Image processing methods and electronic devices

Abstract

This application provides an image processing method and an electronic device. The method includes: acquiring a target image captured by an image acquisition device; performing human body recognition on the target image to obtain a human body recognition result; determining the positional relationship of the identified human body relative to a privacy protection area and a key monitoring area based on the human body recognition result; determining a processing strategy for the target image based on the positional relationship; and processing the target image according to the processing strategy. This method determines the image processing strategy based on the positional relationship of the human body in the image relative to the privacy protection area and the key monitoring area, ensuring that the processed image meets both privacy protection and key monitoring requirements. This avoids the loss of critical information during privacy protection processing and improves the system's reliability and event tracing capabilities.

Description

[0001] This application is a divisional application of the invention patent application filed on February 4, 2026, with application number 202610156795.8 and entitled "Image Processing Method and Electronic Device". Technical Field

[0002] This application relates to the field of image processing technology, and in particular to an image processing method and electronic device. Background Technology

[0003] Image acquisition devices are widely used in daily life, particularly in video surveillance, smart security, and image acquisition scenarios. To reduce power consumption and improve the effectiveness of event recording, existing image acquisition devices are typically equipped with sensing units. Their working principle is usually as follows: a sensing area is pre-defined; when the sensing unit detects a target object within that area, the system activates the image acquisition device to start and acquire images.

[0004] In real-world surveillance scenarios, in addition to key monitoring areas requiring security protection, the areas covered by image acquisition equipment are typically designated as privacy protection zones to safeguard personal privacy. These privacy protection zones generally correspond to areas involving sensitive information, such as entrances to residences, windows, changing room entrances, and restroom entrances. After designating privacy protection zones, the system applies privacy protection processing such as occlusion, blurring, mosaicking, or other methods to the corresponding image areas to meet privacy protection requirements.

[0005] However, in practical applications, it has been found that when a user is not located in the privacy protection area, but the image corresponding to the user overlaps with the image corresponding to the privacy protection area, the image corresponding to the user will also be processed for privacy protection, which will lead to the loss of key information in the captured image and affect the reliability of the system and the ability to trace events.

[0006] To avoid privacy violations and reduce invalid triggers, it's typically necessary to adjust the coverage area of ​​the sensing zone to avoid various privacy-protected areas as much as possible. However, when there are many of these privacy-protected areas and they are scattered throughout the core monitoring area, no matter how the size and orientation of the sensing zone are adjusted, it's difficult for a single sensing zone to completely avoid all privacy-protected areas. This means that even if a target is moving normally within a privacy-protected area, the sensing unit may still be triggered, unnecessarily waking up the image acquisition device. This not only increases invalid monitoring but also further increases the risk of privacy leaks. Summary of the Invention

[0007] In view of this, this application provides an image processing method and an electronic device to at least partially solve the above-mentioned problems existing in the prior art.

[0008] Specifically, this application is implemented through the following technical solution: This application provides an image processing method, the method comprising: Acquire a target image captured by an image acquisition device, perform human body recognition on the target image, and obtain human body recognition results; Based on the human body recognition results, the positional relationship of the identified human body relative to the privacy protection area and the key monitoring area is determined; Based on the positional relationship, determine the processing strategy for the target image; The target image is processed according to the processing strategy.

[0009] This application embodiment also provides an image processing apparatus, the apparatus comprising: An image acquisition unit is used to acquire a target image acquired by an image acquisition device, perform human body recognition on the target image, and obtain a human body recognition result. The positional relationship determination unit is used to determine the positional relationship of the identified human body relative to the privacy protection area and the key monitoring area based on the human body recognition result; A processing strategy determination unit is used to determine the processing strategy of the target image based on the positional relationship. The processing unit is used to process the target image according to the processing strategy.

[0010] This application also provides an electronic device, 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 image processing method described above.

[0011] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the image processing method described above.

[0012] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the image processing method described above.

[0013] The image processing method provided in this application determines the image processing strategy based on the positional relationship between the human body in the image and the privacy protection area and the key monitoring area. This ensures that the processed image meets both privacy protection and key monitoring requirements, avoids the loss of key information during privacy protection processing, and improves the system's reliability and event tracing capabilities.

[0014] The sensing area is determined by both the sensing angle and sensing distance of the sensing unit. By flexibly configuring these two parameters, the sensing area can be divided into multiple continuous or spaced-out angular segments, ensuring that each segment covers both the key monitoring area and completely avoids all privacy-protected areas. Even if multiple discrete privacy areas exist within the area covered by the image acquisition device, this configuration effectively prevents the sensing area from overlapping with any privacy area. In this way, when a target object appears at any location within any privacy area, the sensing unit will not be triggered, and the image acquisition device will not be unnecessarily activated, significantly reducing the amount of footage taken of privacy areas and further lowering the risk of privacy breaches. Attached Figure Description

[0015] Figure 1 This is a schematic diagram illustrating an implementation environment as shown in an exemplary embodiment of this application.

[0016] Figure 2 This is a schematic flowchart illustrating an image processing method according to an exemplary embodiment of this application.

[0017] Figure 3 This is a schematic diagram illustrating an exemplary embodiment of the present application of a sensing area.

[0018] Figure 4 This is a schematic diagram illustrating an exemplary embodiment of the present application of a sensing area.

[0019] Figure 5 This is a schematic flowchart illustrating an image processing method according to an exemplary embodiment of this application.

