Method and device for monitoring image denoising, electronic device and storage medium

Abstract

The application relates to a monitoring image noise reduction method and device, an electronic device and a storage medium, wherein the monitoring image noise reduction method comprises the following steps: acquiring a monitoring image by a front-end image acquisition device; determining a current noise reduction parameter corresponding to the monitoring image according to an environment parameter of the monitoring image; and sending the monitoring image and the current noise reduction parameter to a back-end image noise reduction device for noise reduction. Through the application, the problem that the image noise of a front-end image acquisition device with a relatively low configuration is relatively large because the back-end image noise reduction device uses the same noise reduction parameter to reduce the image of multiple front-end image acquisition devices is solved, and the noise reduction quality and adaptability of the same back-end image noise reduction device when reducing the image of different front-end image acquisition devices are improved.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a method, device, electronic device, and storage medium for noise reduction of surveillance images. Background Art

[0002] During surveillance using a combination of front-end image acquisition equipment and back-end image noise reduction equipment, noise reduction processing is required for the images in the surveillance video. Taking cameras and DVRs as an example, the camera has an internal image processing unit that performs noise reduction on the captured images before sending them to the DVR. The DVR also has internal image noise reduction capabilities. After receiving the camera image, the DVR further reduces the noise of the image to produce a better image quality.

[0003] In related technologies, a back-end image noise reduction device is usually connected to multiple front-end image acquisition devices. However, each front-end image acquisition device has different configurations such as hardware, image signal processing (ISP), and central processing unit (CPU). As a result, the image processing and denoising effects vary. When the back-end image noise reduction device is connected to these different front-end image acquisition devices, it uses the same noise reduction parameters to reduce the noise of images from all front-end image acquisition devices. This results in higher image noise when the back-end image noise reduction device is used to reduce the noise of the front-end image acquisition device with lower configuration.

[0004] Currently, in related technologies, the back-end image noise reduction device uses the same noise reduction parameters to reduce the noise of images from multiple front-end image acquisition devices, resulting in a problem in which the image noise of the front-end image acquisition device with lower configuration is larger. No effective solution has been proposed yet. Summary of the Invention

[0005] The embodiments of the present application provide a monitoring image noise reduction method, device, front-end image acquisition equipment, back-end image noise reduction equipment, electronic device and storage medium, so as to at least solve the problem in the related art that a hard disk recorder uses the same noise reduction parameters to reduce the noise of images of multiple cameras, resulting in larger image noise in cameras with lower configurations.

[0006] In a first aspect, an embodiment of the present application provides a method for reducing noise in a surveillance image, comprising:

[0007] Acquire monitoring images through front-end image acquisition equipment;

[0008] determining a current noise reduction parameter corresponding to the surveillance image according to the environmental parameters of the surveillance image;

[0009] The monitoring image and the current noise reduction parameters are sent to a back-end image noise reduction device for noise reduction.

[0010] In some embodiments, determining a current noise reduction parameter corresponding to the surveillance image according to the environmental parameter of the surveillance image includes:

[0011] The current noise reduction parameter is determined according to the device information of the front-end image acquisition device.

[0012] In some embodiments, determining a current noise reduction parameter corresponding to the surveillance image according to the environmental parameter of the surveillance image includes:

[0013] The current noise reduction parameter is determined according to a current scene mode corresponding to the surveillance image, wherein the current scene mode is determined according to light intensity.

[0014] In some embodiments, before determining the current noise reduction parameter corresponding to the surveillance image based on the environmental parameter of the surveillance image, the method further includes:

[0015] Acquire a plurality of test images obtained by the front-end image acquisition device, wherein the plurality of test images respectively correspond to a plurality of different scene modes;

[0016] In each of the scene modes, obtaining a plurality of noise reduction results of the test image under different noise reduction parameters, and determining a noise reduction parameter corresponding to the scene mode according to the plurality of noise reduction results;

[0017] Determine the noise reduction parameters of the front-end image acquisition device in all the scene modes in sequence.

[0018] In some embodiments, before obtaining a plurality of noise reduction results of the test image under different noise reduction parameters, the method includes:

[0019] Obtaining a noise reduction result of the test image under a default configuration;

[0020] The range of the noise reduction parameter is determined according to the noise reduction result.

[0021] In some embodiments, determining the current noise reduction parameter according to the current scene mode corresponding to the surveillance image includes:

[0022] Updating the monitoring image according to a preset time period;

[0023] Obtaining the light intensity of the monitoring scene corresponding to the updated monitoring image;

[0024] determining a current scene mode corresponding to the updated surveillance image according to the light intensity;

[0025] determining the current noise reduction parameter according to the current scene mode.

[0026] In some embodiments, the determining the current noise reduction parameter according to the current scene mode comprises:

[0027] determining a current noise reduction level corresponding to the current scene mode according to a preset correspondence relationship between the front-end image acquisition device, the current scene mode and noise reduction levels, wherein the noise reduction levels correspond to a plurality of noise reduction parameters.

[0028] In some embodiments, after determining the current noise reduction level corresponding to the current scene mode, the method further comprises:

[0029] in a case where the current noise reduction level is different from a historical noise reduction level, determining a current noise reduction intensity corresponding to the current noise reduction level according to a mapping table, wherein the mapping table is used to record a mapping relationship between a plurality of noise reduction levels and noise reduction intensities, and is pre-stored in the back-end image noise reduction device.

[0030] In a second aspect, the embodiments of the present application provide a noise reduction method for a monitoring image, comprising:

[0031] acquiring a monitoring image collected by a front-end image acquisition device;

[0032] performing noise reduction on the monitoring image according to a current noise reduction parameter corresponding to the monitoring image, wherein the current noise reduction parameter is determined according to an environmental parameter of the monitoring image.

[0033] In a third aspect, the embodiments of the present application provide a front-end image acquisition device, comprising an acquisition module, a determination module and a sending module;

[0034] the acquisition module is configured to acquire a monitoring image;

[0035] the determination module is configured to determine a current noise reduction parameter corresponding to the monitoring image according to an environmental parameter of the monitoring image;

[0036] the sending module is configured to send the monitoring image and the current noise reduction parameter to a back-end image noise reduction device for noise reduction.

[0037] In a fourth aspect, the embodiments of the present application provide a back-end image noise reduction device, comprising a receiving module and a noise reduction module;

[0038] the receiving module is configured to acquire a monitoring image collected by a front-end image acquisition device;

[0039] The noise reduction module is configured to reduce noise of the monitoring image according to a current noise reduction parameter corresponding to the monitoring image, wherein the current noise reduction parameter is determined according to an environmental parameter of the monitoring image.

[0040] In a fifth aspect, an embodiment of the present application provides a noise reduction device for a monitoring image, comprising a front-end image acquisition device and a back-end image noise reduction device.

[0041] The front-end image acquisition device acquires a monitoring image and determines a current noise reduction parameter corresponding to the monitoring image according to an environmental parameter of the monitoring image.

