions with initial parameters, and image quality degradation is more likely to occur in adverse environments such as ultra-low illuminance and thick fog. Conventionally, when imaging is performed in such an environment and the visibility is low, the parameters are manually adjusted. On the other hand, by automatically adjusting the parameters as in Embodiment 1 described above, it is possible to improve the visibility of the captured image while suppressing the human cost.

[0059] In this embodiment, the explanation was given using a RAW image of a Bayer array as the captured image. However, other color filter arrays may be used, or a developed RGB image may also be used. Note that the timing for updating the camera parameters and the image processing parameters was described as the time when the high-image-quality processing is executed and the correction value is calculated by analyzing the result. However, image quality degradation may occur again after the correction. In such a case, a mechanism for detecting a certain change in brightness or color in the captured image or the output image may be provided, and the analysis process may be executed at the detected timing to adjust the camera parameters and the image processing parameters. Further, the analysis process may be executed at the time specified by the user or the like, or when a preset time has elapsed, to adjust the camera parameters and the image processing parameters.

[0060] [Embodiment 2] In Embodiment 1, an example was described in which, when image quality degradation occurs by analyzing the result of performing high-image-quality processing, the process of calculating correction parameters and updating the parameters of the camera and the edge device is automatically performed. In Embodiment 2, in order to achieve flexible correction, a method for favorably displaying a specific area pre-selected or set by the user from captured images will be described. Note that descriptions of the content common to Embodiment 1, such as the basic configuration of the imaging system, will be omitted, and the following will focus on the differences.

[0061] <System Configuration> FIG. 1(B) is a diagram showing a configuration example of the imaging system according to Embodiment 2. The imaging system shown in FIG. 1(B) includes a camera 10 responsible for imaging, an edge device 40 responsible for high-quality processing of the captured image, an edge device 50 responsible for analysis processing of the high-quality processing result, and a display device 30 responsible for screen display of the high-quality processed image and the like, which are connected.

[0062] The hardware configurations of the edge device 40 and the edge device 50 in Embodiment 2 are the same as those of the edge device 20 in Embodiment 1. However, the functional configurations of the edge device 40 and the edge device 50 in Embodiment 2 are different from those of the edge device 20 in Embodiment 1.

[0063] The edge device 40 of the present embodiment acquires the RAW image data (Bayer array) output from the camera 10 as an input image to be subjected to high-quality processing. Then, the edge device 40 performs high-quality processing on the input image to be subjected to high-quality processing, and transmits the output image (high-quality processed image) to the display device 30 and the edge device 50. Further, the edge device 50 of the present embodiment receives the output image from the edge device 40, performs analysis processing, calculates correction parameters related to the camera 10 or the edge device 20 as necessary based on the analysis result of the output image, transmits them, and updates the high-quality processing.

[0064] <Functional Configuration of the System> Referring to FIG. 7, the functional configuration of the imaging system in Embodiment 2 will be described. FIG. 7 is a block diagram for explaining an example of the functional configuration of the imaging system according to Embodiment 2. In FIG. 7, the same components as those shown in FIG. 3 are denoted by the same reference numerals, and redundant descriptions are omitted. The edge device 40 includes a scene discrimination unit 711 and an image processing unit 712. The edge device 50 includes a user instruction unit 721, an analysis processing unit 722, a parameter calculation unit 723, and a parameter update unit 724. Note that the camera 10 in Embodiment 2 is the same as the camera 10 in Embodiment 1. The camera 10 is an example of an imaging means, the edge device 40 is an example of a first processing device, and the edge device 50 is an example of a second processing device. Each functional unit shown in FIG. 7 is realized, for example, by the CPU of the camera 10, the CPUs of the edge devices 40 and 50 executing computer programs for realizing the respective functions. Note that all or part of the functional units shown in FIG. 7 may be implemented in hardware.

[0065] The edge device 40 will be described. Similar to the scene discrimination unit 311 in Embodiment 1, the scene discrimination unit 711 receives the captured image SA and the imaging information SB from the camera 10, and discriminates a scene such as the overall location and situation of the object shown in the captured image SA based on the received imaging information SB. The scene discrimination unit 711 outputs the captured image SA and the imaging information SB, and the result of the scene discrimination to the image processing unit 712.

