Display control method and device of video monitoring equipment and video monitoring equipment

Abstract

The application discloses a display control method and device of a video monitoring device and the video monitoring device, and relates to the technical field of security monitoring. The method writes AI detection events returned by a cloud server and user operation events and timer events generated locally into an event queue, calculates a scheduling score based on the priority and waiting time of each event, selects a target event, determines the display time and UI control corresponding to different event types, determines the area that needs to be lighted on the display screen according to the layout position of the UI control, controls the area to be lighted according to the display time, and only executes display refresh on the UI control in the area. The application makes the lightening time and range of the display screen dynamically change with the event type, reduces the power consumption of the display screen while ensuring the response time of the event, and prolongs the endurance time of the battery-powered camera.

Description

Technical Field

[0001] This application relates to the field of security monitoring technology, and in particular to a display control method, device, and video monitoring equipment for video surveillance. Background Technology

[0002] Video surveillance equipment with displays has been widely used in the security monitoring field. Battery-powered video surveillance equipment with displays does not require an external power source and offers flexible installation, gradually becoming an important product type in the market.

[0003] In existing video surveillance equipment with displays, screen illumination control typically employs a fixed strategy. When preset trigger conditions are met, the display is turned on and remains lit for a fixed duration, automatically turning off after the set duration is reached. Using a uniform illumination duration can lead to the display remaining on for longer than actually needed in certain scenarios, resulting in unnecessary power consumption. This issue shortens the battery life of battery-powered video surveillance equipment with displays. Summary of the Invention

[0004] This application provides a display control method, apparatus, and video surveillance equipment, which can solve the technical problem in the prior art where battery-powered video surveillance equipment with displays consumes a lot of power, resulting in short battery life. The technical solution is as follows: In a first aspect, embodiments of this application provide a display control method for a video surveillance device, applied to a video surveillance device with a display screen, wherein the video surveillance device is communicatively connected to a cloud server, and the cloud server is deployed with a pre-trained AI detection model, the method comprising: Acquire audio and video data and send the audio and video data to the cloud server; receive AI detection events returned by the cloud server and write the AI ​​detection events into an event queue; wherein, the event queue is also used to store user operation events and timer events, and the AI ​​detection events, the user operation events and the timer events each carry their respective event type identifiers; Based on the priority and waiting time of each pending event in the event queue, the scheduling score of each pending event is calculated, and the pending event with the highest scheduling score is dequeued from the event queue as the target event. Based on the event type identifier carried by the target event, determine the target display duration corresponding to the event type identifier from the preset mapping relationship, and determine at least one target UI control corresponding to the event type identifier; Based on the placement position of the at least one target UI control on the display screen, determine the target illuminated area on the display screen; According to the target display duration, control the target illuminated area of ​​the display screen to be lit; Within the target illuminated area of ​​the display screen, the display state refresh action is performed only on the at least one target UI control based on the state information of the target event.

[0005] Secondly, embodiments of this application provide a display control device for a video surveillance equipment, the device comprising: The acquisition module is used to acquire audio and video data and send the audio and video data to the cloud server; receive AI detection events returned by the cloud server and write the AI ​​detection events into the event queue; wherein, the event queue is also used to store user operation events and timer events, and the AI ​​detection events, the user operation events and the timer events each carry their respective event type identifiers; The calculation module is used to calculate the scheduling score of each pending event based on the priority and waiting time of each pending event in the event queue, and to dequeue the pending event with the highest scheduling score from the event queue as the target event. The determination module is used to determine the target display duration corresponding to the event type identifier from a preset mapping relationship based on the event type identifier carried by the target event, and to determine at least one target UI control corresponding to the event type identifier; The determining module is further configured to determine a target illuminated area on the display screen based on the placement position of the at least one target UI control on the display screen; The control module is used to control the target illuminated area of ​​the display screen to be lit according to the target display duration; A refresh module is used to perform a display state refresh action only on the at least one target UI control within the target illuminated area of ​​the display screen, based on the state information of the target event.

[0006] Thirdly, embodiments of this application provide a computer storage medium storing a plurality of instructions adapted for loading by a processor and executing the above-described method steps.

[0007] Fourthly, embodiments of this application provide a video surveillance device, which may include: a processor and a memory; wherein the memory stores a computer program, the computer program being adapted to be loaded by the processor and to execute the above-described method steps.

[0008] The beneficial effects of the technical solutions provided in some embodiments of this application include at least the following: This application configures different display durations for different types of events, so that the duration of the display screen is lit up to match the actual needs of the event. This avoids the energy waste caused by long-term screen lighting for low-value events under a fixed screen lighting strategy. At the same time, by precisely limiting the lighting range to the area where the target UI control is located instead of lighting up the entire display screen, the power consumption of the display screen is further reduced.

[0009] At the event scheduling level, the comprehensive scoring mechanism of priority and waiting time ensures that high-priority events can be responded to in a timely manner, while the introduction of waiting time avoids the long-term starvation of low-priority events, thus ensuring the timeliness of security event response while taking into account the fairness of event handling.

[0010] During the display refresh process, only the local area where the target UI control is located is updated, which significantly reduces the amount of display data transmission compared to the full-screen refresh method, thereby reducing power consumption from the display driver level.

[0011] In summary, this application comprehensively reduces the power consumption of the display screen from multiple dimensions, including event scheduling, screen-on duration control, illuminated area optimization, and display refresh range reduction. It effectively solves the problem of insufficient battery life caused by fixed screen-on duration and full-screen illumination strategies in the prior art, and significantly extends the single-charge battery life of battery-powered video surveillance equipment. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a schematic diagram of a video surveillance system provided in an embodiment of this application; Figure 2 This is a flowchart illustrating a display control method for a video surveillance device provided in an embodiment of this application. Figure 3 This is a schematic diagram of the structure of a display control device for a video surveillance equipment provided in this application; Figure 4 This is a schematic diagram of a computer storage medium provided in this application; Figure 5 This is a structural schematic diagram of a video surveillance device provided in this application. Detailed Implementation

[0014] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0015] Figure 1 This is a scene diagram of a video surveillance system provided in an embodiment of this application.

[0016] like Figure 1 As shown, the video surveillance system includes: the system includes a video surveillance device 1 and a cloud server 2, and the video surveillance device 1 has a display screen 11.

[0017] The video surveillance device 1 is a battery-powered wireless network video surveillance device, which integrates an image sensor, a sound sensor, a wireless communication module, a processor, and a display screen 11. The image sensor is used to collect image data within the field of view of the video surveillance device 1; the sound sensor is used to collect audio data from the environment in which the video surveillance device 1 is located; the wireless communication module is used to realize data interaction between the video surveillance device 1 and the cloud server 2; and the processor is used to execute the display control steps in the various method embodiments of this application. The display screen 11 is used to display the operating status information of the video surveillance device 1, AI detection event prompts, and the user interface. The display screen 11 can be located on the front or back of the housing of the video surveillance device 1, and can be used to display the operating status information of the video surveillance device 1, AI detection event prompts, and the user interface. The display screen 11 can be a liquid crystal display (LCD) or an organic light-emitting diode (OLED) display.

