Monitoring method and electronic equipment

Abstract

The invention provides a monitoring method and electronic equipment, the method is applied to image acquisition equipment, and the image acquisition equipment comprises a camera; the method comprises the following steps: acquiring a monitoring image acquired by the camera; determining a safety monitoring area of the image acquisition equipment based on the monitoring image; in response to the determination of the safety monitoring area, adjusting camera parameters of the camera so as to enable the depth-of-field range of the camera to be matched with the safety monitoring area; and controlling the camera to carry out monitoring according to the adjusted camera parameters. According to the method, the privacy protection in the monitoring scene is realized by utilizing the optical imaging characteristic, so that the privacy protection processing does not need to be performed on the monitoring image acquired by the camera subsequently, the computing resource of the equipment is effectively saved, and the power consumption of the system is reduced.

Description

Technical Field

[0001] This specification relates to the field of terminal technology, and in particular to a monitoring method and electronic device. Background Technology

[0002] In scenarios such as video surveillance, intelligent security, and image acquisition, privacy protection processing is usually performed on images captured by cameras in order to protect personal privacy. This includes processes such as occlusion, blurring, mosaicking, or other forms of privacy protection on privacy-protected areas or objects in the image, which results in a large computational burden on the device. Summary of the Invention

[0003] In view of this, this application provides a monitoring method and electronic device to at least partially solve the above-mentioned problems existing in the prior art.

[0004] According to a first aspect of the embodiments of this specification, a monitoring method is provided, applied to an image acquisition device, the image acquisition device including a camera; the method includes: Acquire the surveillance images captured by the camera; The security monitoring area of ​​the image acquisition device is determined based on the monitoring images; In response to the determination of the security monitoring area, the camera parameters of the camera are adjusted so that the depth range of the camera matches the security monitoring area; Control the camera to monitor according to the adjusted camera parameters.

[0005] According to a second aspect of the embodiments of this specification, a monitoring device is provided, the monitoring device comprising: The image acquisition unit is used to acquire the monitoring images captured by the camera; A region determination unit is used to determine the security monitoring area of ​​the image acquisition device based on the monitoring image; A parameter adjustment unit is used to adjust the camera parameters of the camera in response to the determination of the security monitoring area, so that the depth range of the camera matches the security monitoring area; The monitoring unit is used to control the camera to monitor according to the adjusted camera parameters.

[0006] According to a third aspect of the embodiments of this specification, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the monitoring method described above.

[0007] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the monitoring method described above.

[0008] According to a fifth aspect of the embodiments of this specification, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the monitoring method described above.

[0009] The technical solutions provided in the embodiments of this specification may include the following beneficial effects: In the embodiments described in this specification, after the security monitoring area is determined, the camera parameters can be automatically adjusted to match the camera's depth of field with the security monitoring area. Since the camera only captures images clearly within its depth of field, while images outside the depth of field are blurred, controlling the camera to monitor according to the adjusted camera parameters ensures that objects within the security monitoring area are clearly imaged, while objects outside the security monitoring area are naturally blurred. This method utilizes the characteristics of optical imaging to achieve privacy protection in the monitoring scenario, thus eliminating the need for subsequent privacy protection processing of the monitoring images captured by the camera. This effectively saves the device's computing resources, reduces system power consumption, and avoids the delay caused by image post-processing, significantly improving the real-time performance and response speed of the monitoring system.

[0010] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this specification. Attached Figure Description

[0011] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this specification and, together with the description, serve to explain the principles of this specification.

[0012] Figure 1 This is a flowchart illustrating a monitoring method according to an exemplary embodiment of this specification.

[0013] Figure 2 This is a schematic diagram illustrating a method for determining a security monitoring area according to an exemplary embodiment.

[0014] Figure 3 This is a schematic diagram illustrating a method for determining a security monitoring area according to an exemplary embodiment.

[0015] Figure 4 This is a schematic diagram illustrating a matching depth of field range and a security monitoring area according to an exemplary embodiment of this specification.

[0016] Figure 5This is a schematic diagram illustrating a matching depth of field range and a security monitoring area according to an exemplary embodiment of this specification.

[0017] Figure 6 This is a schematic diagram illustrating a matching depth of field range and a security monitoring area according to an exemplary embodiment of this specification.

[0018] Figures 7 to 16 This is a schematic diagram illustrating a surveillance image according to an exemplary embodiment of this specification.

[0019] Figure 17 This is a hardware structure diagram of an electronic device illustrated in this specification according to an exemplary embodiment.

[0020] Figure 18 This is a block diagram illustrating a monitoring device according to an exemplary embodiment of this specification. Detailed Implementation

[0021] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this specification. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this specification as detailed in the appended claims.

[0022] The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to be limiting of this specification. The singular forms “a,” “the,” and “the” as used in this specification and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0023] It should be understood that although the terms first, second, third, etc., may be used in this specification to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this specification, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0024] In one possible implementation, the monitoring method provided in the embodiments of this specification is executed by an electronic device. In some embodiments, the electronic device may be an image acquisition device, which may be any type of image acquisition device such as a smart door lock, indoor monitoring device, outdoor monitoring device, or smart access control system; the embodiments of this specification do not limit this. In some embodiments, the electronic device may be part of an image acquisition device; for example, the electronic device may be a processor in the image acquisition device, such as an MCU (Microcontroller Unit), SoC (System on Chip), DSP (Digital Signal Processor), or NPU (Neural Processing Unit).

[0025] Figure 1 This is a flowchart illustrating a monitoring method according to an exemplary embodiment. The subject executing this method can be an electronic device, which may be an image acquisition device or a part of an image acquisition device, such as a processor within the image acquisition device. Figure 1 As shown, the method includes: S101. Acquire the surveillance images captured by the camera.

[0026] Surveillance images are image data obtained by cameras capturing the current scene.

[0027] In some embodiments, the camera is always on, continuously capturing monitoring images. Accordingly, acquiring the monitoring images captured by the camera includes: acquiring the currently captured monitoring image by the camera. In some embodiments, to reduce power consumption, the camera is in a sleep or off state by default, only activating and capturing images when specific triggering conditions are met. Therefore, acquiring the monitoring images captured by the camera includes: waking up the camera in response to the security monitoring area setting function being triggered, and acquiring the monitoring image captured after the camera is turned on.