[0042] The front-end image acquisition device sends the monitoring image and the current noise reduction parameter to the back-end image noise reduction device.

[0043] The back-end image noise reduction device reduces noise of the monitoring image according to the current noise reduction parameter.

[0044] In a sixth aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the noise reduction method for a monitoring image according to the first aspect.

[0045] In a seventh aspect, an embodiment of the present application provides a storage medium having a computer program stored thereon, wherein the program is executable on a processor to implement the noise reduction method for a monitoring image according to the first aspect.

[0046] Compared with the related art, the noise reduction method for a monitoring image provided by the embodiment of the present application acquires a monitoring image by a front-end image acquisition device, determines a current noise reduction parameter corresponding to the monitoring image according to an environmental parameter of the monitoring image, and sends the monitoring image and the current noise reduction parameter to a back-end image noise reduction device for noise reduction, thereby solving the problem that the same noise reduction parameter is used by the back-end image noise reduction device to reduce noise of images of multiple front-end image acquisition devices, resulting in a larger image noise of a front-end image acquisition device with a lower configuration, and improving the noise reduction quality and adaptability of the same back-end image noise reduction device when reducing noise of different front-end image acquisition devices.

[0047] Details of one or more embodiments of the present application are presented in the following drawings and description to make other features, objects and advantages of the present application more apparent. BRIEF DESCRIPTION OF DRAWINGS

[0048] The accompanying drawings illustrated herein are used to provide further understanding of the present application, and constitute a part of the present application. The illustrative embodiments of the present application and their description serve to explain the present application, and do not constitute improper limitations on the present application. In the drawings:

[0049] Figure 1 2 is a schematic diagram of an application environment of a method for reducing noise in surveillance images according to an embodiment of the present application;

[0050] Figure 2 is a flowchart of a method for reducing noise in surveillance images according to an embodiment of the present application;

[0051] Figure 3 is a flow chart of a method for determining noise reduction parameters according to an embodiment of the present application;

[0052] Figure 4 is a flowchart of a method for identifying a current scene mode according to an embodiment of the present application;

[0053] Figure 5 is a flow chart of a method for determining a noise reduction level according to an embodiment of the present application;

[0054] Figure 6 is a flowchart of another method for reducing noise of surveillance images according to an embodiment of the present application;

[0055] Figure 7 This is a hardware structure block diagram of a terminal for the method for reducing noise in surveillance images according to an embodiment of the present application;

[0056] Figure 8 is a structural block diagram of a front-end image acquisition device according to an embodiment of the present application;

[0057] Figure 9 4 is a flowchart of a method for reducing noise of a surveillance image according to a preferred embodiment of the present application. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application. In addition, it can also be understood that although the efforts made in this development process may be complex and lengthy, for ordinary technicians in the field related to the contents disclosed in the present application, some changes such as design, manufacturing or production based on the technical contents disclosed in the present application are only conventional technical means and should not be understood as the contents disclosed in the present application being insufficient.

[0059] References to "embodiments" in this application mean that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it refer to independent or alternative embodiments that are mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described in this application may be combined with other embodiments unless there is a conflict.

[0060] Unless otherwise defined, the technical or scientific terms used in this application should have the ordinary meaning understood by a person of ordinary skill in the technical field to which this application belongs. The words "one", "a", "the" and the like used in this application do not indicate a limit on quantity and may indicate the singular or plural. The terms "include", "comprise", "have" and any variations thereof used in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units that are inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like used in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The word "multiple" used in this application means greater than or equal to two. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. The terms "first", "second", "third" and the like involved in this application are merely used to distinguish similar objects and do not represent a specific ordering of the objects.

[0061] The noise reduction method of the monitoring image provided by this application can be applied to Figure 1 In the application environment shown, Figure 1 FIG. 1 is a schematic diagram of an application environment of a noise reduction method for monitoring images according to an embodiment of the present application. Figure 1As shown in the figure. The digital video recorder (DVR) is connected with multiple front-end cameras through a coaxial line, wherein the front-end cameras can be high definition composite video interface (HDCVI) cameras. Each CVI camera is calibrated with different scene modes before being connected with the DVR, and the noise reduction level corresponds to the noise reduction strength of the DVR. Therefore, in the actual monitoring process, the DVR can adaptively adjust the noise reduction strength according to the noise reduction level transmitted by each CVI camera, so as to reduce the noise of the monitoring images of different CVI cameras.

[0062] The embodiment provides a noise reduction method of a monitoring image. Figure 2 The flowchart of the noise reduction method of the monitoring image according to the embodiment of the application is shown in the figure, and the method comprises the following steps: Figure 2

[0063] In step S210, a monitoring image is acquired by a front-end image acquisition device.

[0064] The front-end image acquisition device in the embodiment is used for image acquisition in a monitoring scene, and can be a CVI camera, a camera or a camera head or any device capable of acquiring an image. The monitoring image can be a snapshot image of a current monitoring scene or an image frame in a monitoring video.

[0065] In step S220, a current noise reduction parameter corresponding to the monitoring image is determined according to an environmental parameter of the monitoring image.

[0066] The environmental parameter in the embodiment comprises a hardware environmental parameter and a natural environmental parameter in the process of acquiring the monitoring image. Specifically, the hardware environmental parameter is a hardware parameter corresponding to the front-end image acquisition device for acquiring the monitoring image, for example, exposure, brightness, focal length, model, version and the like of the front-end image acquisition device, and the natural environmental parameter is another parameter related to light intensity, shooting time, weather at the time of shooting and the like.

[0067] Image noise refers to unnecessary or redundant interference information existing in an image. The existence of image noise seriously affects the quality of the image, and therefore, the image noise needs to be corrected to improve the image quality. Since different hardware environmental parameters and natural environmental parameters can cause the image quality of the monitoring image to change, a corresponding current noise reduction parameter needs to be determined according to the environmental parameter during noise reduction, so as to obtain a better noise reduction effect. The current noise reduction parameter is a noise reduction parameter corresponding to the moment of acquiring the monitoring image.

[0068] ​Step S230: Send the monitoring image and the current noise reduction parameters to a backend image noise reduction device for noise reduction.

[0069] In this embodiment, noise reduction is performed on surveillance images using a back-end image noise reduction device. This device can be a DVR or a processor. It should be noted that the back-end image noise reduction device can be connected to multiple front-end image acquisition devices. Specifically, after obtaining current noise reduction parameters, the back-end image noise reduction device performs noise reduction on the surveillance images based on the current noise reduction parameters. Alternatively, noise reduction can be performed on surveillance images using methods such as mean filters, adaptive Wiener filters, median filters, morphological noise filters, and wavelet denoising.