[0018] Cloud server 2 is a server device deployed on the network side, internally running a pre-trained AI (Artificial Intelligence) detection model. This AI detection model includes at least a human detection sub-model, a face detection sub-model, a crying sound detection sub-model, and a motion detection sub-model, used to perform inference analysis on the audio and video data uploaded by video surveillance device 1 and output AI detection events. Cloud server 2 maintains a communication connection with video surveillance device 1 via a wireless network, receives the audio and video data sent by video surveillance device 1, and returns the detection results of AI detection events to video surveillance device 1.

[0019] The communication process between video surveillance device 1 and cloud server 2 is as follows: Video surveillance device 1 collects image data and audio data through image sensors and sound sensors, respectively. After aligning the timestamps of the collected image and audio data, it encapsulates them into an audio-video data packet. Video surveillance device 1 sends this audio-video data packet to cloud server 2 via a wireless communication module. After receiving the audio-video data packet, cloud server 2 calls a pre-trained AI detection model to perform inference analysis on the image and audio data in the audio-video data packet, generating an AI detection event. Cloud server 2 returns this AI detection event to video surveillance device 1. After receiving the AI ​​detection event, video surveillance device 1 processes the event according to the steps in the various method embodiments of this application, and controls the display state of display screen 11 based on the processing result.

[0020] It should be noted that, Figure 1 The system architecture shown is merely an exemplary structure of this application and does not constitute a limitation on the application scenarios of this application. Those skilled in the art will understand that, in practical applications, the functional modules of the video surveillance device 1 and the cloud server 2 can be appropriately divided and combined based on actual needs.

[0021] The following will be combined with the appendix Figure 2 This application provides a detailed description of the display control method for a video surveillance device according to embodiments of the present application. The display control device for the video surveillance device in these embodiments may be... Figure 1 The video surveillance equipment shown.

[0022] Please see Figure 2 This is a flowchart illustrating a display control method for a video surveillance device, as provided in an embodiment of this application. Figure 2 As shown, the method described in this application embodiment may include the following steps: S1. Acquire audio and video data and send the audio and video data to the cloud server; receive AI detection events returned by the cloud server and write the AI ​​detection events into the event queue.

[0023] First, image data within the field of view of the video surveillance equipment is acquired using an image sensor, while audio data from the environment surrounding the equipment is acquired using a sound sensor. The image sensor can be a complementary metal-oxide-semiconductor (CMOS) image sensor, outputting raw image data in YUV (Luma-Chroma-Chroma) or RGB (Red-Green-Blue) format. The sound sensor can be a microelectromechanical system (MEMS) microphone, outputting audio data streams in pulse density modulation (PDM) or integrated circuit-based audio bus format. The image sensor's acquisition sequence is controlled according to a preset sampling frame rate, which can be set to 15 to 30 frames per second, depending on the specific needs of the security scenario. Similarly, the sound sensor's acquisition sequence is controlled according to a preset sampling rate, which can be set to 16 kHz or 48 kHz.

[0024] After acquiring image and audio data, a timestamp alignment operation is performed on them. Specifically, when each frame of image data is read out, the acquisition time of that frame is recorded, generating a timestamp for that frame; when each segment of audio data is read out, the acquisition time of that segment is recorded, generating a timestamp for that segment. Then, image and audio data with the same timestamp or timestamp differences within a preset tolerance range are associated and encapsulated to generate an audio / video data packet. This preset tolerance range can be set to no more than 10 milliseconds to ensure that the synchronization accuracy of the image and audio meets the requirements of subsequent AI detection.

[0025] After the audio and video data packets are encapsulated, they are sent to the cloud server via a wireless communication module. The wireless communication module can be a Wi-Fi communication module conforming to the 802.11 series standards, or a cellular network-based communication module. The cloud server is equipped with a pre-trained AI detection model, which includes at least a human detection sub-model, a face detection sub-model, a crying sound detection sub-model, and a motion detection sub-model. Upon receiving the audio and video data packets, the cloud server uses the aforementioned AI detection models to perform comprehensive reasoning and analysis on the image and audio data within the data packets, outputting an AI detection event. Each AI detection event includes at least an event type identifier and a detection confidence score. The event type identifier indicates whether the AI ​​detection event belongs to a stranger detection event, a suspicious person detection event, a human detection event, a crying sound detection event, a motion detection event, or a known person detection event. The detection confidence score indicates the reliability of the AI ​​detection event, with a value ranging from 0 to 1.

[0026] The system receives AI detection events returned by the cloud server via a wireless communication module and writes these events into a local event queue. This event queue is a first-in, first-out (FIFO) storage area in memory used to uniformly store pending events from different sources. Specifically, the event queue stores not only AI detection events from the cloud server but also user operation events and timer events. User operation events refer to events generated when a user performs operations on the video surveillance equipment through physical buttons, touchscreens, or remote applications, such as pressing a call button or touching confirmation or cancellation controls on the screen. Timer events refer to events automatically triggered by the internal timer module when a preset time threshold is reached, such as status timeout events or timed reminder events.

[0027] AI detection events, user action events, and timer events each carry their respective event type identifiers when written to the event queue. The event type identifier is a predefined enumeration or encoded value used to uniquely indicate the type of the event. For example, the event type identifier for a stranger detection event can be encoded as value 1, for a suspicious person detection event as value 2, for a human figure detection event as value 3, for a crying sound detection event as value 4, for a movement detection event as value 5, for a known person detection event as value 6, for a user action event as value 10, and for a timer event as value 20. Sufficient numerical intervals are maintained between the encoded values ​​of different event type identifiers to prevent conflicts with existing encodings when new event types are subsequently added.

[0028] S2. Calculate the scheduling score of each pending event based on its priority and waiting time in the event queue, and dequeue the pending event with the highest scheduling score from the event queue as the target event.

[0029] The event queue is processed according to a preset scheduling cycle. Within each scheduling cycle, all currently pending events in the event queue are read, and a scheduling score is calculated for each event. This scheduling score considers both the priority of the event and its waiting time in the event queue.

[0030] Specifically, each event type is pre-assigned a priority value, which indicates the importance of that event type when it is scheduled. The smaller the priority value, the higher the priority of the event type. In this embodiment, the priority value for stranger detection and suspicious person detection events is set to 1, the priority value for human figure detection and crying detection events is set to 3, the priority value for movement detection events is set to 5, the priority value for known person detection events is set to 6, the priority value for user operation events is set to 10, and the priority value for timer events is set to 20. It should be noted that the specific values ​​of the above priority values ​​are merely exemplary, and those skilled in the art can adjust these values ​​according to the needs of actual application scenarios.

[0031] The waiting time refers to the elapsed time from the moment the event was written to the event queue to the moment of the current scheduling cycle, measured in milliseconds. An internal high-precision timer is maintained to record the timestamp of each event when it is written to the event queue. When calculating the scheduling score, the current timestamp is read, and the timestamp of the event when it was written is subtracted to obtain the waiting time for that event.