[0028] In some embodiments, in step S101 above, only one monitoring image captured by the camera is acquired to determine or assist in determining the security monitoring area. In some embodiments, in step S101 above, multiple consecutive monitoring images captured by the camera can be acquired, that is, a monitoring video segment captured by the camera is acquired.

[0029] S102. Determine the safe monitoring area of ​​the image acquisition device based on the monitoring image.

[0030] A security monitoring area is a specific area in a monitoring scenario that requires focused monitoring, and users expect this area to be clearly recorded by cameras. In some embodiments, this security monitoring area corresponds to areas related to security protection, such as the activity area within a certain space directly in front of electronic devices, doorways, corridors, the area around a crib, or the area around where valuables are stored.

[0031] In some possible implementations, the monitoring scenario may include a privacy protection area in addition to the security monitoring area. The privacy protection area refers to areas in the monitoring scenario that are not intended to be clearly recorded, for example, areas involving personal privacy or sensitive information. Examples include a neighbor's doorway, a neighbor's window, a changing room doorway, and a restroom doorway. Since the monitoring requirements for the security monitoring area and the privacy protection area differ—the former requires clear recording, while the latter requires avoiding clear recording—the security monitoring area and the privacy protection area do not overlap. Therefore, the privacy protection area can be identified first based on the monitoring image, and then the security monitoring area can be determined based on the privacy protection area.

[0032] The process of determining the security monitoring area of ​​the image acquisition device based on the surveillance images includes: determining the privacy protection area based on the surveillance images acquired by the camera, and determining the security monitoring area based on the determined privacy protection area, wherein the security monitoring area and the privacy protection area do not overlap.

[0033] The following embodiments of this specification provide an exemplary description of how to determine privacy-protected areas based on surveillance images: In some embodiments, objects in the monitoring scene that require privacy protection can be identified, and based on these objects, a privacy protection area can be determined so that the objects requiring privacy protection are not clearly recorded by the camera.

[0034] The process of determining privacy-protected areas based on surveillance images captured by cameras includes: identifying a first target object in the surveillance image, obtaining the identification result, and determining the privacy-protected area based on the identification result. The first target object is an object in the surveillance scene that is related to privacy protection. For example, the first target object could be a door, window, or similar object.

[0035] The reason why doors and windows are chosen as the primary target objects in this embodiment is that these objects are usually related to private living spaces and have a certain degree of privacy sensitivity. For example, if a camera captures a resident's front door when they enter or leave their home, it will not only capture images of neighbors, exposing their living habits and family members, but also capture some interior views when the door is open. Similarly, a camera may inadvertently capture images of a neighbor's home through a window. Therefore, in this embodiment, once a door or window is identified in the surveillance image, its location can be designated as a privacy protection zone to avoid collecting privacy-sensitive information.

[0036] The identification result can be used to indicate whether a first target object exists in the surveillance image, and, if the first target object exists in the surveillance image, its location information. In some embodiments, the identification result can also be used to indicate the type of the first target object. For example, performing first target object identification on a surveillance image can not only identify the first target object in the surveillance image, but also identify whether the first target object is a door or a window.

[0037] The identification of the first target object in the monitoring image can be achieved by a recognition model for identifying the first target object. This recognition model can be MobileNet-SSD (MobileNet Single Shot MultiBoxDetector, a single-shot multi-box target detector based on MobileNet), YOLO Tiny (a simplified version of YOLO), etc. The embodiments in this specification do not limit the recognition model.

[0038] Optionally, the privacy protection area is the spatial area where the first target object is located. Alternatively, the privacy protection area may include not only the spatial area where the first target object is located, but also the surrounding area. For example, the privacy protection area may include not only the spatial area where the first target object is located, but also at least one of the following: a portion of the area in front of the first target object, a portion of the area behind it, a portion of the area to its left, a portion of the area to its right, a portion of the area above it, and a portion of the area below it. By defining the spatial area where the first target object is located and the surrounding area as the privacy protection area, privacy protection can be better achieved, and the effectiveness of privacy protection can be improved.

[0039] In some embodiments, the privacy protection area can be user-defined. Determining the privacy protection area based on a surveillance image captured by a camera includes: displaying the surveillance image; and determining the user-annotated privacy protection area based on the user's annotation operation on the surveillance image.

[0040] The annotation operation can be a combination of any one or more operations, and the specific operation method of the annotation operation is not limited in the embodiments of this specification. For example, the annotation operation can be a selection operation, where the user can drag on the monitoring image to form a rectangle or other polygonal box, and the area enclosed by the rectangle or other polygonal box is the privacy protection area. For example, the annotation operation can be a smearing operation, where the user can directly smear on the monitoring image, and the smeared area is the privacy protection area.

[0041] It should be noted that the embodiments in this specification are merely illustrative of annotation operations and are not intended to limit them.

[0042] In some embodiments, the two methods for setting privacy protection areas described above can be combined. For example, an electronic device can identify a first target object in a surveillance image and display the identified first target object to the user. The user can choose which spatial areas containing the first target object are designated as privacy protection areas. Specifically, determining the privacy protection areas based on surveillance images captured by a camera includes: identifying the first target object in the surveillance image to obtain an identification result; displaying the identified first target object in the surveillance image based on the identification result; and determining the privacy protection areas based on the user's selection of the first target object in the surveillance image.

[0043] For example, by performing initial target object identification on a surveillance image, door 1, door 2, window 1, and window 2 are identified. These identified doors 1, 2, 1, and 2 are then highlighted in the surveillance image. A user observes the image and discovers that doors 1, 2, and 2 belong to their neighbor, while window 1 belongs to their own home. The user can then select doors 1, 2, and 2, defining the areas containing them as privacy protection zones.

[0044] For example, an electronic device can identify a first target object in a surveillance image and determine a privacy-protected area based on the identified first target object; it can then display the surveillance image and the determined privacy-protected area to the user, who can then delete or add to the privacy-protected area.

[0045] Optionally, determining a privacy-protected area based on a surveillance image captured by a camera includes: performing a first target object identification on the surveillance image to obtain an identification result; determining a privacy-protected area based on the identification result; displaying the determined privacy-protected area in the surveillance image; and determining an edited privacy-protected area based on the user's editing operation on the privacy-protected area in the surveillance image.