[0066] Similar to the image processing unit 312 in Embodiment 1, the image processing unit 712 performs high-quality processing for reducing image quality degradation on the captured image SA based on the result of the scene discrimination output by the scene discrimination unit 711 and the imaging information SB. The result of the high-quality processing is sent to, for example, the display device 30 and displayed as an output image. The image processing unit 712 also transmits the output image (the image subjected to the high-quality processing) to the edge device 50.

[0067] Next, the edge device 50 will be described. The user instruction unit 721 receives user instructions performed by the user via a graphical user interface (GUI) as shown in FIG. 8 as an example. The user can select a correction mode for the output image, set a specific area for which visibility is to be improved, adjust the correction intensity such as brightness, contrast, sharpness, etc. via the GUI screen.

[0068] FIGS. 8(A) and 8(B) are diagrams showing an example of the GUI screen. On the GUI screen 800 shown in FIG. 8(A), a high-quality processed output image 801 and a priority mode selection window 802 during high-quality processing are displayed. Also, on the GUI screen 800, a detail button 803 for adjusting the correction intensity, a record button 804 for recording settings, and a determination button 805 for reflecting the settings are displayed. The priority modes selectable by the priority mode selection window 802 include, for example, a fully automatic mode that automatically performs high-quality processing in the same manner as the processing of Embodiment 1, an Av priority mode that prioritizes the aperture of the camera, a Tv priority mode that prioritizes the shutter speed, and the like.

[0069] Also, the user can set a specific area 806 in any size for the output image 801 displayed on the GUI screen 800 as shown in FIG. 8(B) as an example, and can change the correction intensity within the area. When changing the correction intensity, by pressing the detail button 803 shown in FIG. 8(A), for example, an intensity adjustment window 807 as shown in FIG. 8(B) is displayed, and the intensity of brightness, contrast, and sharpness can be adjusted with a slide bar. The adjustment of the correction intensity using the intensity adjustment window 807 is reflected by pressing the apply button 808, and by pressing the back button 809, the user returns to the GUI screen 800 shown in FIG. 8(A). Also, by pressing the record button 804 shown in FIG. 8(A), it is possible to record the correction mode and intensity adjustment settings adjusted by the user in the large-capacity recording device within the edge device 50, and this setting can be used from the next time onwards.

[0070] Similar to the analysis processing unit 313 in Embodiment 1, the analysis processing unit 722 analyzes the output image (the image subjected to the high image quality processing) to determine whether an image quality defect has occurred or whether there is room for further improving the visibility. However, the analysis processing unit 722 performs analysis processing on the specific area set by the user instruction unit 721.

[0071] Based on the intensity adjustment set by the user instruction unit 721 and the result of the analysis processing by the analysis processing unit 722, the parameter calculation unit 723 calculates correction values for the camera parameter PA and the image processing parameter PB so as to improve the visibility of the output image. Similar to the parameter calculation unit 314 in Embodiment 1, the parameter calculation unit 723 calculates correction values for the camera parameter PA and the image processing parameter PB based on the result of the analysis processing by the analysis processing unit 722. Then, based on the intensity adjustment set by the user instruction unit 721, the parameter calculation unit 723 multiplies the calculated image processing parameter by the value of the intensity adjustment set by the user to adjust the intensity of the correction parameter. The value of the intensity adjustment is based on 1. When it is less than 1, the correction intensity becomes smaller, and when it is greater than 1, the correction intensity becomes larger. The parameter calculation unit 723 sends the calculated camera parameter PA to the parameter update unit 302 of the camera 10, and sends the calculated image processing parameter PB to the parameter update unit 724 in the edge device 50.

[0072] Based on the image processing parameter PB calculated by the parameter calculation unit 723, the parameter update unit 724 updates the parameters related to the high image quality processing in the image processing unit 712 of the edge device 40. In the example shown in FIG. 7, the parameter update unit 724 is provided in the edge device 50. However, the parameter update unit 724 may be provided in the edge device 40 to update the parameters related to the high image quality processing.

[0073] <Processing flow of the entire system> Next, with reference to FIG. 9, various processes performed in the imaging system according to Embodiment 2 will be described. FIG. 9 is a flowchart showing an example of processing in the imaging system according to Embodiment 2.

[0074] In S901, the imaging unit 301 of the camera 10 images the imaging target area to obtain an imaging image SA, and transmits the imaging image SA and imaging information SB including the setting values at the time of imaging in the camera 10 to the edge device 40. In S902, the scene discrimination unit 711 of the edge device 40 discriminates the scene of the imaging image SA acquired and transmitted by the camera 10 in S901. The scene discrimination unit 711 receives the imaging image SA and the imaging information SB transmitted from the camera 10, and discriminates the scene such as the overall location and situation from the objects shown in the imaging image SA based on the received imaging information SB.