[0032] Optionally, this application may calculate the scheduling score for each pending event according to the following formula: After identifying the pending event requiring scheduling score calculation in the event queue, the priority parameter of that event is first retrieved. This priority parameter is a pre-configured, fixed attribute value stored in local memory, representing the importance of the event type during scheduling. A smaller priority parameter value indicates a higher priority for the event type. The priority parameter can be obtained by reading the event type identifier of the pending event and using that identifier as an index to query the priority configuration table stored in local memory.

[0033] Simultaneously, obtain the enqueue timestamp and current timestamp of the event to be processed. The enqueue timestamp refers to the moment when the event to be processed is written into the event queue. This moment is automatically recorded by an internal high-precision timer when the event is enqueued and is stored in the event queue as an attribute field of the event. The current timestamp refers to the real-time moment when the current scheduling score calculation operation is performed. This moment is also provided by an internal high-precision timer. These two timestamps can be obtained by reading the enqueue timestamp attribute field of the event to be processed and the current count value of the timer, respectively. Both the enqueue timestamp and the current timestamp are measured in milliseconds.

[0034] Suppose an event to be processed is retrieved from the event queue for calculating its scheduling score; this event is a stranger detection event. The priority configuration table in local memory is queried using the event type identifier carried by the event, and the priority parameter for this event is found to be 1. The enqueue timestamp attribute field of the event is read, and its value is 50 milliseconds prior to the current time. The current count value of the internal high-precision timer is read as the current timestamp. The priority parameter and the two timestamps are then stored in internal registers.

[0035] After obtaining the enqueue timestamp and current timestamp of the event to be processed, the difference between the current timestamp and the enqueue timestamp is determined as the waiting time for that event. The unit of waiting time is milliseconds, and its physical meaning is the length of time the event has waited since it was written into the event queue until the current scheduling time. The formula for calculating the waiting time is: waiting time equals current timestamp minus enqueue timestamp. Since the enqueue timestamp is always earlier than or equal to the current timestamp, this difference is always a value greater than or equal to zero.

[0036] Continuing with the previous example of the stranger detection event, the enqueue timestamp for this event is 50 milliseconds prior to the current time, and the current timestamp is the current time. The difference between the current timestamp and the enqueue timestamp is calculated; this difference is 50 milliseconds. Therefore, the waiting time for this stranger detection event is determined to be 50 milliseconds.

[0037] The priority weighted value is obtained by multiplying the priority parameter of the event to be processed by a preset priority weighting coefficient. The priority weighting coefficient is a pre-defined constant whose function is to amplify the influence of the priority parameter in the scheduling score calculation, making priority a dominant factor in the scheduling decision. The value of the priority weighting coefficient is much larger than the value of the waiting time weighting coefficient, ensuring that even with a short waiting time, a high-priority event still receives a lower scheduling score than a low-priority event, even with a long waiting time. The formula for calculating the priority weighted value is: Priority weighted value = Priority parameter multiplied by the priority weighting coefficient.

[0038] Continuing from the previous scenario, the obtained priority parameter is 1, and the preset priority weight coefficient is 0.999. Calculate the priority weight value by multiplying 1 by 0.999, which equals 0.999.

[0039] The waiting time of the pending event is multiplied by a preset waiting time weighting coefficient to obtain the waiting time weighted value. The waiting time weighting coefficient is a pre-set constant whose function is to ensure that the waiting time factor has a corresponding influence on the scheduling score calculation, ensuring that low-priority events with long waiting times do not never receive a scheduling opportunity due to their low priority. The value of the waiting time weighting coefficient is much smaller than the value of the priority weighting coefficient, ensuring that the waiting time factor only plays a supporting adjustment role. The formula for calculating the waiting time weighted value is: waiting time weighted value = waiting time multiplied by the waiting time weighting coefficient.

[0040] Continuing from the previous scenario, the obtained waiting time is 50 milliseconds, and the preset waiting time weighting coefficient is 0.001. Calculate the weighted value of the waiting time by multiplying 50 milliseconds by 0.001, which equals 0.05.

[0041] The scheduling score for the pending event is obtained by adding the priority weighted value and the waiting time weighted value. The scheduling score is the final quantitative basis for ranking and selecting pending events; its value directly reflects the priority order in which the event should be processed at the current scheduling moment. The formula for calculating the scheduling score is: Scheduling score = Priority weighted value + Waiting time weighted value. Substituting the two intermediate calculation results mentioned above, the scheduling score equals the priority parameter multiplied by the priority weight coefficient plus the waiting time multiplied by the waiting time weight coefficient. The sum of the priority weight coefficient and the waiting time weight coefficient equals 1. After calculating the scheduling score, this score is associated with the pending event and stored for subsequent comparison with the scheduling scores of other pending events. The above calculation process is performed for all pending events, and the event with the smallest scheduling score is selected as the target event.

[0042] Continuing with the previous scenario, the priority weighted value is 0.999, and the waiting time weighted value is 0.05. Adding the two together, the scheduling score is 0.999 plus 0.05, which equals 1.049. Therefore, the scheduling score for this stranger detection event is 1.049.

[0043] Suppose that at the start of a certain scheduling cycle, there are three pending events in the event queue. The first event is a stranger detection event with event type 1, priority value of 1, and waiting time of 50 milliseconds. The second event is a user operation event with event type 10, priority value of 10, and waiting time of 500 milliseconds. The third event is a timer event with event type 20, priority value of 20, and waiting time of 1000 milliseconds. The priority weight coefficient is 0.999, and the waiting time weight coefficient is 0.001.

[0044] The scheduling scores for the three events are calculated using the formulas described above. The scheduling score for the stranger detection event is 1 multiplied by 0.999 plus 50 multiplied by 0.001, resulting in 1.049. The scheduling score for the user operation event is 10 multiplied by 0.999 plus 500 multiplied by 0.001, resulting in 10.49. The scheduling score for the timer event is 20 multiplied by 0.999 plus 1000 multiplied by 0.001, resulting in 20.98. Comparing the three scheduling scores, the stranger detection event, with a score of 1.049, is determined to be the minimum. Therefore, this stranger detection event is selected as the target event and dequeued from the event queue. At this point, although the user operation event and the timer event have waited longer in the queue, the stranger detection event, having the highest priority, still has the lowest scheduling score and is therefore processed first.

[0045] In another scenario, suppose the event queue contains only two pending events: a known person detection event and a timer event. The known person detection event has a priority value of 6 and has been waiting in the queue for 100 milliseconds. The timer event has a priority value of 20 and has been waiting in the queue for 5000 milliseconds. The scheduling score for the known person detection event is equal to 6 multiplied by 0.999 plus 100 multiplied by 0.001, resulting in 6.094. The scheduling score for the timer event is equal to 20 multiplied by 0.999 plus 5000 multiplied by 0.001, resulting in 24.98. The known person detection event with the lower scheduling score is still selected as the target event. However, if the known person detection event remains unscheduled, its waiting time increases. For example, when the waiting time reaches 14986 milliseconds, its scheduling score becomes 6 multiplied by 0.999 plus 14986 multiplied by 0.001, equaling 20.98. If there is a timer event with a waiting time of 1000 milliseconds, its scheduling score is 20 multiplied by 0.999 plus 1000 multiplied by 0.001, which equals 20.98, meaning the two events have the same scheduling score. When scheduling scores are equal, the event with the earlier write time can be selected as the target event according to the first-in, first-out principle, or the tie can be broken according to a preset priority rule.