[0046] The editing operations may include deletion, addition, and modification operations, and the embodiments in this specification do not limit the editing operations. For example, the editing operation includes a deletion operation, which allows the user to reduce the automatically identified privacy protection area. For example, the editing operation includes an addition operation, which allows the user to add to the privacy protection area. For example, the editing operation includes a modification operation, which allows the user to expand or shrink the privacy protection area.

[0047] It should be noted that this instruction manual is only an illustrative example of the two methods of setting up privacy protection areas described above. Of course, other methods not mentioned in this instruction manual can also be used to determine privacy protection areas, and this instruction manual does not limit them.

[0048] In some embodiments, the security monitoring area is an area in the monitoring scene other than the privacy protection area. In some embodiments, the security monitoring area is the area between the image acquisition device and the privacy protection area in the monitoring scene. In some embodiments, the relationship between the security monitoring area and the privacy protection area may be different in different application scenarios, and the embodiments in this specification do not limit this.

[0049] Next, this specification will use the example of a security monitoring area being the area between an image acquisition device and a privacy protection area in a monitoring scenario to illustrate how to determine a security monitoring area based on a defined privacy protection area: In some possible implementations, the far boundary of the security monitoring area can be dynamically determined based on the location of the privacy protection area. Specifically, determining the security monitoring area based on the determined privacy protection area includes: determining the far boundary of the security monitoring area based on the physical distance between the privacy protection area and the image acquisition device; and determining the security monitoring area based on the far boundary.

[0050] For example, such as Figure 2 As shown, the monitoring area is a cone-shaped space determined by the camera's field of view. Within this monitoring area, the privacy protection zone is located at a distance from the image acquisition device, such as a neighbor's door, window, or door at the end of a stairwell. Based on the physical distance between the privacy protection zone and the image acquisition device, the farthest boundary of the security monitoring area can be determined. This ensures that when the camera's depth of field matches the security monitoring area, the privacy protection zone is outside the depth of field, resulting in blurred images of objects within the privacy protection zone.

[0051] The physical distance between the remote boundary and the image acquisition device can be equal to or slightly less than the physical distance between the privacy protection area and the image acquisition device, ensuring a certain distance between the remote boundary and the privacy protection area and better guaranteeing the privacy of the privacy protection area. After determining the remote boundary, the area between the image acquisition device and the remote boundary can be defined as the security monitoring area.

[0052] In some possible implementations, the imaging principle of a camera is similar to that of the human eye. Objects very close to the camera are often difficult to capture clearly, or even impossible to image, just as objects very close to the human eye are often difficult to see clearly. If a camera is to be able to clearly capture objects at very close range, a macro camera is required, which obviously increases the cost of the image acquisition equipment. If a macro camera is not used, the depth of field cannot cover areas very close to the image acquisition equipment, which may increase the difficulty of matching the camera's depth of field with the security monitoring area. Therefore, embodiments of this specification also provide a method for determining a security monitoring area, wherein the security monitoring area determined by this method does not include areas very close to the image acquisition equipment.

[0053] The process of determining a security monitoring area based on the established privacy protection area includes: determining the far boundary of the security monitoring area based on the physical distance between the privacy protection area and the image acquisition device; determining the near boundary of the security monitoring area based on a preset physical distance; and determining the security monitoring area based on the far boundary and the near boundary.

[0054] The preset physical distance can be any distance such as 10 cm, 20 cm, or 30 cm, and this embodiment does not limit the preset physical distance. This physical distance can be a system default value, a user-set distance, or a distance determined based on the actual application scenario; this embodiment does not limit it.

[0055] For example, such as Figure 3 As shown, the method for determining the far boundary can be referred to Figure 2 The near-end boundary is determined based on a preset physical distance; that is, the physical distance between the near-end boundary and the image acquisition device is this preset physical distance. The area between the near-end boundary and the far-end boundary is the security monitoring area.

[0056] In some embodiments, the near-end boundary is determined based on the camera's closest focusing distance. Within this near-end boundary, the camera cannot capture an image at all; therefore, the area within the near-end boundary can also be considered the camera's blind spot. The area within the near-end boundary refers to the region between the near-end boundary and the image acquisition device.

[0057] The following embodiments of this specification provide an exemplary description of how to determine the physical distance between the privacy protection area and the image acquisition device: In some possible implementations, the physical distance between the privacy-protected area and the image acquisition device can be determined based on the acquired surveillance images. Determining the physical distance between the privacy-protected area and the image acquisition device may include: calculating the physical distance between the privacy-protected area and the image acquisition device based on the visual information of the privacy-protected area in the surveillance image.

[0058] In some embodiments, the physical distance between a privacy protection area and an image acquisition device can be determined based on a surveillance image captured by a camera. The privacy protection area is the spatial region where the first target object is located; therefore, the physical distance between the privacy protection area and the image acquisition device can be determined by determining the physical distance between the first target object and the image acquisition device.

[0059] For example, calculating the physical distance between the privacy protection area and the image acquisition device based on the visual information of the privacy protection area in the surveillance image includes: determining the pixel height of the first target object corresponding to the privacy protection area in the surveillance image; determining the physical distance between the first target object and the image acquisition device based on the physical height of the first target object, the pixel height, and the focal length of the camera; and determining the physical distance between the privacy protection area and the image acquisition device based on the physical distance.

[0060] Since the primary target object is typically an object such as a door or window, and different types of doors and windows generally have relatively uniform heights but significant width differences. For example, besides the common single door, there are also double doors and mother-daughter doors, etc., which vary considerably in width but are typically around 2.05 meters in height. Similarly, windows can be single-pane, double-pane, or triple-pane, with varying widths but generally uniform heights of around 1.5 meters. Therefore, this embodiment calculates the physical distance between the primary target object and the image acquisition device based on the physical height and pixel height of the primary target object. The pixel height of the primary target object can be read from the monitoring image, and the physical height of the primary target object can be determined based on a preset value. For example, different types of primary target objects have pre-stored physical height values. For instance, the physical height of a door is preset to 2.05 meters, and the physical height of a window is preset to 1.5 meters. Therefore, based on the type of primary target object, the corresponding physical height can be found from the preset values.