[0020] Figure 6 This is a schematic diagram illustrating a processed target image according to an exemplary embodiment of this application.

[0021] Figure 7 This is a schematic diagram of the structure of an image processing apparatus according to an exemplary embodiment of this application.

[0022] Figure 8 This is a schematic diagram of the structure of an electronic device shown in an exemplary embodiment of this application. Detailed Implementation

[0023] 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 numbers 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 application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0024] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application 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 or all possible combinations of one or more of the associated listed items.

[0025] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such 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 application, 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."

[0026] In one possible implementation, the image processing method provided in this application is executed by an electronic device. This electronic device may include an image acquisition device, or it may be itself an image acquisition device, or it may be connected to an image acquisition device and capable of acquiring images acquired by the image acquisition device. In some embodiments, the electronic device may be a smart door lock, monitoring equipment, smart home device, mobile phone, tablet, computer, etc., and this disclosure does not limit the type of electronic device. Of course, the electronic device may also be other types of devices not mentioned in this application.

[0027] Figure 1 This is a schematic diagram of an implementation environment provided in an embodiment of this application, such as... Figure 1 As shown, the implementation environment includes an electronic device 101 and a server 102. A communication connection is established between the electronic device 101 and the server 102. This communication connection can be a wired communication connection or a wireless communication connection. This application embodiment does not limit this.

[0028] In one embodiment, server 102 is a service provider for electronic device 101. For example, electronic device 101 is a smart lock, and server 102 is a cloud server for the smart lock.

[0029] In another embodiment, a target application provided by server 102 is installed on electronic device 101. Electronic device 101 can perform functions such as data transmission and message interaction through this target application. Optionally, the target application can be a target application within the operating system of electronic device 101, or a target application provided by a third party. For example, the target application can be a monitoring application, a door lock management application, etc. This application embodiment does not limit the target application. The target application has monitoring functions; of course, the target application can also have other functions, such as management functions and setting functions.

[0030] Optionally, electronic device 101 can be a smart door lock, indoor monitoring equipment, garage monitoring equipment, street monitoring equipment, factory monitoring equipment, or other types of equipment. Optionally, server 102 can be a backend server for electronic device 101 or a cloud server providing cloud computing and cloud storage services.

[0031] In one embodiment, server 102 is used to receive and store images captured by electronic device 101. These images may be images that have undergone privacy protection processing; alternatively, they may be images that have not undergone privacy protection processing, in which case server 102 performs privacy protection processing and stores the privacy-protected images.

[0032] It should be noted that the image processing method provided in this application embodiment can be completed independently by the electronic device 101, or it can be completed by the electronic device 101 and the server 102 in cooperation. This application embodiment does not impose any restrictions on this. Furthermore, when the image processing method provided in this application embodiment is completed by the electronic device 101 and the server 102 in cooperation, this application embodiment does not limit which specific steps are performed by the electronic device 101 and the server 102.

[0033] Figure 2 This is a flowchart of an image processing method provided in an embodiment of this application. The subject executing this method can be an electronic device, which may include an image acquisition device. Figure 2 As shown, the method includes: Step S201: Acquire the target image captured by the image acquisition device, perform human body recognition on the target image, and obtain the human body recognition result.

[0034] The image acquisition device can be any device with image acquisition capabilities, such as a smart lock, a camera within a smart lock, or a surveillance device. This application does not limit the type of image acquisition device. The target image can be any image acquired by the image acquisition device. In some embodiments, the acquisition range of the image acquisition device includes areas requiring privacy protection. For example, the acquisition range of the image acquisition device may include the area near a neighbor's door.

[0035] In some embodiments, the timing for acquiring the target image captured by the image acquisition device may be: acquiring the target image in response to the image acquisition device completing the acquisition of a target image; or it may be obtaining the target image by extracting images from images continuously acquired by the image acquisition device. This disclosure does not limit the timing of acquiring the target image captured by the image acquisition device.

[0036] In some possible implementations, the image acquisition device may continuously acquire images without relying on any triggering conditions. In some possible implementations, the image acquisition device relies on triggering conditions and acquires images when the triggering conditions are met. In some embodiments, the image acquisition device includes a sensing unit. The method further includes: controlling the image acquisition device to acquire images in response to the sensing unit detecting a target object within a sensing area.

[0037] The sensing unit is used to sense whether a target object is approaching the image acquisition device. The target object can be any object; for example, it can be a physical object such as a person, animal, vehicle, or package, or an abstract signal such as sound, light, or temperature, or other perceptible or detectable things. This application embodiment does not limit the type of target object. In some embodiments, the sensing unit can be any sensing device such as radar, infrared sensor, or sound sensor; this application embodiment does not limit the sensing unit.

[0038] In some embodiments, the sensing unit may or may not distinguish between objects approaching the image acquisition device. For example, the sensing unit may distinguish between objects approaching the image acquisition device; when the sensing unit detects an animal within the sensing area, it does not control the image acquisition device to acquire an image; when the sensing unit detects a person within the sensing area, it controls the image acquisition device to acquire an image. Alternatively, the sensing unit may not distinguish between objects approaching the image acquisition device; when the sensing unit detects any object within the sensing area, it controls the image acquisition device to acquire an image.

[0039] In some embodiments, the sensing area is determined by the capabilities or physical characteristics of the sensing unit itself.