[0046] S3. Based on the event type identifier carried by the target event, determine the target display duration corresponding to the event type identifier from the preset mapping relationship, and determine at least one target UI control corresponding to the event type identifier.

[0047] After retrieving the target event from the event queue, the event type identifier carried by the target event is read. Then, a mapping table pre-stored in local memory is accessed. This mapping table records the correspondence between event type identifiers and display durations, as well as the correspondence between event type identifiers and UI controls.

[0048] Display duration refers to the length of time, measured in seconds, that the LCD (Liquid Crystal Display) screen corresponding to the event type should remain lit. Different AI detection event types correspond to different display durations. Specifically, stranger detection and suspicious person detection events are the highest priority security alarm events, requiring timely user attention and handling; therefore, their display duration is set to remain lit until the user actively turns it off or until the call ends. Human detection and crying detection events are high priority security alarm events, requiring sufficient time to present warning information to the user for judgment and response; therefore, their display duration is set to 15 seconds. Movement detection events are medium priority security alert events, requiring only a brief movement warning message to the user; therefore, their display duration is set to 5 seconds. Known person detection events are low priority security alert events, requiring only a brief welcome message to the user; therefore, their display duration is set to 3 seconds. The display duration for user operation events depends on the specific type of user operation; for example, when a user initiates a video call, the screen remains lit until the call ends. The display duration for a timer event depends on the specific type of the timer event. For example, the display duration for a timed reminder event can be set to 10 seconds.

[0049] UI controls are graphical interface elements on an LCD screen used to present specific information or provide specific interactive functions, such as text labels, icon buttons, image areas, and face bounding boxes. Each event type corresponds to at least one UI control, and these UI controls together constitute all the graphical interface elements required to present information for that event type on the LCD screen. A mapping table records the correspondence between event type identifiers and UI control identifiers; by querying this mapping table, all UI controls corresponding to the current target event can be determined.

[0050] In one specific implementation, the UI controls for a stranger detection event include a face bounding box control, a warning text label control, and a call button control. The controls for a suspicious person detection event include a face bounding box control, a warning text label control, and an alarm icon control. The controls for a human shape detection event include a human shape bounding box control and a warning text label control. The controls for a crying sound detection event include a crying sound alert icon control and a warning text label control. The controls for a movement detection event include a movement alert icon control. The controls for a known person detection event include a welcome text label control. The UI controls for user action events depend on the specific type of user action, such as the set of call interface controls corresponding to when a user presses the call button. The UI controls for timer events depend on the specific type of timer event, such as a reminder text label control corresponding to a timed reminder event.

[0051] S4. Determine the target illuminated area on the display screen based on the placement position of at least one target UI control on the display screen.

[0052] S5. Control the target illuminated area of ​​the display screen to be lit according to the target display duration.

[0053] After determining the target illuminated area, the target illuminated area of ​​the LCD screen is controlled to remain illuminated for the specified display duration, as determined in step three. Specifically, this area illumination control is achieved through the backlight driving circuit and display driving circuit of the LCD screen.

[0054] The backlight of an LCD display is typically provided by a backlight module composed of multiple light-emitting diodes (LEDs), which can be divided into multiple independent backlight zones. The brightness of each backlight zone is controlled individually using a pulse-width modulation (PWM) signal. For backlight zones covered by the target illuminated area, a PWM signal with a first duty cycle is output to illuminate these zones. For backlight zones outside the target illuminated area, a PWM signal with a second duty cycle is output to de-illuminate or reduce brightness in these zones. The first duty cycle is greater than the second duty cycle. In one specific embodiment, the first duty cycle can be set to a value between 50% and 100%, and the second duty cycle can be set to 0%.

[0055] Simultaneously, the display driver circuit controls the pixel array of the LCD screen. For pixels within the target illuminated area, pixel data is written to them according to the normal display driver timing sequence, enabling these pixels to display the required color and brightness. For pixels outside the target illuminated area, they are controlled to be in a black screen state, meaning all sub-pixels are either turned off or appear black.

[0056] A timer is started based on the target display duration, with the timer's duration equal to the target display duration. During the timer's operation, the target illuminated area remains lit. When the timer reaches the preset duration, the target illuminated area is turned off, restoring the LCD screen to its previous display state. If the target display duration is continuous illumination until the user actively turns it off or until the call ends, the timer is not started. Instead, the user's operation or call status is continuously monitored, and the target illuminated area is turned off only when the user actively turns off the screen or the call ends.

[0057] In one example, continuing the scenario of the aforementioned stranger detection event, the target illuminated area is determined to be a rectangular area starting at coordinates (120, 80), with a width of 340 pixels and a height of 340 pixels. The target display duration is determined to be continuous illumination until the user actively turns it off or until the call ends. A pulse width modulation (PWM) signal is used to control the backlight area covered by this target illuminated area to illuminate at 80% duty cycle, while the backlight areas outside the target illuminated area are controlled to be completely off at 0% duty cycle. Simultaneously, pixels within the target illuminated area are controlled to display image data according to the normal driving timing, while pixels outside the target illuminated area remain in a black screen state. Since the display duration corresponding to this stranger detection event is continuous illumination until the call ends, a screen-off timer is not activated; instead, the video call status is continuously monitored. When the user ends the video call through a remote application or local operation of the video monitoring device, a call end signal is detected, and the target illuminated area is immediately turned off, and the LCD display returns to standby display mode.

[0058] In a motion detection event scenario, the target display duration is determined to be 5 seconds. Once the target's illuminated area is turned on, a timer with a duration of 5 seconds is immediately started. During these 5 seconds, the illuminated area on the LCD screen continuously displays a motion indicator icon. After the 5 seconds elapse, the timer sends an expiration signal, and the illuminated area is immediately turned off, restoring the LCD screen to its previous display state.

[0059] S6. Within the target illuminated area of ​​the display screen, based on the state information of the target event, only perform a display state refresh action on at least one target UI control.

[0060] While the target illuminated area is illuminated, based on the state information of the target event, a display state refresh action is performed only on at least one target UI control within the illuminated area. Display state refresh refers to updating the visual presentation of UI controls, such as updating the text content in a text label, updating the color or shape of an icon, or updating the position or size of a face frame.

[0061] First, the state information of the target event is obtained. For AI detection events, the state information includes at least the target's position coordinates in the image and the detection confidence score. The target's position coordinates in the image are represented by a detection box, which includes four parameters: horizontal starting coordinates, vertical starting coordinates, width, and height. The detection confidence score is a value between 0 and 1, used to represent the reliability of the detection result. For user operation events, the state information includes the type of user operation and operation parameters, such as which button the user clicked and the user's touch coordinates on the touchscreen. For timer events, the state information includes the timer type and remaining time.