[0061] In some embodiments, the principle of similar triangles can be used to calculate the physical distance between the first target object and the image acquisition device. Specifically, when the camera images the first target object, the optical path can approximately form two similar triangles. One triangle is formed by the physical height of the first target object and its distance from the camera, and the other triangle is formed by the pixel height of the first target object and the focal length of the camera. Based on the proportional relationship between the corresponding sides of the similar triangles, we can obtain: the physical distance between the first target object and the image acquisition device = (physical height of the first target object × focal length f of the camera) / pixel height of the first target object.

[0062] After determining the physical distance between the first target object and the image acquisition device, this physical distance can be directly used as the physical distance between the privacy protection area and the image acquisition device. Alternatively, after determining the physical distance between the first target object and the image acquisition device, this physical distance can be appropriately reduced to obtain the physical distance between the privacy protection area and the image acquisition device. For example, a preset value can be subtracted from the physical distance between the first target object and the image acquisition device to obtain the physical distance between the privacy protection area and the image acquisition device. For example, the physical distance between the first target object and the image acquisition device can be multiplied by a preset coefficient to obtain the physical distance between the privacy protection area and the image acquisition device.

[0063] In some embodiments, the physical distance between a privacy protection area and an image acquisition device can be determined based on surveillance images captured by two cameras, that is, by using the principle of binocular ranging to determine the physical relationship between the privacy protection area and the image acquisition device. The image acquisition device includes a first camera and a second camera. Calculating the physical distance between the privacy protection area and the image acquisition device based on the visual information of the privacy protection area in the surveillance images includes: obtaining parallax information of a first target object based on the surveillance images captured by the first and second cameras; determining the physical distance between the first target object and the image acquisition device based on the positional relationship between the first and second cameras, the focal lengths of the first and second cameras, and the parallax information; and determining the physical distance between the privacy protection area and the image acquisition device based on this physical distance.

[0064] The parallax information is used to represent the positional difference between the first target object in the monitoring image captured by the first camera and the monitoring image captured by the second camera. The positional relationship between the first camera and the second camera can be the distance between the centers of the first camera and the second camera.

[0065] It should be noted that the focal length of the first camera is the same as that of the second camera; therefore, the focal lengths of the first and second cameras are actually the same value.

[0066] For example, the relationship between the distance between the center of the first camera and the center of the second camera, the focal length of the first camera and the second camera, the parallax information, and the physical distance between the first target object and the image acquisition device is as follows: The physical distance between the first target object and the image acquisition device = the distance between the center of the first camera and the center of the second camera × the focal length / parallax information of the first and second cameras.

[0067] For example, when measuring the physical distance between a door handle and an image acquisition device, the door handle's position in the monitoring image captured by the first camera is x=300 pixels, and its position in the monitoring image captured by the second camera is x=260 pixels. Therefore, the parallax information = (300-260) pixels = 40 pixels. The distance between the centers of the first and second cameras is 6 centimeters, and the focal length is 600 pixels. In this case, the physical distance between the door handle and the image acquisition device = (6×600)÷40 = 90 centimeters. As another example, the door handle's position in the monitoring image captured by the first camera is x=300 pixels, and its position in the monitoring image captured by the second camera is x=295 pixels. Therefore, the parallax information = (300-295) pixels = 5 pixels. The distance between the centers of the first and second cameras is 6 centimeters, and the focal length is 600 pixels. In this case, the physical distance between the door handle and the image acquisition device = (6×600)÷5 = 720 centimeters = 7.2 meters.

[0068] In some embodiments, when the image acquisition device includes a first camera and a second camera, the first camera is configured with adjustable camera parameters, while the second camera is configured with non-adjustable camera parameters. The monitoring method provided in the embodiments of this specification can be used to adjust the camera parameters of the first camera to capture a clear monitoring image of the security monitoring area and a blurred image of the privacy protection area. The second camera can be configured to provide a clear image across the entire field of view. The monitoring image captured by the first camera can be stored for later review, while the monitoring image captured by the second camera is only used for some processing and is not stored.

[0069] In some possible implementations, the image acquisition device further includes a distance sensor. Determining the physical distance between the privacy protection area and the image acquisition device includes acquiring the physical distance between the privacy protection area and the image acquisition device using the distance sensor.

[0070] The distance sensor can be any type of sensor, such as a TOF (Time-of-Flight) sensor, an array radar, or an ultrasonic sensor. This specification does not limit the type of distance sensor in the embodiments.

[0071] The process of obtaining the physical distance between the privacy protection area and the image acquisition device using the distance sensor may include: obtaining a depth map of the monitoring scene based on the distance sensor; reading the depth value of the first target object from the corresponding position in the depth map based on the position of the first target object corresponding to the privacy protection area in the monitoring image; and determining the physical distance between the privacy protection area and the image acquisition device based on the depth value of the first target object.

[0072] The location of the first target object in the monitoring image can be a single point, such as the center point of the first target object, or a region. When the location of the first target object in the monitoring image refers to a region, multiple depth values ​​can be read from that region in the depth map, and the average or median of these multiple depth values ​​can be used as the depth value of the first target object.

[0073] In some possible implementations, the setting of the security monitoring area depends on the setting of the privacy protection area, and the user can set the security monitoring area separately. Specifically, determining the security monitoring area of ​​the image acquisition device based on the monitoring image includes: displaying a security monitoring area setting interface containing the monitoring image, and determining the security monitoring area based on the setting information input by the user.

[0074] In some embodiments, the security monitoring zone settings interface may include at least one of the following components: (1) Monitoring image display area. This monitoring image display area is used to display monitoring images captured by the camera.

[0075] (2) Area drawing control. This area drawing control allows users to directly draw security monitoring areas on the monitoring image.

[0076] For example, users can directly select a region on the monitoring image using a mouse or touch screen, and the selected region becomes the security monitoring area.

[0077] (3) Parameter Input Area. This parameter input area allows users to directly input the setting parameters of the security monitoring area, such as the far boundary of the security monitoring area and the size of the security monitoring area.

[0078] For example, the user enters a safety monitoring range of 3 meters in the parameter input area, which means that the far boundary of the safety monitoring area is 3 meters away from the image acquisition device.

[0079] When the security monitoring area settings interface includes an area drawing control, the user-inputted settings information can include the boundary information of the security monitoring area drawn by the user. When the security monitoring area settings interface includes a parameter input area, the user-inputted settings information can include the settings parameters entered by the user in the parameter input area.