[0040] In some embodiments, the sensing area is set by the user. This allows the user to customize the sensing area according to actual needs, making the configuration of the sensing area more flexible and better adaptable to usage requirements in different environments.

[0041] Optionally, the sensing area is determined by the sensing angle and sensing distance of the sensing unit. The user can configure the sensing area by configuring the sensing angle and / or sensing distance of the sensing unit. The method further includes: displaying a setting interface for the sensing area; determining the sensing angle and / or sensing distance of the sensing unit based on the setting interface; and determining the sensing area based on the sensing angle and / or sensing distance of the sensing unit. The sensing angle of the sensing unit can be configured as multiple angle segments or as a single angle segment. When the sensing angle of the sensing unit is configured as multiple angle segments, there are intervals between these multiple angle segments. In some embodiments, the intervals between the multiple angle segments are set by the user based on the layout of the privacy protection area within the acquisition range of the image acquisition device. Therefore, the intervals between the multiple angle segments can be the same or different, and this application embodiment does not impose any limitations on this.

[0042] The settings interface provides various settings options for users to configure the sensing area. For example, users can directly specify the start and end range of the sensing angle and / or the sensing distance through input boxes; alternatively, users can intuitively adjust the sensing area by dragging, scaling, or moving the boundary lines of the sensing area. These settings options can be provided individually or in combination, and this embodiment does not impose any limitations on this.

[0043] Optionally, when displaying the settings interface for the sensing area, an image captured by the image acquisition device can be displayed in the settings interface, and a visual identifier (such as a highlighted area, mask, outline, etc.) representing the sensing area can be overlaid on the image to intuitively present the currently configured sensing area. By aligning the sensing area with the actual scene image, users can more accurately determine the spatial location and coverage of the sensing area, thereby improving the accuracy and efficiency of the sensing area configuration.

[0044] For example, when the sensing angle of the sensing unit is configured to be an angle segment, it can be as follows: Figure 3 As shown. Figure 3 In the diagram, the solid-lined sector represents the initial sensing area of ​​the sensing unit. Users can move the radius and arc of the sensing area to adjust the sensing angle by moving the radius and the sensing distance by moving the arc. Figure 3 The radius of the dashed line is used to represent the radius after the user moves. Figure 3 The dashed arc in the diagram represents the arc after the user moves, and the dashed sector area formed by the dashed radius and the dashed arc represents the sensing area configured by the user.

[0045] For example, when the sensing angle of the sensing unit is configured into multiple angle segments, it can be as follows: Figure 4As shown, the solid-lined sector represents the initial sensing area of ​​the sensing unit, the dotted-line box represents the privacy protection area, the dashed-line box represents the key monitoring area, and the dashed-lined sector represents the user-configured sensing area. Users can set the sensing angle and distance of the sensing unit according to the locations of the privacy protection area and the key monitoring area, so that the sensing area includes the key monitoring area but excludes the privacy protection area. Figure 4 As shown, the user configures the sensing angle of the sensing unit to two angle segments, so that the sensing areas corresponding to the two angle segments are located on either side of the privacy protection area, thus avoiding the privacy protection area in the middle of the initial sensing area. In this way, when someone appears in the privacy protection area, it will not trigger the image acquisition device to capture an image, nor will it perform image processing. This protects the privacy of the privacy protection area while eliminating the need for image processing.

[0046] It should be noted that the sensing area of ​​the sensing unit is actually a three-dimensional spatial region. Figure 3 and Figure 4 Using a top-down view as an example, the coverage area of ​​the sensing zone and its relative position to the privacy protection zone and the key monitoring zone are illustrated.

[0047] It should be noted that the embodiments of this application are only examples of configuring the sensing angle and / or sensing distance to illustrate the method of configuring the sensing area. In another embodiment, the shape, position, etc. of the sensing area can also be configured. The embodiments of this application do not limit the configuration parameters of the sensing area.

[0048] In some embodiments, the sensing area is automatically determined based on a privacy-preserving area and / or a key monitoring area.

[0049] Optionally, after determining the privacy protection area, the portion of the sensing area that overlaps with or is obscured by the privacy protection area is removed. The portion obscured by the privacy protection area can be the area between the privacy protection area and the sensing unit, or it can be the area of ​​the privacy protection area furthest from the sensing unit; that is, the privacy protection area is located between the obscured area and the sensing unit.

[0050] Optionally, the sensing angle of the sensing unit is determined based on the privacy protection area, so that the sensing area determined based on the sensing angle does not include the privacy protection area; the sensing distance of the sensing unit is determined based on the key monitoring area, so that the sensing area determined based on the sensing distance includes the key monitoring area.

[0051] For example, determining the sensing angle of the sensing unit based on the privacy protection area includes: determining the sensing angle segment corresponding to the privacy protection area; removing the sensing angle segment from the sensing angle range of the sensing unit, and using the remaining sensing angle segment as the sensing angle of the sensing unit.

[0052] The sensing angle segment corresponding to the privacy protection area refers to the angle formed by the direction lines generated from the sensing unit's location as the vertex, pointing from the sensing unit to the two boundaries of the privacy protection area.

[0053] For example, determining the sensing distance of the sensing unit based on the key monitoring area includes: identifying the boundary point of the key monitoring area farthest from the sensing unit, obtaining the distance between the sensing unit and the boundary point, and increasing this distance based on a preset value to obtain the sensing distance. For example, the preset value is added to the distance to obtain the sensing distance. Or, the preset value is multiplied by the distance to obtain the sensing distance.