[0070] Through the above steps S210 to S230, in the process of denoising the monitoring image, the current noise reduction parameters can be determined according to the environmental parameters in the process of obtaining the monitoring image, and the monitoring image is denoised according to the current noise reduction parameters, which is more compatible with the front-end image acquisition device and the monitoring image and more targeted. Therefore, it solves the problem in the related art that the back-end image noise reduction device uses the same noise reduction parameters to denoise the monitoring images of multiple different front-end image acquisition devices, resulting in greater image noise in the front-end image acquisition device with lower configuration, and improves the noise reduction quality and adaptability of the same back-end image noise reduction device when denoising different front-end image acquisition devices.

[0071] In some embodiments, the current noise reduction parameters are determined based on the device information of the front-end image acquisition device. The device information in this embodiment refers to the hardware environment information corresponding to the front-end image acquisition device, such as the device model and device configuration information of the front-end image acquisition device. If the device information of the front-end image acquisition device is different, even if the noise reduction parameters are used to reduce the noise of the surveillance image based on the same noise reduction parameters, different noise reduction effects will be achieved. Therefore, when performing noise reduction, selecting the noise reduction parameters corresponding to the front-end image acquisition device based on the device information can achieve better noise reduction effects.

[0072] Furthermore, the correspondence between the device information of the front-end image acquisition device and the noise reduction parameters can be set and stored in advance.

[0073] Furthermore, the current noise reduction parameters are determined based on the current scene mode corresponding to the surveillance image, where the current scene mode is determined based on light intensity. Specifically, different surveillance scenes can be pre-classified into multiple scene modes based on light intensity, where light intensity is used to indicate light intensity. For example, surveillance scenes can be classified into high-illuminance scenes, medium-illuminance scenes, low-illuminance scenes, and nighttime infrared scenes based on different light intensities. In other embodiments, more levels of scene modes can be set based on light intensity and actual needs.

[0074] In this embodiment, the correspondence between light intensity and scene mode can be manually set and updated according to actual needs. During actual monitoring, the current scene mode can be determined based on the preset correspondence and the current light intensity. The current light intensity and the current scene mode both correspond to the time when the monitoring image is acquired.

[0075] Because light intensity significantly affects noise reduction parameters, for example, if sufficient light intensity is used when acquiring surveillance images, the noise in the surveillance images is low, and accordingly, a lower noise reduction level is required. Therefore, in this embodiment, by selecting the corresponding current noise reduction parameters based on the scene mode determined by light intensity, the noise reduction effect can be further improved.

[0076] It should be noted that the current noise reduction parameters may be determined jointly based on the device information of the front-end image acquisition device and the current scene mode, or may be determined separately based on the device information or the current scene mode.

[0077] In some embodiments, for the back-end image noise reduction device used in the actual monitoring process, the correspondence between the scene mode, the front-end image acquisition device and the noise reduction parameters can be determined in advance by other back-end image noise reduction devices with the same or corresponding noise reduction strength. For example, when using a DVR to perform image noise reduction on the monitoring image, it is possible to test other DVRs of the same model to determine the corresponding relationship that needs to be preset, or to test the front-end image acquisition device based on other models of DVRs, but it is necessary to first determine the correspondence between the noise reduction strengths of different models of DVRs to ensure the accuracy of the noise reduction results. For a determined front-end image acquisition device, Figure 3 is a flow chart of a method for determining noise reduction parameters according to an embodiment of the present application. Figure 3 As shown, the method includes the following steps:

[0078] Step S310: Acquire a plurality of test images obtained by a front-end image acquisition device, wherein the plurality of test images respectively correspond to a plurality of different scene modes.

[0079] When testing front-end image acquisition devices, it is necessary to obtain test images in different scene modes to ensure that the front-end image acquisition device can maintain optimal noise reduction effects around the clock. Preferably, each scene mode can correspond to multiple test images to improve the accuracy of the correspondence between scene modes, front-end image acquisition devices, and noise reduction parameters.

[0080] Step S320 : obtaining multiple noise reduction results of the test image under different noise reduction parameters in each scene mode, and determining the noise reduction parameter corresponding to the scene mode according to the multiple noise reduction results.

[0081] In this embodiment, the corresponding relationship between the scene mode, the front-end image acquisition device and the noise reduction parameter is determined by the back-end image noise reduction device. Specifically, each back-end image noise reduction device has multiple sets of noise reduction parameters, and the specific values of each set of noise reduction parameters are also different, so the noise reduction results are also different. Therefore, in the test process, the test image needs to be noise-reduced under different noise reduction parameters to determine the noise reduction results under each set of noise reduction parameters, and the different noise reduction results are compared to determine the noise reduction parameter corresponding to the scene mode.

[0082] In step S330, the noise reduction parameters of the front-end image acquisition device under all scene modes are determined in sequence.

[0083] For the front-end image acquisition device, since the noise of the monitoring image under different light intensities is inconsistent, multiple scene modes can be set according to the light intensity of different time periods. For each scene mode of the front-end image acquisition device, the noise reduction parameter corresponding to the scene mode can be determined to improve the noise reduction effect.

[0084] Through the above steps S310 to S330, in this embodiment, for the front-end image acquisition device, the test image is noise-reduced under different scene modes and different noise reduction intensities to determine the optimal noise reduction parameter corresponding to the front-end image acquisition device and the scene mode, thereby improving the noise reduction accuracy of the monitoring image of the front-end image acquisition device.

[0085] Further, in the case where one back-end image acquisition device needs to connect multiple front-end image acquisition devices, each front-end image acquisition device can determine the corresponding relationship between the scene mode, the front-end image acquisition device and the noise reduction parameter through the above steps S310 to S330.

[0086] In some embodiments, before obtaining multiple noise reduction results of the test image under different noise reduction parameters, the noise reduction result of the test image under the default configuration needs to be obtained first, wherein the default configuration is the default noise reduction configuration of the back-end image noise reduction device during the test, corresponding to a set of default noise reduction parameters, and then the range of the noise reduction parameter is determined according to the noise reduction result under the default configuration, and multiple sets of noise reduction parameters are determined to perform noise reduction on the test image. In this embodiment, the range of the noise reduction parameter can be more reasonably set according to the noise reduction result under the default configuration. For example, in the case where it is judged according to the noise reduction result that the noise reduction parameter under the default configuration is too low, a higher range of the noise reduction parameter can be set, in the case where it is judged according to the noise reduction result that the noise reduction parameter under the default configuration is too high, a lower range of the noise reduction parameter can be set, and in the case where it is judged according to the noise reduction result that the noise reduction parameter under the default configuration can be used, the noise reduction parameter corresponding to the default configuration can be used as a reference to expand in the direction of lower and higher to obtain the final range of the noise reduction parameter, thereby improving the speed and accuracy of the determination of the noise reduction parameter.

[0087] In some embodiments, Figure 4 is a flowchart of a method for identifying a current scene mode according to an embodiment of the present application, as shown in Figure 4 The method comprises the following steps:

[0088] In step S410, the monitoring image is updated according to a preset time period.