[0080] In some embodiments, after a user enters setting information in the security monitoring area setting interface, the security monitoring area determined based on the setting information can be overlaid on the monitoring image so that the user can more intuitively understand the security monitoring area they have set.

[0081] S103. In response to the determination of the security monitoring area, adjust the camera parameters of the camera to match the depth range of the camera with the security monitoring area.

[0082] In some embodiments, after the image acquisition device is installed, the user can set a security monitoring area or a privacy protection area. The image acquisition device automatically determines the security monitoring area based on the privacy protection area. Once the security monitoring area is determined, the camera parameters are automatically adjusted to match the camera's depth of field with the current security monitoring area. That is, the security monitoring area is clear in the monitoring image captured by the camera, while other areas are blurred.

[0083] In the embodiments described in this specification, the security monitoring area is adjustable. Each time the security monitoring area is redefined, the camera parameters are automatically adjusted to match the depth range of the camera with the current security monitoring area.

[0084] In this context, matching the camera's depth of field with the security monitoring area can be achieved by aligning the camera's depth of field with the security monitoring area (for example, such as...). Figure 4 (As shown), or the depth of field of the camera can be slightly larger or smaller than the security monitoring area (for example, such as...). Figure 5 and 6 (As shown).

[0085] In some possible implementations, since adjusting the camera's focusing distance simultaneously affects both the physical spatial location and depth range of the camera's depth of field, that is, it affects both the location and size of the depth of field, the depth of field can be adjusted by adjusting the camera's focusing distance. Specifically, in response to the determination of the security monitoring area, adjusting the camera parameters includes: adjusting the camera's focusing distance based on the far and near boundaries of the security monitoring area, so that the physical spatial location corresponding to the camera's depth of field matches the physical spatial location of the security monitoring area, and the depth range of the camera's depth of field matches the depth range of the security monitoring area.

[0086] The physical spatial location corresponding to the depth of field range can refer to the physical spatial location of that depth of field range relative to the image acquisition device. Similarly, the physical spatial location of a security monitoring area can be the physical spatial location of that security monitoring area relative to the image acquisition device.

[0087] The depth range refers to the distance between the nearest and farthest points of focus captured by the camera. For example, if the camera captures a clear image in an area between 0.3 meters and 3 meters from the image acquisition device, but the image is blurry beyond 3 meters, then the depth range is (3-0.3) meters = 2.7 meters. This depth range is also the distance between the near and far boundaries of the depth of field.

[0088] When adjusting the focus distance of the camera according to the far and near boundaries of the security monitoring area, it is necessary to match the physical spatial location corresponding to the depth range of the camera with the physical spatial location of the security monitoring area as much as possible, and the depth range of the camera's depth range should match the depth range of the security monitoring area.

[0089] In some possible implementations, the greater the focusing distance, the farther the depth of field is from the image acquisition device, and the larger the depth of field range. Therefore, a relationship function between the focusing distance and the depth of field range can be preset. When adjusting the camera's focusing distance according to the far and near boundaries of the security monitoring area, the focusing distance can be calculated based on this relationship function, so that the depth of field range corresponding to the focusing distance matches the security monitoring area as closely as possible.

[0090] In some possible implementations, a mapping table can be pre-set, storing multiple correspondences between depth-of-field ranges and focusing distances. The depth-of-field range can be represented by its near and far boundaries. Each correspondence satisfies the following condition: when the camera uses a given focusing distance, its depth-of-field range is the corresponding depth-of-field range. Adjusting the camera's focusing distance based on the far and near boundaries of the security monitoring area includes: querying the pre-set mapping table based on the far and near boundaries of the security monitoring area to obtain a target focusing distance whose depth-of-field range matches the security monitoring area, and adjusting the camera's focusing distance to the target focusing distance.

[0091] In some possible implementations, changing the camera's focusing distance alters not only the position of the depth of field but also its size, potentially leading to difficulties in simultaneously achieving a good match between the position and size of the depth of field and the security monitoring area. Adjusting the camera's aperture and / or focal length can increase or decrease the depth of field without changing its position. Therefore, adjusting the camera's focusing distance can ensure a good match between the physical spatial position of the camera's depth of field and the physical spatial position of the security monitoring area, while appropriately sacrificing a good match between the depth range of the depth of field and the depth range of the security monitoring area. Then, adjusting the camera's aperture and / or focal length can further refine the match between the depth range of the camera and the depth range of the security monitoring area. This method further includes adjusting the camera's aperture and / or focal length based on the far and near boundaries of the security monitoring area to optimize the match between the depth range of the camera's depth of field and the depth range of the security monitoring area.

[0092] For example, when the depth range of the camera is greater than the depth range of the security monitoring area, the aperture and / or focal length can be increased to reduce the depth range; when the depth range of the camera is less than the depth range of the security monitoring area, the aperture and / or focal length can be decreased to increase the depth range.

[0093] It should be noted that in the embodiments of this specification, the focus distance of the camera can be adjusted first, and then the aperture and / or focal length can be adjusted according to the effect of the adjustment; alternatively, the focus distance and aperture / or focal length of the camera can be determined and adjusted simultaneously according to the far and near boundaries of the security monitoring area.

[0094] In some possible implementations, a mapping table can be pre-set, storing multiple correspondences between depth-of-field ranges and camera parameters, including focusing distance, aperture, and / or focal length. The depth-of-field range can be represented by its near and far boundaries. Each correspondence satisfies the following condition: when a camera uses these camera parameters, its depth-of-field range is the corresponding depth-of-field range. Based on the far and near boundaries of the security monitoring area, the pre-set mapping table is consulted to obtain the target camera parameters whose depth-of-field range matches the security monitoring area, and the camera parameters of the current camera are adjusted to match the target camera parameters.

[0095] In some possible implementations, considering that the setting of the security monitoring area is arbitrary, in practical applications, there may be situations where the depth of field range of the camera cannot match the security monitoring area. To improve the adaptability of this solution, this specification embodiment also provides a method, which further includes: if the depth of field range of the camera cannot match the security monitoring area after adjusting the camera parameters, then adjust the camera parameters of the camera according to the far boundary of the security monitoring area so that the depth of field range of the camera at least covers a portion of the security monitoring area adjacent to the far boundary; if a second target object appears in the monitoring scene, adjust the camera parameters of the camera according to the position of the second target object in the monitoring scene so that after the second target object enters the security monitoring area, the second target object is within the depth of field range of the camera.