[0054] In some embodiments, the human body recognition result is used to indicate whether a human body exists in the target image. In some embodiments, the human body recognition result is used to indicate whether a human body exists in the target image, and, when a human body exists in the target image, related information about that human body. This related information may be the image location information of the human body, the spatial location information of the human body, the head position of the human body, the torso position of the human body, etc., and the embodiments of this application do not limit the human body recognition result.

[0055] In performing human body recognition on the target image, any human body recognition method can be used, and this application embodiment does not impose any limitations on this. The following embodiments are provided as examples only: In some embodiments, the process of human recognition of a target image may include: processing the target image using a human segmentation model and a pose estimation model; wherein, the human segmentation model can obtain the human contour, and the pose estimation model can obtain the joint localization of the human body, such as the position of the eyes, nose, ears, shoulders, waist, elbows, wrists, knees, and ankles. Associating the outputs of the human segmentation model and the pose estimation model with the same human body allows the connection of the body's joints to form a human skeleton. Based on this human skeleton, the human posture and orientation can be determined. The orientation of the human body can assist the device in tracking the human body.

[0056] This embodiment achieves human body recognition through a dual-model approach, which can improve the accuracy of human body recognition. Of course, human body recognition can also be achieved using a single model, such as a human body segmentation model or a pose estimation model, which can improve the efficiency of human body recognition. This application does not limit which models are used for human body recognition.

[0057] Step S202: Based on the human body recognition results, determine the positional relationship of the identified human body relative to the privacy protection area and the key monitoring area.

[0058] The privacy protection area refers to the area that one does not wish to be photographed by an image acquisition device. In some embodiments, this privacy protection area corresponds to areas involving sensitive information, such as the entrance to a residence, a window of a residence, the entrance to a dressing room, or the entrance to a restroom.

[0059] A key monitoring area refers to an area that is desired to be captured by an image acquisition device. In some embodiments, this key monitoring area corresponds to a security-related area, such as an activity area within a certain space directly in front of an electronic device, a doorway, a corridor, the area around a crib, or the area around a location where valuables are stored.

[0060] In some embodiments, the privacy protection area and the key monitoring area can be user-defined. The electronic device can provide a corresponding settings interface, allowing the user to configure the privacy protection area and / or key monitoring area. Alternatively, the user can deploy corresponding markers or sensors in the environment captured by the image acquisition device to delineate the privacy protection area and / or key monitoring area. This application does not limit the setting of the privacy protection area and key monitoring area.

[0061] For example, a user can set the area within 3 meters of their door as a key monitoring zone and set their neighbor's doorway as a privacy protection zone.

[0062] In some embodiments, the privacy protection area and the key monitoring area are automatically determined based on the content of the target image. For example, areas in the target image containing sensitive information can be automatically identified to obtain the privacy protection area. For instance, the neighbor's doorway can be automatically identified, and the neighbor's doorway (or the neighbor's doorway and its extended space within a certain range) can be determined as the privacy protection area. For example, the key monitoring area can be determined based on the scene in the target image. For instance, if the scene is a front door, the area within 3 meters in front of the door can be determined as the key monitoring area; if the scene is a nursery, the area within 1.5 meters around the crib can be determined as the key monitoring area.

[0063] Considering the need for privacy protection of objects within the privacy protection zone, the processed image must not clearly display the content of the privacy protection zone to meet privacy protection requirements. Conversely, objects in key monitoring areas need to be clearly displayed in the image to achieve a security protection effect. Furthermore, when a human body is not located within the privacy protection zone but is positioned in front of or behind it relative to the image acquisition device, the image of the human body will overlap with the image of the privacy protection zone. If privacy protection processing is directly applied to the privacy protection zone in the target image, it is inevitable that the same privacy protection processing will be applied to human bodies located in front of or behind that privacy protection zone, resulting in the privacy protection of key monitoring targets and affecting the monitoring effect.

[0064] Therefore, when determining the positional relationship between a human body and the privacy protection area and the key monitoring area based on the human body recognition results, this positional relationship can directly or indirectly indicate whether processing the privacy protection area will affect the monitoring of the human body.

[0065] In some possible implementations, determining the positional relationship of the identified human body relative to the privacy protection area and the key monitoring area based on the human body recognition results includes: determining the spatial positional relationship of the human body relative to the privacy protection area and the key monitoring area based on the human body recognition results.

[0066] The spatial position of the human body relative to the privacy protection area indicates not only whether the body is physically located within the privacy protection area, but also its orientation within that area. Examples include: the body is located within the privacy protection area; the body is located in front of the privacy protection area; the body is located behind the privacy protection area; and the body is located to either side of the privacy protection area. "The body is located in front of the privacy protection area" means the body is between the privacy protection area and the image acquisition device, but not actually within the privacy protection area. "The body is located behind the privacy protection area" means the body is located on the side of the privacy protection area furthest from the image acquisition device, i.e., the privacy protection area separates the image acquisition device from the body.

[0067] Among them, the spatial position of a human body relative to the key monitoring area can indicate whether the human body is located in the physical space of the key monitoring area.

[0068] The spatial relationships described above can be used to determine whether privacy protection measures for privacy-protected areas will affect the need for human surveillance.