[0062] Based on the status information of the target event, the display content of each target UI control is updated. For the face bounding box control, a rectangle is drawn within the target's illuminated area based on the target's position coordinates. The position and size of this rectangle correspond to the target's position coordinates, visually indicating the location of the face or human figure on the LCD screen. For the warning text label control, corresponding warning text is displayed based on the detection confidence level. For example, when the confidence level is higher than 0.85, the text "Stranger detected, calling" is displayed; when the confidence level is between 0.70 and 0.85, the text "Suspected stranger, confirming" is displayed. For the call button control, corresponding button text and style are displayed based on the current call status. For example, a "Call" button is displayed when no call is initiated, a "Calling..." button is displayed during a call and made inoperable, and a "Hang Up" button is displayed after the call is connected.

[0063] Throughout the entire display state refresh process, the refresh range is strictly limited, performing data update operations only on the pixel area occupied by the target UI control within the target illuminated area. Blank areas within the target illuminated area that do not belong to any target UI control are not refreshed, and the entire display screen area outside the target illuminated area is also not refreshed. This precise local refresh method minimizes the amount of display data transmitted for each event response.

[0064] In one example, continuing the scenario of the aforementioned stranger detection event, the target area has been illuminated, and face bounding box controls, warning text labels, and call button controls are displayed within that area. Meanwhile, the cloud server continuously performs AI detection on the audio and video data and returns updated detection results. Upon receiving the updated detection results, the latest status information of the target event is obtained, including the latest position coordinates of the stranger's face in the current frame image and the updated detection confidence level of 0.95.

[0065] The display content of the three target UI controls is refreshed based on the latest status information. For the face bounding box control, the position of the face bounding box on the LCD screen is recalculated based on the latest face position coordinates, and the face bounding box is drawn to the updated position within the target illuminated area. For the warning text label control, the display content is updated to "Stranger detected, 95% confidence, calling." For the call button control, since a video call has been initiated, the button's display status is updated from "Calling" to "Calling...", and it is made inactive.

[0066] During the entire refresh process, data updates were performed only on the pixel areas containing the three UI controls mentioned above. The updated area for the face frame label control was 150 pixels by 180 pixels, the updated area for the warning text label control was 260 pixels by 40 pixels, and the updated area for the call button control was 120 pixels by 60 pixels. The total updated area of ​​the three controls was 150 x 180 + 260 x 40 + 120 x 60, which equals 27000 + 10400 + 7200, or 44600 square pixels. The total area of ​​the entire LCD screen is 800 x 480, which equals 384000 square pixels. Each refresh only updated approximately 11.6% of the total screen area, while the remaining 88.4% of the pixel area did not undergo any data update operations, thus significantly reducing the amount of data transmission between the LCD screen driver circuitry and the LCD screen.

[0067] In scenarios involving motion detection events, the target event corresponds to only one motion tooltip icon control. Each refresh only updates the area of ​​80 pixels by 80 pixels, which is 6400 square pixels, occupying approximately 1.7% of the total display area of ​​384,000 square pixels. This results in a more significant reduction in data transmission volume.

[0068] In one possible implementation, determining the target illuminated area on the display screen based on the placement position of at least one target UI control on the display screen includes: S41a. Obtain the placement position of each target UI control on the display screen in at least one target UI control.

[0069] The placement position is a fixed attribute information that is predefined and stored in local memory during the design phase of each UI control. It describes the spatial positioning relationship of the UI control on the LCD screen.

[0070] The placement of each UI control is defined by four parameters: horizontal starting coordinates, vertical starting coordinates, control width, and control height. The horizontal starting coordinates represent the pixel distance of the control's left edge from the left edge of the LCD screen in the horizontal direction; the vertical starting coordinates represent the pixel distance of the control's top edge from the top edge of the LCD screen in the vertical direction; the control width represents the number of pixels occupied by the control in the horizontal direction; and the control height represents the number of pixels occupied by the control in the vertical direction. Both the horizontal and vertical starting coordinates are in pixels, as are the control width and height. The horizontal direction of the LCD screen refers to the horizontal axis of the screen, and the vertical direction refers to the vertical axis of the screen.

[0071] The display area of ​​an LCD screen is defined as a two-dimensional pixel coordinate system. The origin of this coordinate system is located at the top left corner of the LCD screen. The horizontal axis extends from left to right along the top edge of the screen, and the vertical axis extends from top to bottom along the left edge of the screen. In this coordinate system, the entire display area of ​​the LCD screen is represented as a rectangular area with a horizontal coordinate from 0 to the total horizontal pixel count minus 1 and a vertical coordinate from 0 to the total vertical pixel count minus 1. The placement of each UI control is defined with reference to this coordinate system.

[0072] When obtaining the placement position of each target UI control, the system reads the four parameter values ​​corresponding to each target UI control: horizontal starting coordinate, vertical starting coordinate, control width, and control height. These parameter values ​​are then temporarily stored in internal registers or caches for later calculation.

[0073] S42a. Based on the placement position of each target UI control, determine the control display area of ​​each target UI control on the display screen.

[0074] Based on the placement parameters of each target UI control obtained in step S41a, the control display area occupied by each target UI control on the LCD screen is calculated. The control display area refers to the pixel range actually occupied by the UI control on the LCD screen, which is also represented by a rectangular area in a two-dimensional pixel coordinate system.

[0075] For any target UI control, its display area is determined as follows: The horizontal starting coordinate of the display area is equal to the horizontal starting coordinate of the UI control itself. The vertical starting coordinate of the display area is equal to the vertical starting coordinate of the UI control itself. The horizontal ending coordinate of the display area is equal to the horizontal starting coordinate of the UI control plus the width of the UI control minus 1. The vertical ending coordinate of the display area is equal to the vertical starting coordinate of the UI control plus the height of the UI control minus 1. The reason for subtracting 1 is that pixel coordinates are counted starting from 0. If the starting coordinate is 0 and the width is 100, the ending coordinate will be 99, for a total of 100 pixels.

[0076] To facilitate subsequent area merging, either start and end coordinates can be used, or start coordinates plus width and height can be used. When using start coordinates plus width and height, the horizontal and vertical start coordinates of the control's display area are directly taken from the UI control's placement position. The horizontal dimension of the control's display area is equal to the control's width, and the vertical dimension is equal to the control's height.

[0077] The above calculations are performed for each target UI control individually, resulting in multiple control display areas equal to the number of target UI controls. Each control display area is a rectangular area that contains all the pixels occupied by the UI control on the LCD screen.

[0078] S43a. Merge the display areas of all target UI controls to generate a merged display area.

[0079] The display areas of all controls determined in step S42a are merged to generate a merged display area. This merged display area is the smallest rectangular area that can encompass all the display areas of all controls.

[0080] The specific method for merging is as follows: Find the minimum horizontal start coordinate value, the minimum vertical start coordinate value, the maximum horizontal end coordinate value, and the maximum vertical end coordinate value from all control display areas. The minimum horizontal start coordinate value is equal to the minimum horizontal start coordinate value among all control display areas. The minimum vertical start coordinate value is equal to the minimum vertical start coordinate value among all control display areas. The maximum horizontal end coordinate value is equal to the maximum horizontal end coordinate value among all control display areas. The maximum vertical end coordinate value is equal to the maximum vertical end coordinate value among all control display areas.