[0096] In some embodiments, the second target object can be an object of a target category, such as a person, animal, or vehicle. In some embodiments, the second target object can be another user who is not a trusted user of the image acquisition device. For example, the image acquisition device is a door lock, and the second target object is someone other than a family member. Of course, the second target object can be flexibly set according to the actual application scenario, and the embodiments in this specification do not limit this.

[0097] For example, the security monitoring area is the region within 0.1 meters to 6 meters in front of the image acquisition device. If adjusting the camera parameters cannot control the depth of field within this range, the camera parameters can be adjusted based on the far boundary of the security monitoring area so that the far boundary of the depth of field is 6 meters. In this case, the depth of field is controlled within the region within N meters to 6 meters in front of the image acquisition device, where N is a value greater than 0.1 and less than 6. This value of N is determined by the various camera parameters used, and specific values ​​are not provided here.

[0098] If a second target object appears in the monitoring scene, and if the second target object does not enter the security monitoring area, the camera parameters do not need to be adjusted. If the second target object enters the security monitoring area and moves within N meters to 6 meters in front of the image acquisition device, the camera parameters also do not need to be adjusted. If the second target object is close to within N meters in front of the image acquisition device, the camera parameters can be adjusted so that the second target object is always within the depth of field of the camera when it is moving within the security monitoring area. That is, the second target object is always clearly captured when it is moving within the security monitoring area.

[0099] It should be noted that when adjusting the camera parameters based on the location of the second target object in the monitoring scene, if there is a privacy protection area, the depth of field will still not cover the privacy protection area.

[0100] Another point to note is that the embodiments in this specification only illustrate the timing of adjusting camera parameters by taking the second target object near the near edge of the depth of field as an example. Of course, the camera parameters can also be adjusted when the second target object is located at the center of the depth of field; or when the second target object is M meters away from the near edge of the depth of field. The embodiments in this specification do not limit the timing. Wherein, M is any value.

[0101] S104. Control the camera to monitor according to the adjusted camera parameters.

[0102] In some embodiments, the camera can be in a constantly on state, that is, the camera is controlled to continuously monitor according to the adjusted camera parameters. In some embodiments, the camera is in a sleep or off state by default, and the controller only starts and monitors when specific trigger conditions are met.

[0103] For example, the image acquisition device also includes a distance sensor. The distance sensor performs object recognition on the monitored scene to obtain a recognition result; based on the recognition result, it controls the working state of the camera. When the distance sensor's recognition result is a target recognition result, it controls the camera to turn on and monitor according to the adjusted camera parameters. For example, the target recognition result could be the presence of a person in the monitored area, a person approaching the security monitoring area, or a person entering the security monitoring area. This embodiment does not limit the target sensing result.

[0104] For example, the image acquisition device includes two cameras, a first camera and a second camera. The first camera is configured with adjustable parameters, while the second camera is configured with non-adjustable parameters. The monitoring method provided in the embodiments of this specification can be used to adjust the camera parameters of the first camera to capture a clear monitoring image of the security monitoring area and a blurred image of the privacy protection area. The second camera can be configured to provide a clear image across the entire field of view. The second camera can be in a constantly active state, and the monitoring image captured by the second camera can be used to identify a second target object. Based on the identification result, it can be determined whether to activate the first camera.

[0105] The surveillance images captured by the first camera can be stored for later review. The surveillance images captured by the second camera are only used for processing and are not stored.

[0106] In some possible implementations, while the camera is monitoring according to the adjusted camera parameters, an alarm can be issued at an appropriate time based on the monitoring results to further enhance security. The security monitoring area is defined by a near-end boundary and a far-end boundary. The method also includes issuing an alarm in response to a second target object entering within the near-end boundary.

[0107] The area within the near-end boundary refers to the region between the image acquisition device and the near-end boundary. The second target can be anyone other than a trusted person using the image acquisition device. Therefore, if the second target gets too close to the image acquisition device, a security risk exists, and the image acquisition device will issue an alarm.

[0108] In some embodiments, the determination range of the second target object may differ in different scenarios. For example, when any object avoids the camera's shooting angle and suddenly appears within the near-end boundary, no object identification is required, and an alarm is issued directly. When any object does not avoid the camera's shooting angle and gradually approaches the image acquisition device within the camera's field of view, it can be identified whether the object is a trusted person of the image acquisition device. If not, an alarm is issued when the object enters the near-end boundary.

[0109] In the embodiments described in this specification, after the security monitoring area is determined, the camera parameters can be automatically adjusted to match the camera's depth of field with the security monitoring area. Since the camera only captures images clearly within its depth of field, while images outside the depth of field are blurred, controlling the camera to monitor according to the adjusted camera parameters ensures that objects within the security monitoring area are clearly imaged, while objects outside the security monitoring area are naturally blurred. This method utilizes the characteristics of optical imaging to achieve privacy protection in the monitoring scenario, thus eliminating the need for subsequent privacy protection processing of the monitoring images captured by the camera. This effectively saves the device's computing resources, reduces system power consumption, and avoids the delay caused by image post-processing, significantly improving the real-time performance and response speed of the monitoring system.

[0110] It should be noted that the monitoring methods provided in this manual have good monitoring effects in both single-person and multi-person scenarios.

[0111] For example, when the depth of field of the camera matches the security monitoring area, if a user enters the monitoring area of ​​the image acquisition device, and if the user is outside the security monitoring area, that is... Figure 7If the user is at position 1, then the user is also outside the camera's depth of field. Since areas within the depth of field are sharp while other areas are blurred in the camera's captured image, when the user is outside the security monitoring area, the user appears blurred in the camera's captured image, satisfying privacy protection requirements and eliminating the need for privacy processing of the captured image. If the user is within the security monitoring area, that is... Figure 7 If the user is at position 2, then the user is also within the depth of field of the camera. The user is clear in the monitoring image captured by the camera, which meets the monitoring requirements and there is no need to perform privacy protection processing on the monitoring image captured by the camera.