[0069] In some possible implementations, determining the positional relationship of the identified human body relative to the privacy protection area and the key monitoring area based on the human body recognition results includes: determining the spatial positional relationship of the human body relative to the privacy protection area and the key monitoring area based on the human body recognition results, and determining the image positional relationship of the human body relative to the privacy protection area.

[0070] Among them, the spatial position of a human body relative to the privacy protection area can be used to indicate whether the human body is located in the physical space of the privacy protection area; the spatial position of a human body relative to the key monitoring area can be used to indicate whether the human body is located in the physical space of the key monitoring area.

[0071] The positional relationship of the human body relative to the privacy protection area in the image can be used to indicate whether the image area corresponding to the human body overlaps with the image area corresponding to the privacy protection area.

[0072] By analyzing the spatial and image positional relationships described above, it can be determined whether privacy protection processing of privacy-protected areas will affect the need for human body monitoring.

[0073] In some possible implementations, determining the positional relationship of the identified human body relative to the privacy protection area and the key monitoring area based on the human body recognition results includes: determining the spatial positional relationship of the human body relative to the key monitoring area based on the human body recognition results, and determining the image positional relationship of the human body relative to the privacy protection area.

[0074] Humans only need to be clearly presented in images when they are located in key monitoring areas; if they are not clearly presented in images when they are not in key monitoring areas, the impact on monitoring effectiveness is minimal. Therefore, the spatial relationship of a human body relative to the key monitoring area, and the image position of the human body relative to the privacy protection area, can be determined. This allows for the application of appropriate processing strategies to ensure the human body is clearly presented in the processed image when the human body is located in the key monitoring area and the image area corresponding to the human body at least partially overlaps with the image area corresponding to the privacy protection area. Whether the human body is located in the privacy protection area, and the physical spatial orientation of the human body and the privacy protection area, are not important and can be disregarded.

[0075] In some embodiments, when determining the spatial positional relationship between a human body and a privacy protection area based on the human body recognition results, it can be based on the position of the human body in the target image, the position of the privacy protection area in the target image, and the distance between the human body and the image acquisition device.

[0076] For example, if the position of a human body in the target image coincides with the position of the privacy-protected area in the target image, and the distance between the human body and the image acquisition device is between the maximum and minimum distances between the privacy-protected area and the image acquisition device, then the human body is located within the privacy-protected area. The maximum distance between the privacy-protected area and the image acquisition device refers to the distance between the plane of the privacy-protected area furthest from the image acquisition device and the image acquisition device. The minimum distance between the privacy-protected area and the image acquisition device refers to the distance between the plane of the privacy-protected area closest to the image acquisition device and the image acquisition device.

[0077] In some embodiments, when determining the spatial position of a human body relative to a key monitoring area based on human body recognition results, the distance between the human body and the image acquisition device can be used as a basis for determination.

[0078] For example, when the key monitoring area is within 3 meters in front of the image acquisition equipment, if the distance between the human body and the image acquisition equipment is no more than 3 meters, the human body is located in the key monitoring area; if the distance between the human body and the image acquisition equipment is more than 3 meters, the human body is not located in the key monitoring area.

[0079] The distance between the human body and the image acquisition device can be determined using depth estimation methods. For example, the distance can be calculated using camera intrinsic parameters and the principle of similar triangles.

[0080] For example, the distance between the human body and the image acquisition device = camera focal length × camera height / (vertical coordinate of the bottom pixel of the human body bounding box - vertical coordinate of the pixel of the center point of the target image).

[0081] Step S203: Determine the processing strategy for the target image based on the positional relationship.

[0082] In some possible implementations, when a human body is in a key monitoring area, it needs to be clearly presented in the image. However, if the image area of ​​the human body at least partially overlaps with the image area of ​​a privacy-protected area, then when privacy protection processing is applied to the privacy-protected area, the human body may also be at least partially obscured. Therefore, this application provides a method for employing an anti-mis-obscuring privacy protection strategy in this situation.

[0083] The positional relationship includes both spatial positional relationship and image positional relationship. Based on this positional relationship, the processing strategy for the target image is determined as follows: if the spatial positional relationship indicates that the human body is in a key monitoring area, and the image positional relationship indicates that the image area of ​​the human body at least partially overlaps with the image area of ​​the privacy protection area, then the anti-false obscuring privacy protection strategy is determined as the processing strategy for the target image. This anti-false obscuring privacy protection strategy is used to prevent the human body from being falsely obscured. "At least partially overlapping" includes both partial overlap and complete overlap.

[0084] For example, when a human body is in a key monitoring area and at least partially in a privacy protection area, or when a human body is in a key monitoring area and in front of a privacy protection area, or when a human body is in a key monitoring area and behind a privacy protection area, the anti-obstruction privacy protection strategy is determined as the processing strategy for the target image.

[0085] In some possible implementations, considering the various possible positional relationships of the human body relative to the privacy protection area and the key monitoring area, the processing strategies for determining the target image based on these different positional relationships will be further explained below: The positional relationship includes spatial positional relationship and image positional relationship. Specifically, determining the processing strategy for the target image based on this positional relationship includes at least one of the following: (1) If the spatial relationship indicates that the human body is in the key monitoring area, and the image position relationship indicates that the image area of ​​the human body does not overlap with the image area of ​​the privacy protection area, then the regional privacy protection strategy is determined as the processing strategy of the target image. The regional privacy protection strategy is used to protect the privacy of the privacy protection area.