[0089] Since the current scene mode needs to be obtained in real time, the monitoring image needs to be updated regularly. The preset time period in this embodiment can be set and changed according to requirements, such as several seconds, one minute, etc.

[0090] In step S420, the light intensity in the monitoring scene corresponding to the updated monitoring image is obtained.

[0091] When the monitoring image is denoised, the scene mode corresponding to the monitoring image needs to be determined, so when the monitoring image is updated, the light intensity in the corresponding monitoring scene needs to be obtained to determine the scene mode. Generally, the light intensity can be obtained through a sensor, or the monitoring image can be obtained, and the light intensity can be determined by analyzing the monitoring image through an image analysis algorithm.

[0092] In step S430, the current scene mode corresponding to the updated monitoring image is determined according to the light intensity.

[0093] In step S440, the current denoising parameter is determined according to the current scene mode.

[0094] Through the above steps S410 to S440, the monitoring image and the scene mode are updated according to the preset time period, so as to improve the accuracy of image denoising.

[0095] In some embodiments, the method for determining the current denoising parameter is specifically: determining the current denoising level corresponding to the current scene mode according to a preset corresponding relationship between the front-end image acquisition device, the current scene mode and the denoising level, wherein the denoising level corresponds to multiple denoising parameters. The preset corresponding relationship in this embodiment can be a mapping table or an equation relationship between parameters, and is pre-stored in the front-end image acquisition device, so that the front-end image acquisition device can determine effective denoising parameters.

[0096] Based on the above-mentioned preset correspondence, during the process of noise reduction on the surveillance image, the current noise reduction level corresponding to the current scene mode can be determined according to the preset correspondence between the front-end image acquisition device, the scene mode, and the noise reduction level. The surveillance image and the current noise reduction level are then sent to the back-end image noise reduction device, so that the back-end image noise reduction device can perform noise reduction on the surveillance image according to the current noise reduction level. Since noise reduction on the surveillance image is performed according to the current noise reduction level corresponding to the front-end image acquisition device and the current scene mode during the noise reduction process, it is more closely matched with the front-end image acquisition device and is more targeted.

[0097] Preferably, the method for determining the preset correspondence relationship may include: obtaining multiple test images obtained by a front-end image acquisition device, each of the multiple test images corresponding to a plurality of different scene modes; obtaining multiple noise reduction results for the test images at different noise reduction intensities within each scene mode; and determining the noise reduction level corresponding to the scene mode based on the multiple noise reduction results; and sequentially determining the noise reduction level of the front-end image acquisition device for all scene modes. Since each back-end image noise reduction device has multiple noise reduction intensities, the values ​​of the multiple noise reduction parameters corresponding to each noise reduction intensity are different, and thus the noise reduction results are also different. Therefore, during the testing process, it is necessary to perform noise reduction on the test images at different noise reduction intensities to determine the noise reduction results at each noise reduction intensity, and then compare the different noise reduction results to determine the noise reduction level. The multiple noise reduction intensities can be set at equal intervals, or, depending on the actual scenario requirements, the noise reduction intensities can be set densely in certain areas and sparsely in other areas. By testing each scene mode of the front-end image acquisition device, the noise reduction level corresponding to the scene mode can be determined, thereby improving the noise reduction effect.

[0098] Furthermore, Figure 5 is a flow chart of a method for determining a noise reduction level according to an embodiment of the present application. Figure 5 As shown, the method includes the following steps:

[0099] Step S510 : determining a target noise reduction result from a plurality of noise reduction results according to a preset image quality evaluation index.

[0100] Image quality describes the overall effect of an image and can be evaluated using a variety of metrics. In this embodiment, the preset image quality evaluation metrics may include exposure, clarity, color, detail, texture, focus, and smear. In this embodiment, the noise reduction effects at different noise reduction intensities are evaluated using these image quality evaluation metrics. Specifically, this can be achieved using evaluation software or image analysis algorithms.

[0101] Preferably, the target denoising result in this embodiment is the optimal denoising result in the plurality of denoising results, and the denoising effect is the best. In other embodiments, the target denoising result can also be a denoising result that meets a preset image quality evaluation index threshold, for example, the sharpness is greater than or equal to a preset sharpness threshold, the smear is less than or equal to a preset smear threshold, and the like. At this time, the target denoising result can have one or more.

[0102] In step S520, a target denoising intensity corresponding to the target denoising result is determined.

[0103] Since different denoising results are achieved under different denoising intensities, the corresponding target denoising intensity can be determined through the selected target denoising result.

[0104] In step S530, a target denoising level in the scene mode is determined according to the target denoising intensity.

[0105] In this embodiment, the test image is denoised by the back-end image denoising device, and different denoising intensities of the back-end image denoising device correspond to different denoising levels of the front-end image acquisition. Therefore, after the target denoising level is determined, a target denoising level of a front-end image acquisition device can be determined according to the target denoising intensity.

[0106] In the case of multiple target denoising results, multiple target denoising levels can be determined. In actual use, different target denoising levels can be sorted according to different image quality evaluation indexes according to actual scene requirements, and the final target denoising level for use can be determined according to the sorting result.

[0107] Through the above steps S510 to S530, the target denoising result is selected according to the plurality of image quality evaluation indexes in this embodiment, and the target denoising level in a certain scene mode is determined correspondingly, so as to improve the accuracy when the target denoising level is determined.

[0108] In some embodiments, the specific process in which the back-end image denoising device denoises the monitoring image is that, in the case that the current denoising level is different from the historical denoising level, the current denoising intensity corresponding to the current denoising level is determined according to the mapping table, and in the case that the current denoising level is the same as the historical denoising level, the monitoring image is denoised according to the denoising intensity corresponding to the historical denoising level. The mapping table is used to record the mapping relationship between the plurality of denoising levels and the denoising intensities, and is pre-stored in the back-end image denoising device. In the case that the monitoring image is frequently updated, the back-end denoising device needs to update the corresponding denoising intensity in real time, so forming the mapping table of the corresponding relationship between the denoising levels and the denoising intensities in different scene modes is conducive to the storage of the corresponding relationship and improves the searching efficiency. The historical denoising level is the denoising level for denoising the previous frame of the current monitoring image.

[0109] In some embodiments, a back-end image noise reduction device may be connected to multiple front-end image acquisition devices. At this time, the current noise reduction levels sent by the multiple front-end image acquisition devices to the back-end image noise reduction device are respectively obtained, so that the back-end image noise reduction device determines the current noise reduction intensity corresponding to the front-end image acquisition device according to the mapping table. In this embodiment, the current noise reduction level sent by each front-end image acquisition device also corresponds to its own current scene mode. Preferably, the mapping table in the back-end image noise reduction device is a copy to improve the search speed of the current noise reduction intensity.