[0112] For example, when the depth of field of the camera matches the security monitoring area, if multiple users enter the monitoring area of ​​the image acquisition device, or if all users are outside the security monitoring area, such as... Figure 8 As shown, if all users are outside the camera's depth of field, the entire user image captured by the camera will be blurred, meeting privacy protection requirements, and no privacy protection processing is needed for the captured images. However, if some users are outside the security monitoring area and some are within it, such as... Figure 9 As shown, users located outside the security monitoring area are also outside the depth of field, and these users are blurred in the camera's captured images, meeting the privacy protection requirement. Users located within the security monitoring area are also within the depth of field, and these users are clear in the camera's captured images, meeting the monitoring requirement. Therefore, the camera's captured images meet both monitoring and privacy protection requirements, eliminating the need for further privacy protection processing. If all users are within the security monitoring area, such as... Figure 10 As shown, all these users are within the camera's depth of field, and the users are clear in the surveillance images captured by the camera, thus meeting the monitoring requirements. At the same time, there is no need to perform privacy protection processing on these users.

[0113] For example, when the depth of field of the camera cannot match the security monitoring area, the depth of field of the camera covers a portion of the security monitoring area near the far boundary, such as... Figure 11 As shown. If a user enters the monitoring area of ​​the image acquisition device, and if the user is outside the security monitoring area, such as... Figure 11 As shown, the user is also outside the camera's depth of field. In the surveillance image captured by the camera, the user is blurred, meeting the privacy protection requirements, and no privacy protection processing is needed for the camera's captured image. Then, the user continues to approach the image acquisition device, entering the security monitoring area through the far boundary of the security monitoring area, as shown... Figure 12 As shown. Because the depth of field covers a portion of the area near the far boundary of the security monitoring zone, the user is also within the camera's depth of field. The user is clearly visible in the captured image, meeting the monitoring requirements, and there is no need for privacy protection processing of the captured image. Then, as the user continues to approach the image acquisition device, the device adjusts its camera parameters based on the user's position within the monitored scene, ensuring that the user remains within the camera's depth of field throughout their activities within the security monitoring area. Figure 13 As shown. In this way, the user can be clearly monitored while active within the security monitoring area, and since the depth of field does not exceed the security monitoring area, there is no need to perform privacy protection processing on the monitoring images.

[0114] For example, when the depth of field of the camera cannot match the security monitoring area, the camera's depth of field covers a portion of the security monitoring area near the far boundary. If multiple users enter the monitoring area of ​​the image acquisition device, or if all users are outside the security monitoring area, such as... Figure 14 As shown, since these users are all outside the camera's depth of field, all users in the camera's captured surveillance image are blurred, meeting privacy protection requirements, and no privacy protection processing is needed for the camera's captured surveillance image. However, if at least some of these users continue to approach the image acquisition device and enter the security monitoring area through the far boundary of the security monitoring area, such as... Figure 15 As shown. Because the depth of field covers a portion of the area near the far boundary of the security monitoring zone, users entering the security monitoring zone are within the camera's depth of field. Users within the security monitoring zone are clear in the captured image, while users outside the security monitoring zone are blurred, thus satisfying both monitoring and privacy protection requirements without the need for further privacy processing. Then, as some users continue to approach the image acquisition device, the device adjusts its camera parameters based on the location of the nearest user within the monitoring scene, ensuring that the nearest user remains within the camera's depth of field. Figure 16 As shown. This ensures that users who pose a potential security threat (i.e., those closest to the image acquisition device) are always clearly imaged.

[0115] It should be noted that, Figures 7 to 16 This example only illustrates single-person and multi-person scenarios, and therefore only describes how the user appears in the monitoring image. In reality, all objects outside the security monitoring area are blurred or out of focus, ensuring the privacy of the privacy protection area.

[0116] Corresponding to the embodiments of the aforementioned methods, this specification also provides embodiments of the monitoring device and the terminal to which it is applied.

[0117] The embodiments of the monitoring device described in this specification can be applied to electronic devices, such as servers or terminal devices. The device embodiments can be implemented through software, hardware, or a combination of both. Taking software implementation as an example, as a logical device, it is formed by the processor related to the monitoring loading the corresponding computer program instructions from non-volatile memory into memory for execution. From a hardware perspective, such as... Figure 17 The diagram shown is a hardware structure diagram of an electronic device containing the monitoring device in an embodiment of this specification. Except for... Figure 17 In addition to the processor 1710, memory 1730, network interface 1720, and non-volatile memory 1740 shown, the server or electronic device where the monitoring device is located in the embodiment may also include other hardware depending on the actual function of the electronic device, which will not be described in detail here.

[0118] like Figure 18 As shown, Figure 18 This is a block diagram illustrating a monitoring device according to an exemplary embodiment of this specification, the device comprising: The image acquisition unit 1801 is used to acquire the monitoring images captured by the camera. The area determination unit 1802 is used to determine the security monitoring area of ​​the image acquisition device based on the monitoring image; The parameter adjustment unit 1803 is used to adjust the camera parameters of the camera in response to the determination of the security monitoring area, so that the depth range of the camera matches the security monitoring area; The monitoring unit 1804 is used to control the camera to monitor according to the adjusted camera parameters.

[0119] In some possible implementations, the area determination unit 1802 is configured to determine a privacy protection area based on the surveillance image captured by the camera, and to determine the security monitoring area based on the determined privacy protection area, wherein the security monitoring area does not overlap with the privacy protection area; and / or, The area determination unit 1802 is used to display a security monitoring area setting interface containing the monitoring image, and to determine the security monitoring area based on the setting information input by the user.

[0120] In some possible implementations, the region determination unit 1802 is configured to perform at least one of the following: The monitoring image is subjected to first target object recognition to obtain recognition results, and the privacy protection area is determined based on the recognition results; The monitoring image is displayed, and the privacy protection area marked by the user is determined based on the user's annotation operation on the monitoring image; The monitoring image is subjected to first target object recognition to obtain recognition results; based on the recognition results, the recognized first target object is displayed in the monitoring image; based on the user's selection operation of the first target object in the monitoring image, a privacy protection area is determined. The first target object is an object related to privacy protection in the monitoring scenario.

[0121] In some possible implementations, the region determination unit 1802 is used to determine the far boundary of the security monitoring area based on the physical distance between the privacy protection area and the image acquisition device; determine the near boundary of the security monitoring area based on a preset physical distance; and determine the security monitoring area based on the far boundary and the near boundary.