[0086] When the image area of ​​the human body does not overlap with the image area of ​​the privacy protection area, then privacy protection processing of the privacy protection area will not affect the human body. Therefore, the regional privacy protection strategy can be directly determined as the processing strategy of the target image. In other words, the privacy protection strategy can be directly applied to the privacy protection area.

[0087] (2) If the spatial relationship indicates that the human body is not in the key monitoring area, then the human body privacy protection strategy and the regional privacy protection strategy are determined as the processing strategy of the target image. The human body privacy protection strategy is used to protect the privacy of at least a part of the human body.

[0088] In some embodiments, the human body privacy protection strategy is used to protect the privacy of the entire human body. In some embodiments, the human body privacy protection strategy is used to protect the privacy of a part of the human body. For example, the human body privacy protection strategy is used to protect the privacy of sensitive parts of the human body, such as protecting the privacy of the human face; or protecting the privacy of the human body's clothing, etc.

[0089] When a person is not in a high-priority monitoring area, there is no need for focused monitoring. In this case, privacy protection processing of the privacy-protected area will not affect the fulfillment of the monitoring requirement, regardless of whether it affects the presentation of the person. Therefore, as long as the spatial relationship indicates that the person is not in a high-priority monitoring area, privacy protection processing can be directly applied to the privacy-protected area, regardless of whether the person is located in the privacy-protected area or whether the image area corresponding to the person at least partially overlaps with the image area corresponding to the privacy-protected area, without the need for additional processing of the person to make them clear.

[0090] The human body privacy protection strategy is used to protect the privacy of at least a part of the human body. In some embodiments, if the human body is not in a key monitoring area, the human body privacy protection strategy is used to protect the privacy of that human body. The human body privacy protection strategy and the regional privacy protection strategy are determined as the processing strategy for the target image; that is, the human body privacy protection strategy is used to protect the privacy of the human body not in the key monitoring area, and the regional privacy protection strategy is used to protect the privacy of the privacy protection area.

[0091] For example, when a human body is not in a key monitoring area and is at least partially in a privacy protection area, or when a human body is not in a key monitoring area and is not in a privacy protection area, or when a human body is not in a key monitoring area and is in front of a privacy protection area, or when a human body is not in a key monitoring area and is behind a privacy protection area, etc., the human body privacy protection strategy and the area privacy protection strategy are determined as the processing strategy for the target image.

[0092] In some possible implementations, since the spatial relationship indicates that the human body is not in a key monitoring area, it is not necessary to determine the positional relationship between the human body and the privacy protection area. Therefore, as... Figure 5 As shown, the spatial positional relationship of the human body relative to the key monitoring area can be determined first. Based on this spatial positional relationship, it can be decided whether to directly determine the processing strategy of the target image, or to further obtain the spatial positional relationship between the human body and the privacy protection area and / or the image positional relationship. Based on the further obtained positional relationship, the processing strategy of the target image can be determined.

[0093] Step S204: Process the target image according to the processing strategy.

[0094] In some possible implementations, the processing strategy is a privacy protection strategy to prevent accidental blocking.

[0095] In some embodiments, the anti-obstruction privacy protection strategy instructs the removal of the image region corresponding to the human body from the image region corresponding to the privacy protection region to obtain an image processing region, and then performs privacy protection processing on the image processing region. This privacy protection processing can include occlusion processing, blurring processing, adding mosaic, or blurring, etc., and the embodiments of this application do not limit the privacy protection processing method.

[0096] For example, the process of processing the target image according to this anti-obstruction privacy protection strategy can be achieved by layer overlay: a mask (such as a blur layer) covering the privacy protection area is overlaid on the target image, and a non-privacy processing area matching the human body contour is dynamically generated on the mask, so that the human body in the image can be clearly seen through the non-privacy processing area, while the rest of the privacy protection area is effectively obscured. The processed target image has two layers: the bottom layer is the target image captured by the image acquisition device, and the top layer is a mask with human-shaped holes, thus achieving the effect of protecting the privacy protection area without obscuring the people who need to be monitored.

[0097] A mask is a binary or grayscale image used to specify which areas in an image need to be processed, preserved, or ignored.

[0098] In some embodiments, the anti-obstruction privacy protection strategy instructs the acquisition of a human body image corresponding to the human body from the target image, the processing of the region image corresponding to the privacy protection area in the target image, and the overlay of the human body image onto the processed target image.

[0099] For example, the human body image is first extracted from the target image, and then privacy protection processing is performed on the privacy protection areas in the target image. Finally, the extracted human body image is pasted back into the privacy-protected target image, which achieves both privacy protection of the privacy protection areas and ensures the clear presentation of the human body.

[0100] In some possible implementations, the processing strategy is a regional privacy protection strategy. This regional privacy protection strategy is used to protect the privacy of a privacy-protected region. For example, a mask covering the privacy-protected region is overlaid on the target image.

[0101] In some possible implementations, the processing strategy includes a human privacy protection strategy and a region privacy protection strategy. The human privacy protection strategy is used to protect the privacy of human faces outside the key monitoring area. The target image is processed according to this strategy, including: protecting the privacy of human faces outside the key monitoring area and protecting the privacy of the privacy-protected area.

[0102] In some embodiments, when protecting the privacy of a human face, it is necessary to first determine the human head. The privacy of the face can be protected by overlaying a mask covering the head area on the target image.