[0081] The smallest horizontal starting coordinate value is used as the horizontal starting coordinate of the merged display area, the smallest vertical starting coordinate value is used as the vertical starting coordinate of the merged display area, and the largest horizontal ending coordinate value is used as the horizontal ending coordinate of the merged display area, and the largest vertical ending coordinate value is used as the vertical ending coordinate of the merged display area. Therefore, the horizontal and vertical starting coordinates of the merged display area are both the minimum values ​​in their respective directions across all control display areas, and the horizontal and vertical ending coordinates of the merged display area are both the maximum values ​​in their respective directions across all control display areas.

[0082] The horizontal dimension of the merged display area is equal to the horizontal end coordinate of the merged display area minus the horizontal start coordinate of the merged display area. The vertical dimension of the merged display area is equal to the vertical end coordinate of the merged display area minus the vertical start coordinate of the merged display area. When it is necessary to maintain the four-parameter expression method consistent with the layout position, the merged display area can also be expressed as four parameters: horizontal start coordinate, vertical start coordinate, horizontal dimension, and vertical dimension.

[0083] It should be noted that the area of ​​the merged display area may be larger than the sum of the areas of all control display areas minus the overlap between the control display areas, because the merged display area includes the blank gap areas between the control display areas. Although these blank gap areas are not occupied by any UI control, they will be lit up in subsequent steps because they are located inside the merged display area.

[0084] S44a. Determine the position and size of the target illuminated area based on the merged display area.

[0085] The position and size of the target illuminated area are determined based on the merged display area generated in step S43a. In this embodiment, the merged display area is directly determined as the target illuminated area. That is, the horizontal starting coordinate of the target illuminated area is equal to the horizontal starting coordinate of the merged display area, the vertical starting coordinate of the target illuminated area is equal to the vertical starting coordinate of the merged display area, the horizontal size of the target illuminated area is equal to the horizontal size of the merged display area, and the vertical size of the target illuminated area is equal to the vertical size of the merged display area.

[0086] The position and size information of the target illuminated area are stored in an internal register as four parameters: the horizontal starting coordinates, the vertical starting coordinates, the horizontal dimension, and the vertical dimension. In subsequent steps, these four parameters are used to control the backlight driving circuit and display driving circuit of the LCD screen to illuminate the area.

[0087] In other embodiments of this application, edge expansion processing can be performed on the merged display area. A preset number of pixels are added to the outer edges of the merged display area in each of the four directions as an expansion margin, thereby generating an expanded illuminated area slightly larger than the merged display area as the target illuminated area. The value of this expansion margin can be set to any value between 2 and 10 pixels. The advantage of this expansion processing is that it avoids the problem of incomplete display of UI control edges due to calculation accuracy errors, ensuring that the content of all target UI controls is fully presented.

[0088] In one possible implementation, determining the target illuminated area on the display screen based on the placement position of at least one target UI control on the display screen includes: S41b. Determine the initial illumination area based on the placement of at least one target UI control on the display screen.

[0089] Based on the placement of all target UI controls on the LCD screen as determined in step three, a preliminary illumination area is identified. This preliminary illumination area is an initial, un-sized rectangular region, which serves as the base area for subsequent trimming.

[0090] First, the placement position of each target UI control on the LCD screen is obtained one by one. The placement position of each UI control is defined by four parameters: horizontal starting coordinate, vertical starting coordinate, control width, and control height. The horizontal starting coordinate represents the pixel distance of the left boundary of the UI control from the left edge of the LCD screen in the horizontal direction. The vertical starting coordinate represents the pixel distance of the top boundary of the UI control from the top edge of the LCD screen in the vertical direction. The control width represents the number of pixels occupied by the UI control in the horizontal direction, and the control height represents the number of pixels occupied by the UI control in the vertical direction.

[0091] Based on the placement of each target UI control, determine the display area of ​​each target UI control on the LCD screen. For any target UI control, the horizontal starting coordinate of its display area is equal to the horizontal starting coordinate of the UI control, the vertical starting coordinate is equal to the vertical starting coordinate of the UI control, the horizontal ending coordinate is equal to the horizontal starting coordinate plus the width of the UI control, and the vertical ending coordinate is equal to the vertical starting coordinate plus the height of the UI control.

[0092] After obtaining the display areas of all target UI controls, find the minimum horizontal start coordinate value, the minimum vertical start coordinate value, the maximum horizontal end coordinate value, and the maximum vertical end coordinate value from these display areas. The minimum horizontal start coordinate value is equal to the minimum of the horizontal start coordinates of all control display areas, the minimum vertical start coordinate value is equal to the minimum of the vertical start coordinates of all control display areas, and the maximum horizontal end coordinate value is equal to the maximum of the horizontal end coordinates of all control display areas.

[0093] The smallest horizontal starting coordinate value is used as the horizontal starting coordinate of the initial illuminated area, and the smallest vertical starting coordinate value is used as the vertical starting coordinate of the initial illuminated area. The largest horizontal ending coordinate value is used as the horizontal ending coordinate of the initial illuminated area, and the largest vertical ending coordinate value is used as the vertical ending coordinate of the initial illuminated area. The horizontal dimension of the initial illuminated area is equal to the horizontal ending coordinate minus the horizontal starting coordinate, and the vertical dimension of the initial illuminated area is equal to the vertical ending coordinate minus the vertical starting coordinate.

[0094] The initial illuminated area is actually the smallest bounding rectangle that includes the display areas of all target UI controls. It contains not only the display areas of each target UI control, but also the blank gaps between these display areas.

[0095] S42b: Obtain the non-essential display areas in the initial illuminated area that are unrelated to the target event.

[0096] After determining the initial illuminated area, the non-essential display areas unrelated to the target event within this initial illuminated area are further identified. These non-essential display areas refer to pixel regions within the initial illuminated area that do not belong to the display area of ​​any target UI control. Although these pixel regions are located within the boundary of the initial illuminated area, they are not content that the target event needs to display on the LCD screen, and therefore belong to non-essential areas that do not need to be illuminated or refreshed.

[0097] The position and range of the display area of ​​each target UI control within the initial illuminated area are obtained one by one. Then, all pixel areas within the initial illuminated area that do not belong to the display area of ​​any target UI control are identified as unnecessary display areas. The specific method for obtaining unnecessary display areas is as follows.

[0098] The entire rectangular area of ​​the initially illuminated region is taken as the whole set region, and the display area of ​​all target UI controls is taken as the subset region. The union of all subset regions is subtracted from the whole set region, and the remaining part is the unnecessary display area.

[0099] In actual calculations, unnecessary display areas are usually not continuous rectangular areas, but rather composed of multiple scattered rectangular areas. For example, the gap between two horizontally arranged UI controls, the interval between vertically arranged UI controls, and the margin area between UI controls and the boundary of the initially illuminated area are all considered unnecessary display areas.

[0100] When identifying unnecessary display areas, each pixel within the initially illuminated area can be scanned line by line to determine if it belongs to the display area of ​​any target UI control. If not, the pixel is marked as unnecessary. The set of all pixels marked as unnecessary constitutes the unnecessary display area. Alternatively, geometric calculations can be used to quickly calculate the overall extent of the unnecessary display area by performing intersection, union, and complement operations on rectangular regions.