[0110] In some embodiments, Figure 6 FIG. 1 is a flow chart of another method for reducing noise of a surveillance image according to an embodiment of the present application. Figure 6 As shown, the method includes the following steps:

[0111] Step S610, acquiring a surveillance image captured by a front-end image acquisition device;

[0112] Step S620 , performing noise reduction on the surveillance image according to current noise reduction parameters corresponding to the surveillance image, wherein the current noise reduction parameters are determined according to environmental parameters of the surveillance image.

[0113] Specifically, the current noise reduction parameters are determined based on the device information of the front-end image acquisition device; and / or, the current noise reduction parameters are determined based on the current scene mode corresponding to the monitoring image, wherein the current scene mode is determined based on the light intensity.

[0114] Before determining the current noise reduction parameters corresponding to the surveillance image based on the environmental parameters of the surveillance image, it is necessary to obtain multiple test images obtained by the front-end image acquisition device, where the multiple test images correspond to multiple different scene modes. In each scene mode, multiple noise reduction results are obtained for the test image under different noise reduction parameters, and the noise reduction parameters corresponding to the scene mode are determined based on the multiple noise reduction results. The noise reduction parameters of the front-end image acquisition device are then sequentially determined for all scene modes. Furthermore, before obtaining multiple noise reduction results for the test image under different noise reduction parameters, noise reduction results are obtained for the test image under the default configuration, and the range of the noise reduction parameters is determined based on the noise reduction results.

[0115] In some embodiments, determining the current noise reduction parameters includes: updating the surveillance image according to a preset time period; obtaining the light intensity in the surveillance scene corresponding to the updated surveillance image; determining the current scene mode corresponding to the updated surveillance image based on the light intensity; and determining the current noise reduction parameters based on the current scene mode.

[0116] Furthermore, determining the current noise reduction parameters according to the current scene mode includes: determining the current noise reduction level corresponding to the current scene mode according to a preset correspondence between the front-end image acquisition device, the current scene mode and the noise reduction level, wherein the noise reduction level corresponds to multiple noise reduction parameters.

[0117] After determining the current noise reduction level corresponding to the current scene mode, if the current noise reduction level is different from the historical noise reduction level, the current noise reduction intensity corresponding to the current noise reduction level is determined according to a mapping table, wherein the mapping table is used to record the mapping relationship between multiple noise reduction levels and noise reduction intensities, and is pre-stored in the back-end image noise reduction device.

[0118] Through the above-mentioned steps S610 and S620, in the process of denoising the monitoring image, the current noise reduction parameters can be determined according to the environmental parameters in the process of obtaining the monitoring image, and the monitoring image is denoised according to the current noise reduction parameters, which is more compatible with the front-end image acquisition device and the monitoring image and more targeted. Therefore, it solves the problem in the related art that the back-end image noise reduction device uses the same noise reduction parameters to denoise the monitoring images of multiple different front-end image acquisition devices, resulting in greater image noise in the front-end image acquisition device with lower configuration, and improves the noise reduction quality and adaptability of the same back-end image noise reduction device when denoising different front-end image acquisition devices.

[0119] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0120] The method embodiments provided in this application can be executed in a terminal, a computer or a similar computing device. Taking running on a terminal as an example, Figure 7 FIG. 1 is a block diagram of the hardware structure of a terminal of the method for reducing noise of monitoring images according to an embodiment of the present application. Figure 7 As shown, the terminal 70 may include one or more ( Figure 7 Only one is shown) processor 702 (processor 702 may include but is not limited to a microprocessor MCU or a programmable logic device FPGA and other processing devices) and a memory 704 for storing data. Optionally, the terminal may also include a transmission device 706 and an input / output device 708 for communication functions. It will be understood by those skilled in the art that Figure 7 The structure shown is only for illustration and does not limit the structure of the above terminal. Figure 7 More or fewer components than shown, or with Figure 7 Different configurations shown.

[0121] Memory 704 can be used to store control programs, such as software programs and modules of application software, such as the control program corresponding to the surveillance image noise reduction method in the embodiments of the present application. Processor 702 executes the control program stored in memory 704 to execute various functional applications and data processing, thereby implementing the aforementioned method. Memory 704 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 704 may further include memory remotely located relative to processor 702, and such remote memory may be connected to terminal 70 via a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0122] Transmission device 706 is used to receive or send data via a network. A specific example of the aforementioned network may include a wireless network provided by the communications provider of terminal 70. In one embodiment, transmission device 706 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, transmission device 706 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0123] This embodiment also provides a front-end image acquisition device, which is used to implement the above-mentioned embodiments and preferred implementation methods. The details that have been described will not be repeated here. As used below, the terms "module", "unit", "sub-unit", etc. can be a combination of software and / or hardware that implements the predetermined functions. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and conceivable.

[0124] Figure 8 is a structural block diagram of a front-end image acquisition device according to an embodiment of the present application, such as Figure 8 As shown, the device includes an acquisition module 81, a determination module 82 and a sending module 83: the acquisition module 81 is used to acquire a monitoring image; the determination module 82 is used to determine the current noise reduction parameters corresponding to the monitoring image according to the environmental parameters of the monitoring image; the sending module 83 is used to send the monitoring image and the current noise reduction parameters to the back-end image noise reduction device for noise reduction.

[0125] In the process of denoising the surveillance image, the determination module 82 can determine the current noise reduction parameters based on the environmental parameters in the process of obtaining the surveillance image, and the sending module 83 sends the surveillance image and the current noise reduction parameters to the back-end image noise reduction device, so that the back-end image noise reduction device can reduce the noise of the surveillance image according to the current noise reduction parameters, which is more matched with the front-end image acquisition device and the surveillance image, and more targeted. Therefore, it solves the problem in the related technology that the back-end image noise reduction device uses the same noise reduction parameters to reduce the noise of the surveillance images of multiple different front-end image acquisition devices, resulting in greater image noise in the front-end image acquisition device with lower configuration, and improves the noise reduction quality and adaptability of the same back-end image noise reduction device when reducing the noise of different front-end image acquisition devices.

[0126] In some embodiments, the determination module 82 determines the current noise reduction parameters based on the device information of the front-end image acquisition device; and / or determines the current noise reduction parameters based on the current scene mode corresponding to the monitoring image, wherein the current scene mode is determined based on the light intensity.

[0127] In some embodiments, the determination module 82 is further used to obtain multiple test images obtained by the front-end image acquisition device, wherein the multiple test images correspond to multiple different scene modes respectively; in each scene mode, multiple noise reduction results of the test image under different noise reduction parameters are obtained, and the noise reduction parameters corresponding to the scene mode are determined based on the multiple noise reduction results; and the noise reduction parameters of the front-end image acquisition device in all scene modes are determined in turn.

[0128] In some embodiments, the determination module 82 is further used to determine a target noise reduction result among multiple noise reduction results based on a preset image quality evaluation index; determine a target noise reduction intensity corresponding to the target noise reduction result; and determine a target noise reduction level in the scene mode based on the target noise reduction intensity.