[0075] In S903, the image processing unit 712 of the edge device 40 performs high-image-quality processing on the imaging image SA based on the result of the scene discrimination in S902 and the imaging information SB. Then, the image processing unit 712 transmits the image subjected to the high-image-quality processing to the display device 30 and the edge device 50 as an output image. In S904, the user instruction unit 721 of the edge device 50 receives the specific area to be analyzed and the intensity adjustment related to the high-image-quality processing instructed by the user via the GUI screen 800.

[0076] In S905, the analysis processing unit 722 of the edge device 50 analyzes the output image that is the result of the high-image-quality processing in S903. In the analysis processing in this step S905, the analysis processing unit 722 performs analysis processing on the specific area within the output image specified by the user as the analysis target. In S906, the parameter calculation unit 723 of the edge device 50 calculates correction parameters (camera parameter PA and image processing parameter PB) based on the intensity adjustment instructed by the user and the result of the analysis processing in S905. Then, the parameter calculation unit 723 sends the calculated correction parameters to the parameter update unit 302 of the camera 10 and the parameter update unit 724 of the edge device 50.

[0077] In S907, the parameter update unit 302 of the camera 10 receives the camera parameter PA from the edge device 50, and updates the setting value of the camera 10 based on the received camera parameter PA. Also, the parameter update unit 724 of the edge device 50 controls the parameters of the image processing unit 712 of the edge device 40 based on the image processing parameter PB calculated by the parameter calculation unit 723, and updates the intensity of the high image quality processing. The above is the processing flow performed by the imaging system according to Embodiment 2.

[0078] In Embodiment 2, a method for optimally displaying a specific area selected or set by the user from the captured images has been described. As in Embodiment 2 described above, the visibility of the captured images can be improved more flexibly through the user's instructions. Also, as in Embodiment 2 described above, by performing the high image quality processing and the analysis processing on different edge devices, the processing load can be dispersed and the service life can be extended.

[0079] 〔Embodiment 3〕 In Embodiments 1 and 2, examples of performing the process of calculating correction parameters and updating the parameters of the camera and the edge device automatically or at the user's instruction when analyzing the result of high image quality processing of the captured images and finding that image quality defects have occurred have been described. In Embodiment 3, by combining a radar (such as millimeter wave / microwave, etc.), an object that cannot be detected by the camera is detected, and based on the position information of the target object, the operation control of the camera pan-tilt unit is performed so that it is displayed at an appropriate size at the center position of the captured image. Note that the description of the content common to Embodiments 1 and 2 in terms of the basic configuration of the imaging system and the like will be omitted, and the following will focus on the differences.

[0080] <System Configuration> FIG. 1(C) is a diagram showing a configuration example of the imaging system according to Embodiment 3. The imaging system shown in FIG. 1(C) has a pan-tilt unit 70 responsible for controlling the orientation and angle of view of the camera and a radar 80 responsible for object detection additionally connected to the imaging system of FIG. 1(B).

[0081] <Hardware Configuration of the System> FIG. 10 is a block diagram for explaining a hardware configuration example of the imaging system according to Embodiment 3. In FIG. 10, the same components as those shown in FIG. 2 are denoted by the same reference numerals, and redundant descriptions are omitted. The pan-tilt unit 70 has a general-purpose I / F 1001, a pan-tilt controller 1002, a pan motor 1003, a tilt motor 1004, and a zoom motor 1005. Further, the pan-tilt unit 70 is connected to the camera 10 and the radar 80 via the general-purpose I / F 1001. The pan-tilt controller 1002 controls the pan motor 1003 for moving the camera 10 in the pan direction, the tilt motor 1004 for moving the camera 10 in the tilt direction, and the zoom motor 1005 for zooming in or out. The radar 80 detects an object using millimeter waves / microwaves or the like, and transmits object position information regarding the detected object to the pan-tilt unit 70. The pan-tilt unit 70 is an example of a control means, and the radar 80 is an example of an object detection means.