[0101] After identifying the unnecessary display areas, the location information of these areas is stored in the internal memory. This location information includes at least the horizontal starting coordinates, vertical starting coordinates, horizontal dimensions, and vertical dimensions of the unnecessary display area on the LCD screen. When the unnecessary display area consists of multiple dispersed sub-regions, the location information of each sub-region is stored separately.

[0102] S43b: Remove unnecessary display areas from the initially illuminated area to generate a size-optimized illuminated area.

[0103] Unnecessary display areas are cropped from the initially illuminated area to generate a size-optimized illuminated area. The purpose of cropping is to remove unnecessary parts of the initially illuminated area, making the final illuminated area as compact as possible.

[0104] The specific method for performing the cropping operation on unnecessary display areas is as follows: Within the initially illuminated area, the display areas of all target UI controls are preserved, while all pixels marked as unnecessary display areas are removed. After cropping, the size-optimized illuminated area includes the display areas of all target UI controls, while excluding blank gaps and edge blank areas between control display areas.

[0105] It is important to note that the size-optimized illuminated area may no longer be a single, complete rectangular region, but rather a collection of multiple separate sub-regions. Each sub-region corresponds to the display area of ​​a target UI control, or to a merged area of ​​the display areas of multiple adjacent or partially overlapping UI controls. When the display areas of multiple target UI controls are spatially non-intersecting and spaced apart, the size-optimized illuminated area will contain multiple separate sub-regions.

[0106] When generating the size-optimized illuminated area, the position and size information of each sub-region are recorded, including the horizontal starting coordinates, vertical starting coordinates, horizontal dimensions, and vertical dimensions of each sub-region. For an illuminated area composed of multiple sub-regions, this information is stored sequentially according to the position order of the sub-regions on the LCD display screen.

[0107] In a preferred embodiment of this application, during the cropping operation, instead of removing all unnecessary display areas within the initially illuminated area, a portion of the unnecessary display areas is retained as a visual buffer area. Specifically, a buffer margin with a preset width of 2 to 5 pixels is retained outside the control display area of ​​each target UI control. Although this buffer margin belongs to the unnecessary display area, it is retained to prevent the edges of the UI controls from being too close to the boundaries of the illuminated area, thus avoiding a visually oppressive feeling. It also provides display margin for slight positional changes of the UI controls.

[0108] S44b: Determine the size-optimized illuminated area as the target illuminated area.

[0109] The size-optimized illuminated area is defined as the target illuminated area. The target illuminated area is the area where the LCD display will be actually illuminated in subsequent steps.

[0110] When the size-optimized illuminated area contains multiple separate sub-regions, the target illuminated area also contains multiple separate sub-regions. The position and size information of each sub-region are stored separately, including its horizontal starting coordinates, vertical starting coordinates, horizontal dimensions, and vertical dimensions. In subsequent steps, an illumination operation will be performed for each sub-region separately; that is, the backlight driving circuit and display driving circuit of the LCD screen will provide independent illumination drive for each sub-region.

[0111] When the target illumination area contains multiple separate sub-regions, it is necessary to control the backlight partition and pixel area corresponding to each sub-region separately. Specifically, a corresponding pulse width modulation control signal is generated for each sub-region to control the on / off state of the backlight partition covered by each sub-region, and pixel data is written to the pixel array covered by each sub-region.

[0112] Compared to the implementation methods in steps S41a to S44a, this implementation method optimizes the target illuminated area from a single rectangular area into a set that may contain multiple sub-regions by trimming unnecessary display areas in the initially illuminated area. Each sub-region precisely corresponds to the control display area of ​​one or a group of target UI controls. This optimization method further reduces the area that needs to be illuminated, and the effect is more significant, especially when the target UI controls are distributed across the LCD screen.

[0113] The following are embodiments of the apparatus described in this application, which can be used to execute the embodiments of the method described in this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method described in this application.

[0114] Please see Figure 3 This illustration shows a schematic diagram of the structure of a display control device for a video surveillance equipment provided in an exemplary embodiment of this application, hereinafter referred to as device 3. Device 3 can be implemented as all or part of the video surveillance equipment through software, hardware, or a combination of both. Device 3 includes: The acquisition module 301 is used to acquire audio and video data and send the audio and video data to the cloud server; receive AI detection events returned by the cloud server and write the AI ​​detection events into the event queue; wherein, the event queue is also used to store user operation events and timer events, and the AI ​​detection events, the user operation events and the timer events respectively carry their respective event type identifiers; The calculation module 302 is used to calculate the scheduling score of each pending event according to the priority and waiting time of each pending event in the event queue, and dequeue the pending event with the highest scheduling score from the event queue as the target event; The determining module 303 is used to determine the target display duration corresponding to the event type identifier from a preset mapping relationship based on the event type identifier carried by the target event, and to determine at least one target UI control corresponding to the event type identifier; The determining module 303 is further configured to determine a target illuminated area on the display screen based on the placement position of the at least one target UI control on the display screen; The control module 304 is used to control the target illuminated area of ​​the display screen to be lit according to the target display duration; The refresh module 305 is used to perform a display state refresh action only on the at least one target UI control within the target illuminated area of ​​the display screen, based on the state information of the target event.

[0115] For other details regarding the implementation of the above technical solution by each module in the display control device of the above video surveillance equipment, please refer to the description in the display control method of the video surveillance equipment provided in the above-mentioned embodiments of the invention, which will not be repeated here.

[0116] It should be noted that the above-described embodiment of the device 3, when executing the display control method for video surveillance equipment, only exemplifies the division of the above-described functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the above functions. Furthermore, the display control device for video surveillance equipment provided in the above-described embodiment and the display control method embodiment for video surveillance equipment belong to the same concept, and their implementation process is detailed in the method embodiment, which will not be repeated here.

[0117] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0118] See Figure 4 The diagram shown is a schematic of a computer storage medium provided in an embodiment of this application. The computer storage medium can store multiple instructions (i.e., ... Figure 4 The computer program shown above), the instructions are adapted to be loaded and executed by a processor as described above. Figure 2 The method steps of the illustrated embodiment can be found in the following documentation for detailed execution. Figure 2 The specific details of the illustrated embodiments will not be elaborated here.

[0119] This application also provides a computer program product that stores at least one instruction, which is loaded and executed by the processor to implement the display control method of the video surveillance device as described in the above embodiments.

[0120] Please see Figure 5This document provides a structural schematic diagram of a video surveillance device according to an embodiment of this application. Figure 5 As shown, the video surveillance device 500 may include: at least one processor 501, a wireless communication module 504, a display screen 503, a memory 505, an image sensor 506, a sound sensor 507, and a battery. Figure 5 (not shown in the drawing), and at least one communication bus 502.

[0121] The communication bus 502 is used to enable communication between these components.