[0129] In some embodiments, the noise reduction apparatus for monitoring images further includes a pre-noise reduction module for obtaining a noise reduction result of a test image under a default configuration; and determining a range of noise reduction intensity according to the noise reduction result.

[0130] In some embodiments, the acquisition module 81 is also used to update the surveillance image according to a preset time period; obtain the light intensity in the surveillance scene corresponding to the updated surveillance image; determine the current scene mode corresponding to the updated surveillance image based on the light intensity, and determine the current noise reduction parameter based on the current scene mode.

[0131] In some embodiments, the determination module 82 is further used to determine the current noise reduction level corresponding to the current scene mode based on a preset correspondence between the front-end image acquisition device, the current scene mode and the noise reduction level, wherein the noise reduction level corresponds to multiple noise reduction parameters.

[0132] In some embodiments, the determining module 83 is further configured to determine, according to a mapping table, a current noise reduction intensity corresponding to the current noise reduction level when the current noise reduction level is different from the historical noise reduction level, wherein the mapping table is used to record a mapping relationship between a plurality of noise reduction levels and noise reduction intensities, and is pre-stored in the backend image noise reduction device. In the case of a plurality of front-end image acquisition devices, the current noise reduction levels sent by the plurality of front-end image acquisition devices to the backend image noise reduction device are acquired respectively, so that the backend image noise reduction device determines the current noise reduction intensity corresponding to the front-end image acquisition device according to the mapping table.

[0133] Correspondingly, the application further provides a backend image noise reduction device, comprising a receiving module and a noise reduction module; the receiving module is configured to acquire a monitoring image acquired by a front-end image acquisition device; the noise reduction module is configured to perform noise reduction on the monitoring image according to a current noise reduction parameter corresponding to the monitoring image, wherein the current noise reduction parameter is determined according to an environmental parameter of the monitoring image. In this embodiment, the receiving module acquires the monitoring image, the noise reduction module determines the current noise reduction parameter according to the environmental parameter corresponding to the monitoring image, and performs noise reduction on the monitoring image according to the current noise reduction parameter. This is more matched and more targeted with the front-end image acquisition device and the monitoring image, thus solving the problem in the related art that the backend image noise reduction device uses the same noise reduction parameter to perform noise reduction on the monitoring images of a plurality of different front-end image acquisition devices, resulting in a large image noise of the front-end image acquisition device with a lower configuration, and improving the noise reduction quality and adaptability of the same backend image noise reduction device when performing noise reduction on different front-end image acquisition devices.

[0134] Specifically, the noise reduction module determines the current noise reduction parameter according to the device information of the front-end image acquisition device; and / or determines the current noise reduction parameter according to a current scene mode corresponding to the monitoring image, wherein the current scene mode is determined according to the light intensity.

[0135] Before determining the current noise reduction parameter corresponding to the monitoring image according to the environmental parameter of the monitoring image, the noise reduction module further needs to acquire a plurality of test images obtained by the front-end image acquisition device, wherein the plurality of test images correspond to a plurality of different scene modes respectively; in each scene mode, the noise reduction module acquires a plurality of noise reduction results of the test image under different noise reduction parameters, determines the noise reduction parameter corresponding to the scene mode according to the plurality of noise reduction results; and sequentially determines the noise reduction parameter of the front-end image acquisition device under all scene modes. Further, the noise reduction module acquires a noise reduction result of the test image under a default configuration before acquiring the plurality of noise reduction results of the test image under different noise reduction parameters; and determines the range of the noise reduction parameter according to the noise reduction result.

[0136] In some embodiments, the noise reduction module determines the current noise reduction parameters by: updating the surveillance image according to a preset time period; obtaining the light intensity in the surveillance scene corresponding to the updated surveillance image; determining the current scene mode corresponding to the updated surveillance image based on the light intensity; and determining the current noise reduction parameters based on the current scene mode.

[0137] Furthermore, the noise reduction module determines the current noise reduction parameters according to the current scene mode, including: determining the current noise reduction level corresponding to the current scene mode according to a preset correspondence between the front-end image acquisition device, the current scene mode and the noise reduction level, wherein the noise reduction level corresponds to multiple noise reduction parameters.

[0138] After determining the current noise reduction level corresponding to the current scene mode, the noise reduction module determines the current noise reduction intensity corresponding to the current noise reduction level according to a mapping table when the current noise reduction level is different from the historical noise reduction level, wherein the mapping table is used to record the mapping relationship between multiple noise reduction levels and noise reduction intensities, and is pre-stored in the back-end image noise reduction device.

[0139] Finally, the present application also provides a noise reduction device for monitoring images, including a front-end image acquisition device and a back-end image noise reduction device; the front-end image acquisition device acquires a monitoring image and determines a current noise reduction parameter corresponding to the monitoring image based on the environmental parameters of the monitoring image; the front-end image acquisition device sends the monitoring image and the current noise reduction parameter to the back-end image noise reduction device; the back-end image noise reduction device performs noise reduction on the monitoring image according to the current noise reduction parameter.

[0140] Specifically, the front-end image acquisition device determines the current noise reduction parameters based on the device information; and / or determines the current noise reduction parameters based on the current scene mode corresponding to the monitoring image, wherein the current scene mode is determined according to the light intensity.

[0141] Before determining the current noise reduction parameters, the front-end image acquisition device must be tested. Specifically, the front-end image acquisition device acquires multiple test images, each corresponding to a plurality of different scene modes. In each scene mode, the processor of the noise reduction device monitoring the image acquires multiple noise reduction results for the test image under different noise reduction parameters, determines the noise reduction parameters corresponding to the scene mode based on the multiple noise reduction results, and sequentially determines the noise reduction parameters of the front-end image acquisition device for all scene modes. Furthermore, before acquiring multiple noise reduction results for the test image under different noise reduction parameters, the processor acquires noise reduction results for the test image under the default configuration, and determines the range of the noise reduction parameters based on the noise reduction results.

[0142] In some embodiments, the processor controls the front-end image acquisition device to update the monitoring image according to a preset time period; acquires the illumination intensity in the monitoring scene corresponding to the updated monitoring image; determines the current scene mode corresponding to the updated monitoring image according to the illumination intensity; and determines the current noise reduction parameter according to the current scene mode.

[0143] Further, the processor determines the current noise reduction level corresponding to the current scene mode according to a preset correspondence relationship among the front-end image acquisition device, the current scene mode and the noise reduction level, wherein the noise reduction level corresponds to a plurality of noise reduction parameters.

[0144] After determining the current noise reduction level corresponding to the current scene mode, in a case where the current noise reduction level is different from a historical noise reduction level, the processor determines the current noise reduction intensity corresponding to the current noise reduction level according to a mapping table, wherein the mapping table is used to record the mapping relationship between a plurality of noise reduction levels and noise reduction intensities, and is pre-stored in the back-end image noise reduction device.