[0082] <Functional Configuration of the System> Next, with reference to FIG. 11, the functional configuration of the imaging system in Embodiment 3 will be described. FIG. 11 is a block diagram for explaining a functional configuration example of the imaging system according to Embodiment 3. In FIG. 11, the same components as those shown in FIGS. 3 and 7 are denoted by the same reference numerals, and redundant descriptions are omitted. The pan-tilt unit 70 has an object detection unit 1101, a movement amount calculation unit 1102, and a control unit 1103. Note that the camera 10 in Embodiment 3 is the same as the camera 10 in Embodiments 1 and 2, and the edge devices 40 and 50 are the same as the edge devices 40 and 50 in Embodiment 2.

[0083] The object detection unit 1101 receives object position information from the radar 80, and detects the position and direction of the object based on the received object position information. The movement amount calculation unit 1102 calculates a movement amount for turning the camera 10 so that the object is displayed at an appropriate size at the center position of the captured image based on the position and direction of the object detected by the object detection unit 1101. The control unit 1103 drives and controls the pan-tilt unit 70 and the camera 10 based on the movement amount calculated by the movement amount calculation unit 1102, and controls the orientation and angle of view of the camera.

[0084] <Overall system processing flow> Next, with reference to FIG. 12, various processes performed in the imaging system according to Embodiment 3 will be described. FIG. 12 is a flowchart showing an example of processing in the imaging system according to Embodiment 3.

[0085] In S1201, the object detection unit 1101 of the pan-tilt unit 70 determines whether it has received object position information from the radar 80. If the object detection unit 1101 determines that it has received object position information from the radar 80 (YES), the process proceeds to S1202; otherwise (NO), the process proceeds to S1203.

[0086] In S1202, the pan-tilt unit 70 changes the orientation of the camera 10 and the magnification of the lens based on the object position information received from the radar 80. Specifically, based on the object position information received from the radar 80, the object detection unit 1101 detects the position and direction of the object, and the movement amount calculation unit 1102 calculates a movement amount for turning the camera 10 in that position and direction. Then, the control unit 1103 drives and controls the pan-tilt unit 70 and the camera 10 based on the calculated movement amount, and controls the orientation of the camera 10 and the magnification of the lens so that the object is displayed at an appropriate size at the center position of the captured image.

[0087] In S1203, the imaging unit 301 of the camera 10 captures the imaging target area to obtain a captured image SA, and transmits the captured image SA and imaging information SB including the set values at the time of imaging in the camera 10 to the edge device 40. In S1204, the scene discrimination unit 711 of the edge device 40 discriminates the scene of the captured image SA acquired and transmitted by the camera 10 in S1203. The scene discrimination unit 711 receives the captured image SA and the imaging information SB transmitted from the camera 10, and discriminates the scene such as the overall location and situation from the objects shown in the captured image SA based on the received imaging information SB.

[0088] In S1205, the image processing unit 712 of the edge device 40 performs high-quality processing on the captured image SA based on the result of the scene discrimination in S1204 and the imaging information SB. Then, the image processing unit 712 transmits the image subjected to the high-quality processing to the display device 30 and the edge device 50 as an output image. In S1206, the user instruction unit 721 of the edge device 50 receives the specific area to be analyzed and the intensity adjustment regarding the high-quality processing instructed by the user via the GUI screen 800.

[0089] In S1207, the analysis processing unit 722 of the edge device 50 analyzes the output image which is the result of the high-quality processing in S1205. In the analysis processing in this step S1207, the analysis processing unit 722 performs analysis processing on the specific area within the output image designated as the analysis target by the user. In S1208, the parameter calculation unit 723 of the edge device 50 calculates correction parameters (camera parameter PA and image processing parameter PB) based on the intensity adjustment instructed by the user and the result of the analysis processing in S1207. Then, the parameter calculation unit 723 sends the calculated correction parameters to the parameter update unit 302 of the camera 10 and the parameter update unit 724 of the edge device 50.

[0090] In S1209, the parameter update unit 302 of the camera 10 receives the camera parameter PA from the edge device 50, and updates the set value of the camera 10 based on the received camera parameter PA. Also, the parameter update unit 724 of the edge device 50 controls the parameters of the image processing unit 712 of the edge device 40 based on the image processing parameter PB calculated by the parameter calculation unit 723, and updates the intensity of the high-image-quality processing. The above is the processing flow performed in the imaging system according to Embodiment 3.