[0103] In some embodiments, the head region can be determined based on head key points. For example, five head key points can be obtained: the nose, both eyes, and both ears. The head center point is calculated based on the obtained five head key points, and the size of the head region is adjusted according to the depth information of the human body image. The head region is determined based on the head center point and the size of the head region.

[0104] For example, after image processing of the target image, the appearance of the human body at different locations in the processed target image is as follows: Figure 6 As shown, in the image, human body 1 is located in the key monitoring area, and its image area does not overlap with the privacy protection area. Human body 1 is clearly presented in the processed target image. Human body 2 is not located in the key monitoring area, and its image area partially overlaps with the privacy protection area. Therefore, human body 2's face is blurred, and the overlapping portion is also blurred along with the privacy protection area. Human body 3 is not located in the key monitoring area, and its image area does not overlap with the privacy protection area. Therefore, human body 3's face is blurred, but its body shape is clear. Human body 4 is located in the key monitoring area. Although its image area partially overlaps with the privacy protection area, human body 4 is clearly presented in the processed target image.

[0105] The image processing method provided in this application determines the image processing strategy based on the positional relationship between the human body in the image and the privacy protection area and the key monitoring area. This ensures that the processed image meets both privacy protection and key monitoring requirements, avoids the loss of key information during privacy protection processing, and improves the system's reliability and event tracing capabilities.

[0106] Corresponding to the aforementioned embodiments of the image processing method, this application also provides embodiments of the apparatus.

[0107] Figure 7 This is a schematic diagram illustrating the structure of an image processing apparatus according to an exemplary embodiment of this application. Figure 7 As shown, the device includes: The image acquisition unit 701 is used to acquire a target image acquired by the image acquisition device, perform human body recognition on the target image, and obtain a human body recognition result. The position relationship determination unit 702 is used to determine the position relationship of the identified human body relative to the privacy protection area and the key monitoring area based on the human body recognition result; The processing strategy determination unit 703 is used to determine the processing strategy of the target image based on the positional relationship; The processing unit 704 is used to process the target image according to the processing strategy.

[0108] In some possible implementations, the positional relationship determination unit 702 is used to determine the spatial positional relationship of the human body relative to the key monitoring area based on the human body recognition result, and to determine the image positional relationship of the human body relative to the privacy protection area.

[0109] In some possible implementations, the positional relationship includes spatial positional relationship and image positional relationship; the processing strategy determination unit 703 is used to determine the anti-mis-obscuring privacy protection strategy as the processing strategy for the target image if the spatial positional relationship indicates that the human body is in the key monitoring area and the image positional relationship indicates that the image area of ​​the human body at least partially overlaps with the image area of ​​the privacy protection area, and the anti-mis-obscuring privacy protection strategy is used to prevent the human body from being mistakenly obscured.

[0110] In some possible implementations, the anti-mis-obscuring privacy protection strategy instructs the removal of the image region corresponding to the human body from the image region corresponding to the privacy protection region to obtain an image processing region, and then performs privacy protection processing on the image processing region; or, The privacy protection strategy for preventing accidental occlusion instructs to obtain the human body image corresponding to the human body from the target image, perform privacy protection processing on the region image corresponding to the privacy protection area in the target image, and overlay the human body image onto the processed target image.

[0111] In some possible implementations, the positional relationship includes spatial positional relationship and image positional relationship; the processing strategy determination unit 703 is configured to perform at least one of the following: If the spatial positional relationship indicates that the human body is located in the key monitoring area, and the image positional relationship indicates that the image area of ​​the human body does not overlap with the image area of ​​the privacy protection area, then the regional privacy protection strategy is determined as the processing strategy for the target image, and the regional privacy protection strategy is used to protect the privacy of the privacy protection area. If the spatial relationship indicates that the human body is not in the key monitoring area, then the human body privacy protection strategy and the regional privacy protection strategy are determined as the processing strategy for the target image, and the human body privacy protection strategy is used to protect the privacy of at least a part of the human body.

[0112] In some possible implementations, the image acquisition device includes a sensing unit; The image acquisition unit is used to control the image acquisition device to acquire an image in response to the sensing unit detecting a target object in the sensing area; The sensing area is set by the user, or the sensing area is automatically determined based on the privacy protection area and the key monitoring area.

[0113] In some possible implementations, the device further includes: A sensing area determination unit is used to display a setting interface for the sensing area; based on the setting interface, determine the sensing angle and / or sensing distance of the sensing unit, wherein the sensing angle is configured as multiple discontinuous angle segments; and determine the sensing area based on the sensing angle and / or sensing distance of the sensing unit.

[0114] Corresponding to the aforementioned embodiments of the device control method, this application also provides device embodiments.

[0115] Device implementations can be achieved through software, hardware, or a combination of both. Taking software implementation as an example, as a logical device, it is formed by a processor (such as a processing unit) loading corresponding computer program instructions from non-volatile memory into memory for execution. From a hardware perspective, such as... Figure 8 The diagram shown is a hardware structure diagram of the electronic device 800 in this application, except... Figure 8 In addition to the processor 810, memory 830, network interface 820, and non-volatile memory 840 shown, other hardware, such as cameras and sensing units, may also be included depending on the actual function of the electronic device; these will not be elaborated further. It should be noted that... Figure 8 The electronic device 800 in the middle is Figure 1 Electronic device 101.