[0145] In the process of reducing the noise of the monitoring image, the current noise reduction parameter can be determined according to the environmental parameter in the process of acquiring the monitoring image, and the monitoring image is reduced according to the current noise reduction parameter. The front-end image acquisition device and the monitoring image are more matched and more targeted, thus solving the problem in the related art that the back-end image noise reduction device uses the same noise reduction parameter to reduce the monitoring image of a plurality of different front-end image acquisition devices, resulting in a large image noise of the front-end image acquisition device with a lower configuration, and improving the noise reduction quality and adaptability of the same back-end image noise reduction device when reducing the noise of different front-end image acquisition devices.

[0146] It should be noted that each of the above modules can be a functional module or a program module, and can be implemented by software or hardware. For the modules implemented by hardware, each of the above modules can be located in the same processor; or each of the above modules can be located in different processors in any combination.

[0147] The embodiments of the present application are described and explained below by preferred embodiments.

[0148] The monitoring image noise reduction system of the preferred embodiment of the present application comprises a DVR and a plurality of CVI cameras, each of which is connected with the DVR through a coaxial line. The DVR is used as a rear-end image noise reduction device, and the CVI camera is used as a front-end image acquisition device. The CVI camera complies with the HDCVI video transmission protocol and can transmit high-definition video analog signals through the coaxial line. The DVR can support the HDCVI high-definition video signal access and perform image processing, video encoding, video recording and disk storage functions. One DVR usually supports multiple video inputs. The HDCVI video transmission protocol supports bidirectional communication function, that is, the CVI camera and the DVR have certain bidirectional communication capability in addition to the transmission of image signals.

[0149] Generally, the central processing unit (CPU) in the DVR has the capability of reducing the monitoring image. After receiving the monitoring image of the CVI camera, the DVR will perform noise reduction processing on the monitoring image again to present a better image effect. The DVR end will have the noise reduction intensity of each channel for the user to select.

[0150] Figure 9 The flowchart of the monitoring image noise reduction method according to the preferred embodiment of the present application is shown in FIG. 10. The method comprises the following steps: Figure 8

[0151] S910, the CVI camera sets a group of noise reduction levels according to different scene modes, which correspond to the noise reduction intensity required by the DVR.

[0152] The process of determining the noise reduction level is as follows:

[0153] (1) A test DVR is determined as a standard reference device of the actual noise reduction DVR. The noise reduction intensity of the test DVR can be set to 0-100, and the greater the value, the stronger the noise reduction effect. If the model parameters of the actual noise reduction DVR are different from those of the test DVR, the intensity range and the noise reduction effect of the actual noise reduction DVR are taken as the standard of the test DVR;

[0154] (2) The CVI camera whose noise reduction level is to be determined is connected to the test DVR, and the monitoring image of the CVI camera is noise reduced through the default configuration of the test DVR;

[0155] (3) The scene modes are divided into high-illumination scene, medium-illumination scene, low-illumination scene and night infrared scene according to the light intensity, the noise reduction intensity of the test DVR is adjusted from 0 to 100, so that the noise reduction effect of the monitoring image in each scene mode reaches the optimum, and four target noise reduction intensities M1, M2, M3 and M4 corresponding to the scene modes are obtained; ​

[0156] (4) Target noise reduction intensity A mapping table is used to obtain the corresponding target noise reduction levels L1, L2, L3, and L4.

[0157] S920: The CVI camera determines the current scene mode and sends the current scene mode to the DVR via the HDCVI coaxial communication protocol.

[0158] Specifically, the CVI camera determines the current scene mode at preset intervals using its own sensors or through image algorithm analysis. It then transmits the corresponding noise reduction level to the DVR via the HDCVI coaxial communication protocol. For example, if scene modes are categorized by light intensity into high-illuminance, medium-illuminance, low-illuminance, and nighttime infrared scenes, the corresponding target noise reduction levels are L1, L2, L3, and L4, respectively. The CVI camera determines the current scene mode and the corresponding target noise reduction level every minute.

[0159] S930: The DVR receives coaxial data by channel. Since the CVI camera can also transmit other data through the coaxial line, the DVR needs to parse the coaxial data after receiving it. If a noise reduction level is obtained, the noise reduction level L is parsed and a determination is made as to whether it is equal to the noise reduction level received last time. If not, the corresponding noise reduction intensity M is found according to a preset mapping table, and the DVR configuration parameters corresponding to the noise reduction intensity M are activated.

[0160] In this embodiment, the mapping table between L and M is not limited and can be a simple linear relationship, such as S = 10 × L, or the one-to-one correspondence between the noise reduction level and the noise reduction strength can be adjusted according to actual needs. As long as the mapping table on the CVI camera is consistent with the mapping table on the DVR, it will be sufficient.

[0161] Through steps S910 to S930, this embodiment allows different DVR noise reduction parameters to be matched to different CVI cameras, resulting in optimal default noise reduction. For the same CVI camera, different noise reduction intensities can also be matched based on the current scene mode, ensuring optimal noise reduction at all times.

[0162] This embodiment further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0163] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0164] Optionally, in this embodiment, the processor may be configured to execute the following steps through a computer program:

[0165] S1, obtains monitoring images through the front-end image acquisition device.

[0166] S2: Determine a current noise reduction parameter corresponding to the surveillance image according to the environmental parameters of the surveillance image.

[0167] S3: Send the monitoring image and the current noise reduction parameters to a backend image noise reduction device for noise reduction.

[0168] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be repeated here.

[0169] In addition, in conjunction with the surveillance image noise reduction method in the above embodiments, embodiments of the present application may provide a storage medium for implementation. The storage medium stores a computer program; when the computer program is executed by a processor, it implements any of the surveillance image noise reduction methods in the above embodiments.

[0170] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0171] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A method for reducing noise of a surveillance image, characterized in that: The back-end image noise reduction device is connected to a plurality of front-end image acquisition devices via a coaxial line; the back-end image noise reduction device is a hard disk video recorder; The front-end image acquisition device is a CVI camera; the method includes: Acquire monitoring images through front-end image acquisition equipment; Determining a current noise reduction parameter corresponding to the surveillance image according to an environmental parameter of the surveillance image; the environmental parameter includes the light intensity during the acquisition of the surveillance image; The monitoring image and the current noise reduction parameters are sent to a back-end image noise reduction device for noise reduction; the back-end image noise reduction device determines the current noise reduction level corresponding to the current scene mode based on a preset correspondence between the front-end image acquisition device, the current scene mode and the noise reduction level, wherein the noise reduction level corresponds to multiple noise reduction parameters; the current scene mode is determined according to the light intensity; when the current noise reduction level is different from the historical noise reduction level, the current noise reduction intensity corresponding to the current noise reduction level is determined according to a mapping table, wherein the mapping table is used to record the mapping relationship between multiple noise reduction levels and noise reduction intensities.

2. The method for reducing noise of surveillance images according to claim 1, wherein: Determining the current noise reduction parameter corresponding to the surveillance image according to the environmental parameter of the surveillance image includes: The current noise reduction parameter is determined according to the device information of the front-end image acquisition device.