[0091] In Embodiment 3, a method of controlling the operation of the pan-tilt of the camera so that a moving object is displayed at an appropriate size at the center position of the captured image by combining the camera 10, the pan-tilt 70, and the radar 80 has been described. By using an external device such as a radar in combination as in this embodiment, the position information of the monitoring target can be known, and it becomes possible to improve the visibility of a moving object that can be the monitoring target in the captured image.

[0092] Note that in the above-described Embodiments 2 and 3, an example in which the high-image-quality processing and the analysis processing are performed by different edge devices has been shown. However, similar to Embodiment 1, a configuration in which the high-image-quality processing and the analysis processing are performed by one edge device may be adopted.

[0093] (Other Embodiments of the Present Invention) The present invention can also be realized by supplying a program that realizes one or more functions of the above-described embodiments to a system or device via a network or a storage medium, and causing one or more processors in a computer of the system or device to read and execute the program. Further, it can also be realized by a circuit (for example, ASIC) that realizes one or more functions.

[0094] Note that the above-described embodiments are merely specific examples for implementing the present invention, and the technical scope of the present invention should not be construed in a limited manner by these. That is, the present invention can be implemented in various forms without departing from its technical idea or its main features.

[0095] The disclosure of this embodiment includes the following configurations, methods, and the like. (Configuration 1) Image processing means for performing high-quality processing to reduce image quality degradation on the captured image acquired by the imaging means, An image processing apparatus, characterized by comprising adjustment means for adjusting at least one parameter of the parameter related to the imaging means and the parameter related to the high-quality processing based on the analysis result of the captured image subjected to the high-quality processing. (Configuration 2) The adjustment means Calculation means for calculating a correction value of the parameter based on the analysis result of the captured image subjected to the high-quality processing, The image processing apparatus according to Configuration 1, characterized by comprising update means for updating the parameter based on the correction value calculated by the calculation means. (Configuration 3) The image processing apparatus according to Configuration 1 or 2, characterized by comprising analysis processing means for analyzing the captured image subjected to the high-quality processing and outputting the analysis result to the adjustment means. (Configuration 4) The image processing apparatus according to Configuration 3, characterized in that the analysis processing performed by the analysis processing means on the captured image varies according to at least one of the type of the image sensor of the imaging means, the type of the high-quality processing, the use of deep learning in the high-quality processing, and the scene of the captured image. (Configuration 5) The analysis processing means determines whether image quality degradation has occurred in the captured image subjected to the high-quality processing, If image quality degradation has occurred in the captured image subjected to the high-quality processing, the image processing apparatus according to Configuration 3 or 4, characterized in that the parameter is adjusted by the adjustment means. (Configuration 6) The adjustment means adjusts the parameter based on the analysis result of a specific region set as an analysis target in the captured image subjected to the high-quality processing. The image processing apparatus according to any one of Configurations 1 to 5. (Configuration 7) The image processing apparatus according to any one of Configurations 1 to 6, characterized in that at least one of the calculation method of the parameter related to the adjustment of the parameter performed by the adjustment means and the intensity adjustment is settable by the user. (Configuration 8) The image processing apparatus according to any one of Configurations 1 to 7, characterized in that the high image quality processing includes at least one of noise reduction processing, haze removal processing, and super resolution processing. (Configuration 9) The image processing apparatus according to any one of Configurations 1 to 8, characterized in that the parameters related to the imaging means include at least one of an aperture value, a shutter speed, a sensitivity, a focal length, and a white balance calculation mode. (Configuration 10) The image processing apparatus according to any one of Configurations 1 to 9, characterized in that the parameters related to the high image quality processing include parameters related to correction of at least one of brightness, color, contrast, dynamic range, and blur of the captured image. (System 1) An imaging means for acquiring a captured image, An imaging system, characterized in that it has the image processing apparatus according to any one of Configurations 1 to 10. (System 2) A first processing apparatus that performs high image quality processing for reducing image quality defects on the captured image acquired by the imaging means, An imaging system, characterized in that it has a second processing apparatus that is connected to the first processing apparatus and adjusts at least one of the parameters related to the imaging means and the parameters related to the high image quality processing based on the analysis result of the captured image that has been subjected to the high image quality processing. (System 3) The imaging system according to System 2, characterized in that it has an imaging means for acquiring the captured image. (System 4) The imaging system according to System 3, characterized in that it has a control means for controlling at least one of the orientation and the angle of view of the imaging means based on the position information of the object detected by the object detection means. (Method 1) An image processing step of performing high - quality processing to reduce image quality degradation on the captured image obtained by the imaging means, and an adjustment step of adjusting at least one parameter of the parameter related to the imaging means and the parameter related to the high - quality processing based on the analysis result of the captured image that has undergone the high - quality processing. An image processing method characterized by having these steps. (Program 1) A program for causing a computer of an image processing apparatus to execute an image processing step of performing high - quality processing to reduce image quality degradation on the captured image obtained by the imaging means, and an adjustment step of adjusting at least one parameter of the parameter related to the imaging means and the parameter related to the high - quality processing based on the analysis result of the captured image that has undergone the high - quality processing.