[0122] In some possible implementations, the region determination unit 1802 is configured to perform any of the following: Based on the visual information of the privacy protection area in the monitoring image, the physical distance between the privacy protection area and the image acquisition device is calculated. The image acquisition device also includes a distance sensor; the distance sensor is used to obtain the physical distance between the privacy protection area and the image acquisition device.

[0123] In some possible implementations, the parameter adjustment unit 1803 is used to adjust the focusing distance of the camera according to the far boundary and near boundary of the security monitoring area, so that the physical spatial position corresponding to the depth range of the camera matches the physical spatial position of the security monitoring area, and the depth range of the depth range of the camera matches the depth range of the security monitoring area.

[0124] In some possible implementations, the parameter adjustment unit 1803 is further configured to adjust the aperture and / or focal length of the camera according to the far boundary and near boundary of the security monitoring area, so as to optimize the matching relationship between the depth range of the camera's depth of field and the depth range of the security monitoring area.

[0125] In some possible implementations, the parameter adjustment unit 1803 is further configured to, if adjusting the camera parameters of the camera results in the depth-of-field range of the camera not matching the security monitoring area, adjust the camera parameters of the camera according to the far boundary of the security monitoring area so that the depth-of-field range of the camera at least covers a portion of the security monitoring area adjacent to the far boundary; and, if a second target object appears in the monitoring scene, adjust the camera parameters of the camera according to the position of the second target object in the monitoring scene so that after the second target object enters the security monitoring area, the second target object is located within the depth-of-field range of the camera.

[0126] In some embodiments, the security monitoring area is defined by a near-end boundary and a far-end boundary; An alarm unit is used to issue an alarm in response to a second target object entering the near-end boundary.

[0127] The specific implementation process of the functions and roles of each module in the above device can be found in the implementation process of the corresponding steps in the above method, and will not be repeated here.

[0128] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of the solution in this specification according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0129] Accordingly, this specification also provides an electronic device, the device including a processor; a memory for storing processor-executable instructions; wherein the processor is configured to perform the steps in the above-described monitoring method.

[0130] Accordingly, this specification also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the monitoring method described above.

[0131] Accordingly, this specification also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the monitoring method described above.

[0132] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0133] Other embodiments of this specification will readily occur to those skilled in the art upon consideration of the specification and practice of the invention claimed herein. This specification is intended to cover any variations, uses, or adaptations that follow the general principles of this specification and include common knowledge or customary techniques in the art not claimed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this specification are indicated by the following claims.

[0134] It should be understood that this specification is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this specification is limited only by the appended claims.

[0135] The above description is merely a preferred embodiment of this specification and is not intended to limit this specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification should be included within the scope of protection of this specification.

Claims

1. A monitoring method, characterized in that, The method is applied to an image acquisition device, the image acquisition device including a camera; the method includes: Acquire the surveillance images captured by the camera; The security monitoring area of ​​the image acquisition device is determined based on the monitoring images; In response to the determination of the security monitoring area, the camera parameters of the camera are adjusted so that the depth range of the camera matches the security monitoring area; Control the camera to monitor according to the adjusted camera parameters.

2. The method according to claim 1, characterized in that, Determining the security monitoring area of ​​the image acquisition device based on the monitoring image includes: Based on the surveillance images captured by the camera, a privacy protection area is determined; based on the determined privacy protection area, a security monitoring area is determined, wherein the security monitoring area does not overlap with the privacy protection area; and / or, The system displays a security monitoring area setting interface that includes the surveillance images, and determines the security monitoring area based on the setting information input by the user.

3. The method according to claim 2, characterized in that, The determination of privacy-protected areas based on the surveillance images captured by the camera includes any one of the following: The monitoring image is subjected to first target object recognition to obtain recognition results, and the privacy protection area is determined based on the recognition results; The monitoring image is displayed, and the privacy protection area marked by the user is determined based on the user's annotation operation on the monitoring image; The monitoring image is subjected to first target object recognition to obtain the recognition result; Based on the recognition results, the first target object identified is displayed in the monitoring image; Based on the user's selection of a first target object in the monitoring image, a privacy protection area is determined; The first target object is an object related to privacy protection in the monitoring scenario.

4. The method according to claim 2, characterized in that, The determination of the security monitoring area based on the determined privacy protection area includes: The far boundary of the security monitoring area is determined based on the physical distance between the privacy protection area and the image acquisition device; The near-end boundary of the security monitoring area is determined based on a preset physical distance; The security monitoring area is determined based on the far boundary and the near boundary.

5. The method according to claim 4, characterized in that, Determining the physical distance between the privacy protection area and the image acquisition device includes any one of the following: Based on the visual information of the privacy protection area in the monitoring image, the physical distance between the privacy protection area and the image acquisition device is calculated. The image acquisition device also includes a distance sensor; the distance sensor is used to obtain the physical distance between the privacy protection area and the image acquisition device.

6. The method according to claim 1, characterized in that, In response to the determination of the security monitoring area, adjusting the camera parameters of the camera includes: Based on the far and near boundaries of the security monitoring area, the focusing distance of the camera is adjusted so that the physical spatial location corresponding to the depth range of the camera matches the physical spatial location of the security monitoring area, and the depth range of the camera's depth range matches the depth range of the security monitoring area.

7. The method according to claim 6, characterized in that, The method further includes: Based on the far and near boundaries of the security monitoring area, adjust the aperture and / or focal length of the camera to optimize the matching relationship between the depth range of the camera and the depth range of the security monitoring area.

8. The method according to claim 1, characterized in that, The method further includes: If the depth of field of the camera cannot be matched with the security monitoring area after adjusting the camera parameters, then the camera parameters of the camera are adjusted according to the far boundary of the security monitoring area so that the depth of field of the camera at least covers a part of the security monitoring area adjacent to the far boundary. If a second target object appears in the monitoring scene, the camera parameters of the camera are adjusted according to the position of the second target object in the monitoring scene so that after the second target object enters the security monitoring area, the second target object is within the depth range of the camera.

9. The method according to claim 1, characterized in that, The security monitoring area is defined by a near-end boundary and a far-end boundary; the method further includes: issuing an alarm in response to a second target object entering the near-end boundary.

10. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the method as described in any one of claims 1 to 9.

Images