3. The method for reducing noise of a surveillance image according to claim 1 or 2, wherein: Determining the current noise reduction parameter corresponding to the surveillance image according to the environmental parameter of the surveillance image includes: The current noise reduction parameter is determined according to a current scene mode corresponding to the surveillance image, wherein the current scene mode is determined according to light intensity.

4. The method for reducing noise of surveillance images according to claim 3, wherein: Before determining the current noise reduction parameter corresponding to the surveillance image according to the environmental parameter of the surveillance image, the method further includes: Acquire a plurality of test images obtained by the front-end image acquisition device, wherein the plurality of test images respectively correspond to a plurality of different scene modes; In each of the scene modes, obtaining a plurality of noise reduction results of the test image under different noise reduction parameters, and determining a noise reduction parameter corresponding to the scene mode according to the plurality of noise reduction results; Determine the noise reduction parameters of the front-end image acquisition device in all the scene modes in sequence.

5. The method for reducing noise of surveillance images according to claim 4, wherein: Before obtaining a plurality of noise reduction results of the test image under different noise reduction parameters, the method includes: Obtaining a noise reduction result of the test image under a default configuration; The range of the noise reduction parameter is determined according to the noise reduction result.

6. The method for reducing noise of surveillance images according to claim 3, wherein: Determining the current noise reduction parameter according to the current scene mode corresponding to the surveillance image includes: Updating the monitoring image according to a preset time period; Obtaining the light intensity of the monitoring scene corresponding to the updated monitoring image; determining a current scene mode corresponding to the updated surveillance image according to the light intensity; The current noise reduction parameter is determined according to the current scene mode.

7. The method for reducing noise of surveillance images according to claim 6, wherein: The mapping table is pre-stored in the back-end image noise reduction device.

8. A method for reducing noise of a surveillance image, characterized in that: Applied to hard disk video recorders, which are connected to multiple front-end image acquisition devices via coaxial cables; The front-end image acquisition device is a CVI camera; the method includes: Acquire monitoring images collected by the front-end image acquisition device; performing noise reduction on the surveillance image according to a current noise reduction parameter corresponding to the surveillance image, wherein the current noise reduction parameter is determined according to an environmental parameter of the surveillance image; The environmental parameters include the light intensity during the acquisition of monitoring images; The noise reduction of the surveillance image according to the current noise reduction parameters corresponding to the surveillance image includes: determining a current noise reduction level corresponding to the current scene mode according to a preset correspondence between the front-end image acquisition device, the current scene mode, and the noise reduction level, wherein the noise reduction level corresponds to a plurality of noise reduction parameters; and the current scene mode is determined according to light intensity; The method further includes: when the current noise reduction level is different from the historical noise reduction level, determining a current noise reduction intensity corresponding to the current noise reduction level according to a mapping table, wherein the mapping table is used to record mapping relationships between multiple noise reduction levels and noise reduction intensities.

9. A front-end image acquisition device, characterized in that: The back-end image noise reduction device is connected to a plurality of front-end image acquisition devices via a coaxial line; the back-end image noise reduction device is a hard disk video recorder; the front-end image acquisition device is a CVI camera, including an acquisition module, a determination module and a sending module; The acquisition module is used to acquire monitoring images; The determination module is configured to determine a current noise reduction parameter corresponding to the surveillance image according to the environmental parameters of the surveillance image; The sending module is used to send the monitoring image and the current noise reduction parameters to the back-end image noise reduction device for noise reduction; The back-end image noise reduction device is used to determine a current noise reduction level corresponding to the current scene mode based on a preset correspondence between the front-end image acquisition device, the current scene mode, and the noise reduction level; and when the current noise reduction level is different from a historical noise reduction level, determine a current noise reduction intensity corresponding to the current noise reduction level based on a mapping table; wherein the noise reduction level corresponds to a plurality of noise reduction parameters; and the mapping table is used to record the mapping relationships between the plurality of noise reduction levels and the noise reduction intensities; The environmental parameters include light intensity during the acquisition of monitoring images; and the current scene mode is determined according to the light intensity.

10. A back-end image noise reduction device, characterized in that: The back-end image noise reduction device is a hard disk video recorder; the back-end image noise reduction device is connected to multiple front-end image acquisition devices via a coaxial line; the front-end image acquisition device is a CVI camera; including a receiving module and a noise reduction module; The receiving module is used to obtain the monitoring image collected by the front-end image acquisition device; The noise reduction module is configured to perform noise reduction on the surveillance image according to a current noise reduction parameter corresponding to the surveillance image, wherein the current noise reduction parameter is determined according to an environmental parameter of the surveillance image; The noise reduction of the surveillance image according to the current noise reduction parameters corresponding to the surveillance image includes: determining a current noise reduction level corresponding to the current scene mode according to a preset correspondence between the front-end image acquisition device, the current scene mode, and the noise reduction level, wherein the noise reduction level corresponds to a plurality of noise reduction parameters; and the current scene mode is determined according to light intensity; The noise reduction module is further configured to determine, when the current noise reduction level is different from the historical noise reduction level, a current noise reduction intensity corresponding to the current noise reduction level according to a mapping table, wherein the mapping table is configured to record mapping relationships between multiple noise reduction levels and noise reduction intensities.

11. A noise reduction device for monitoring images, characterized in that: It includes a front-end image acquisition device and a back-end image noise reduction device; the back-end image noise reduction device is connected to multiple front-end image acquisition devices via a coaxial line; the back-end image noise reduction device is a hard disk recorder; the front-end image acquisition device is a CVI camera; The front-end image acquisition device acquires a monitoring image and determines a current noise reduction parameter corresponding to the monitoring image according to the environmental parameters of the monitoring image; The environmental parameters include the light intensity during the acquisition of monitoring images; The front-end image acquisition device sends the monitoring image and the current noise reduction parameter to the back-end image noise reduction device; The back-end image noise reduction device performs noise reduction on the monitoring image according to the current noise reduction parameters; Noise reduction is performed on the surveillance image according to the current noise reduction parameters, including: determining a current noise reduction level corresponding to the current scene mode according to a preset correspondence between the front-end image acquisition device, the current scene mode, and the noise reduction level, wherein the noise reduction level corresponds to a plurality of noise reduction parameters; and the current scene mode is determined according to light intensity; When the current noise reduction level is different from the historical noise reduction level, the back-end image noise reduction device further determines the current noise reduction intensity corresponding to the current noise reduction level according to a mapping table, wherein the mapping table is used to record the mapping relationship between multiple noise reduction levels and noise reduction intensities.

12. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to execute the monitoring image noise reduction method according to any one of claims 1 to 7.

13. A storage medium, characterized in that The storage medium stores a computer program, wherein the computer program is configured to execute the steps of the monitoring image noise reduction method according to any one of claims 1 to 7 when running.

Images