[0116] The specific implementation process of the functions and roles of each unit in the above-mentioned equipment can be found in the implementation process of the corresponding steps in the above-mentioned method, and will not be repeated here.

[0117] 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 units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this application according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0118] The embodiments of the subject matter and functional operation described in this specification can be implemented in the following ways: digital electronic circuits, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or combinations thereof. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible, non-transitory program carrier for execution by a data processing apparatus or for controlling the operation of a data processing apparatus. Alternatively or additionally, the program instructions may be encoded on artificially generated propagation signals, such as machine-generated electrical, optical, or electromagnetic signals, which are generated to encode information and transmit it to a suitable receiving device for execution by the data processing apparatus. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or combinations thereof.

[0119] The processing and logic flow described in this specification can be executed by one or more programmable computers that execute one or more computer programs to perform corresponding functions by operating on input data and generating output. The processing and logic flow can also be executed by dedicated logic circuitry—such as FPGAs (Field-Programmable Gate Arrays) or ASICs (Application-Specific Integrated Circuits), and the device can also be implemented as dedicated logic circuitry.

[0120] Suitable computers for executing computer programs include, for example, general-purpose and / or special-purpose microprocessors, or any other type of central processing unit. Typically, the central processing unit receives instructions and data from read-only memory and / or random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include one or more mass storage devices for storing data, such as disks, magneto-optical disks, or optical disks, or the computer will be operatively coupled to such mass storage devices to receive data from or transfer data to them, or both. However, a computer is not required to have such devices. Furthermore, a computer can be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or a portable storage device such as a universal serial bus (USB) flash drive, to name a few.

[0121] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, such as semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal hard disks or removable disks), magneto-optical disks, and CD-ROM and DVD-ROM disks. Processors and memory may be supplemented by or incorporated into dedicated logic circuitry.

[0122] While this specification contains numerous specific implementation details, these should not be construed as limiting the scope of any invention or the scope of the claims, but rather are primarily intended to describe features of specific embodiments of a particular invention. Certain features described in the various embodiments herein may also be implemented in combination in a single embodiment. Conversely, various features described in a single embodiment may also be implemented separately in various embodiments or in any suitable sub-combination. Furthermore, while features may function in certain combinations as described above and even initially claimed in this way, one or more features from a claimed combination may be removed from that combination in some cases, and a claimed combination may refer to a sub-combination or a variation thereof.

[0123] Similarly, although the operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring these operations to be performed in the specific order shown or sequentially, or requiring all illustrated operations to be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system modules and components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0124] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims may be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings are not necessarily shown in a specific order or sequence to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.

[0125] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for starting an image acquisition device, characterized in that, The method includes: In response to a target object detected by the sensing unit of the image acquisition device within the sensing area, the image acquisition device is controlled to acquire an image. The sensing area is determined by the sensing angle and sensing distance of the sensing unit. By configuring the sensing angle and sensing distance, the sensing area is divided into multiple continuous and discretely spaced angle segments, so that the sensing area corresponding to each angle segment includes the key monitoring area and avoids all privacy protection areas.

2. The method according to claim 1, characterized in that, The sensing area is set by the user, or the sensing area is automatically determined based on the privacy protection area and the key monitoring area.

3. The method according to claim 2, characterized in that, When the sensing area is set by the user, the method further includes: Displays the settings interface for the sensing area; Based on the settings interface, determine the sensing angle and / or sensing distance of the sensing unit; The sensing area is determined based on the sensing angle and sensing distance of the sensing unit.

4. The method according to claim 2, characterized in that, The sensing area is automatically determined based on the privacy protection area and the key monitoring area, including: Based on the privacy protection area, the sensing angle of the sensing unit is determined so that the sensing area determined based on the sensing angle does not include the privacy protection area; Based on the key monitoring areas, determine the sensing distance of the sensing unit so that the sensing area determined based on the sensing distance includes the key monitoring areas.

5. The method according to claim 4, characterized in that, The step of determining the sensing angle of the sensing unit based on the privacy protection area includes: Determine the sensing angle segment corresponding to the privacy protection area; remove the sensing angle segment from the sensing angle range of the sensing unit, and use the remaining sensing angle segment as the sensing angle of the sensing unit.

6. The method according to claim 4, characterized in that, The determination of the sensing distance of the sensing unit based on the key monitoring area includes: Determine the boundary point of the key monitoring area that is farthest from the sensing unit, obtain the distance between the sensing unit and the boundary point, and increase the distance based on a preset value to obtain the sensing distance.

7. The method according to claim 1, characterized in that, The method further includes: Acquire a target image captured by an image acquisition device, perform human body recognition on the target image, and obtain human body recognition results; Based on the human body recognition results, the positional relationship of the identified human body relative to the privacy protection area and the key monitoring area is determined; Based on the positional relationship, determine the processing strategy for the target image; The target image is processed according to the processing strategy.

8. A starting device for an image acquisition equipment, characterized in that, The device includes: The startup module is used to control the image acquisition device to acquire images in response to a target object detected by the sensing unit of the image acquisition device within the sensing area. The sensing area is determined by the sensing angle and sensing distance of the sensing unit. The sensing angle is configured as multiple discontinuous angle segments, so that the sensing area corresponding to each angle segment includes the key monitoring area and avoids the privacy protection area.

9. 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 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images