Explanation of Signs

[0096] 10: Camera 20, 40, 50: Edge device 30: Display device 70: Pan - tilt unit 80: Radar 301: Imaging unit 302, 315, 724: Parameter update unit 311, 711: Scene discrimination unit 312, 712: Image processing unit 313, 722: Analysis processing unit 314, 723: Parameter calculation unit 721: User instruction unit

Claims

1. Image processing means for performing high-quality processing to reduce image quality degradation on a captured image acquired by imaging means, and adjustment means for adjusting at least one parameter of a parameter related to the imaging means and a parameter related to the high-quality processing based on an analysis result of the captured image that has undergone the high-quality processing. An image processing apparatus characterized by having the above.

2. The adjustment means, calculation means for calculating a correction value of the parameter based on an analysis result of the captured image that has undergone the high-quality processing, and update means for updating the parameter based on the correction value calculated by the calculation means. The image processing apparatus according to claim 1, characterized by having the above.

3. The image processing apparatus according to claim 1, further comprising analysis processing means for analyzing the captured image that has undergone the high-quality processing and outputting the analysis result to the adjustment means.

4. The analysis processing performed by the analysis processing means on the captured image varies according to at least one of the type of image sensor of the imaging means, the type of high-quality processing, the use of deep learning in the high-quality processing, and the scene of the captured image. The image processing apparatus according to claim 3, characterized by the above.

5. The analysis processing means determines whether image quality degradation has occurred in the captured image that has undergone the high-quality processing, and if image quality degradation has occurred in the captured image that has undergone the high-quality processing, the parameter is adjusted by the adjustment means. The image processing apparatus according to claim 3, characterized by the above.

6. The adjustment means adjusts the parameter based on an analysis result of a specific region set as an analysis target in the captured image that has undergone the high-quality processing. The image processing apparatus according to claim 1, characterized by the above.

7. The image processing apparatus according to claim 1, characterized in that at least one of the calculation method and intensity adjustment of the parameter related to the adjustment of the parameter performed by the adjustment means can be set by the user.

8. The high-quality processing includes at least one of noise reduction processing, haze removal processing, and super-resolution processing. The image processing apparatus according to claim 1, characterized by the above.

9. The parameter related to the imaging means includes at least one of an aperture value, a shutter speed, sensitivity, a focal length, and a white balance calculation mode. The image processing apparatus according to claim 1, characterized by the above.

10. The image processing apparatus according to claim 1, wherein the parameters related to the high-quality processing include parameters related to correction of at least one of brightness, color, contrast, dynamic range, and blur of the captured image.

11. An imaging system comprising imaging means for acquiring a captured image, and the image processing apparatus according to claim 1.

12. A first processing device that performs high-quality processing to reduce image quality defects on the captured image acquired by the imaging means, and a second processing device that is connected to the first processing device and adjusts at least one parameter of the parameters related to the imaging means and the parameters related to the high-quality processing based on the analysis result of the captured image that has been subjected to the high-quality processing.

13. The imaging system according to claim 12, further comprising imaging means for acquiring the captured image.

14. The imaging system according to claim 13, further comprising control means for controlling at least one of the orientation and the angle of view of the imaging means based on the position information of the object detected by the object detection means.

15. An image processing method comprising an image processing step of performing high-quality processing to reduce image quality defects on the captured image acquired by the imaging means, and an adjustment step of adjusting at least one parameter of the parameters related to the imaging means and the parameters related to the high-quality processing based on the analysis result of the captured image that has been subjected to the high-quality processing.

16. A program for causing a computer of an image processing apparatus to execute an image processing step of performing high-quality processing to reduce image quality defects on the captured image acquired by the imaging means, and an adjustment step of adjusting at least one parameter of the parameters related to the imaging means and the parameters related to the high-quality processing based on the analysis result of the captured image that has been subjected to the high-quality processing.

Images