[0122] The processor 501 is the core control unit of the video surveillance equipment 500, and it is communicatively connected to other components in the video surveillance equipment 500 via the communication bus 502. The processor 501 executes the computer program stored in the memory 505 to control the overall operation of the video surveillance equipment 500 and implement the display control steps in the various method embodiments of this application. The processor 501 can be a central processing unit, a digital signal processor, an application-specific integrated circuit, a field-programmable gate array, or other programmable logic devices.

[0123] The display screen 503 is located on the front of the housing of the video surveillance equipment 500 and is used to display the operating status information of the video surveillance equipment 500, the prompts for AI-detected events, and the user interface. The display screen 503 can be an LCD screen or an OLED screen.

[0124] The wireless communication module 504 is used to realize wireless data transmission between the video surveillance device 500 and the cloud server. This wireless communication module 504 can be a wireless fidelity communication module compliant with the 802.11 series standards, or it can be a cellular network-based communication module. The video surveillance device 500 sends the audio and video data collected by the image sensor 506 and the sound sensor 507 to the cloud server through the wireless communication module 504, and also receives AI detection events returned by the cloud server through the same wireless communication module 504.

[0125] The memory 505 is used to store computer programs, a registered facial feature database, an event queue, and various mapping relationship configuration tables. The memory 505 can be a read-only memory, random access memory, flash memory, or other media capable of data storage. When the computer program stored in the memory 505 is executed by the processor 501, the processor 501 performs all or part of the steps in the various method embodiments of this application. The memory 505 also stores the mapping relationship between event type identifiers and display durations, as well as the mapping relationship between event type identifiers and UI controls. During the execution of display control, the processor 501 determines the target display duration and target UI control by querying the aforementioned mapping relationships in the memory 505.

[0126] Image sensor 506 is used to acquire image data within the field of view of video surveillance equipment 500. Image sensor 506 can be a complementary metal-oxide-semiconductor (CMOS) image sensor, and its output format is YUV or RGB raw image data. Processor 501 controls the acquisition timing of image sensor 506 according to a preset sampling frame rate.

[0127] The sound sensor 507 is used to collect audio data from the environment in which the video surveillance equipment 500 is located. The sound sensor 507 can be a microelectromechanical system (MEMS) microphone, and its output format is pulse density modulation or an audio data stream in the format of an integrated circuit's built-in audio bus. The processor 501 controls the acquisition timing of the sound sensor 507 according to a preset sampling rate.

[0128] The battery provides power to all components of the video surveillance equipment 500. Because the video surveillance equipment 500 is battery-powered, it does not require external power cables, offers flexible installation options, and can adapt to various security monitoring scenarios. The battery can be a rechargeable lithium battery, and its capacity can be selected according to actual needs to meet the equipment's requirements for long-term battery life.

[0129] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory, or random access memory, etc.

[0130] The above-disclosed embodiments are merely preferred embodiments of this application and should not be construed as limiting the scope of this application. Therefore, any equivalent variations made in accordance with the claims of this application shall still fall within the scope of this application.

Claims

1. A display control method for a video surveillance device, characterized in that, A method for use with video surveillance equipment having a display screen, the video surveillance equipment being communicatively connected to a cloud server, the cloud server being deployed with a pre-trained AI detection model, the method comprising: Acquire audio and video data and send the audio and video data to the cloud server; receive AI detection events returned by the cloud server and write the AI ​​detection events into an event queue; wherein, the event queue is also used to store user operation events and timer events, and the AI ​​detection events, the user operation events and the timer events each carry their respective event type identifiers; Based on the priority and waiting time of each pending event in the event queue, the scheduling score of each pending event is calculated, and the pending event with the highest scheduling score is dequeued from the event queue as the target event. Based on the event type identifier carried by the target event, determine the target display duration corresponding to the event type identifier from the preset mapping relationship, and determine at least one target UI control corresponding to the event type identifier; Based on the placement position of the at least one target UI control on the display screen, determine the target illuminated area on the display screen; According to the target display duration, control the target illuminated area of ​​the display screen to be lit; Within the target illuminated area of ​​the display screen, the display state refresh action is performed only on the at least one target UI control based on the state information of the target event.

2. The method according to claim 1, characterized in that, Determining the target illuminated area on the display screen based on the placement position of the at least one target UI control on the display screen includes: Obtain the placement position of each of the at least one target UI controls on the display screen; Based on the placement of each target UI control, determine the control display area of ​​each target UI control on the display screen; The display areas of all target UI controls are merged to generate a merged display area; The position and size of the target illuminated area are determined based on the merged display area.

3. The method according to claim 2, characterized in that, The process of merging the display areas of all target UI controls to generate a merged display area includes: Based on the display area of ​​all target UI controls, obtain the boundary coordinate information of the display area of ​​each control; Based on the boundary coordinate information, determine the minimum and maximum coordinate values ​​of the display areas of all controls in the horizontal direction, and use them as the horizontal boundaries; Based on the boundary coordinate information, determine the minimum and maximum coordinate values ​​of all control display areas in the vertical direction, which serve as the vertical boundary; The rectangular area defined by the horizontal boundary and the vertical boundary shall be used as the merged display area.

4. The method according to claim 1, characterized in that, Determining the target illuminated area on the display screen based on the placement position of the at least one target UI control on the display screen includes: The initial illumination area is determined based on the placement of the at least one target UI control on the display screen; Obtain the unnecessary display areas in the initial illuminated area that are unrelated to the target event; The unnecessary display area in the initial illuminated area is cropped out to generate an optimized illuminated area; The size-optimized illuminated area is determined as the target illuminated area.

5. The method according to claim 1, characterized in that, The step of calculating the scheduling score for each pending event based on its priority and waiting time in the event queue includes: Obtain the priority parameter of the event to be processed, and obtain the enqueue timestamp and current timestamp of the event to be processed; The waiting time for the pending event is determined based on the difference between the current timestamp and the enqueue timestamp. Multiply the priority parameter by a preset priority weighting coefficient to obtain the priority weighting value; Multiply the waiting time by a preset waiting time weighting coefficient to obtain a waiting time weighted value; the sum of the waiting time weighting coefficient and the priority weighting coefficient is equal to 1; The priority weighted value is added to the waiting time weighted value to obtain the scheduling score.

6. The method according to claim 1, characterized in that, The step of controlling the target illuminated area of ​​the display screen to illuminate according to the target display duration includes: Obtain the location and size information of the target illuminated area on the display screen; Based on the region location information and the region size information, generate a region lighting control signal corresponding to the target lighting region; The area lighting control signal is sent to the driver of the display screen to control the driver to perform the lighting operation only on the target lighting area; Start the timer to begin counting based on the target display duration; When the timer reaches the target display duration, a zone turn-off control signal is generated; The area extinguishing control signal is sent to the driver of the display screen to control the driver to extinguish the target illuminated area.

7. The method according to claim 1, characterized in that, Within the target illuminated area of ​​the display screen, the display state refresh action is performed only on the at least one target UI control based on the state information of the target event, including: Read the status information carried by the target event; the status information is used to identify the current business processing stage of the target event; Based on the business processing stage identified by the status information, determine the content to be displayed for each of the at least one target UI control; Based on the content to be displayed, generate refresh pixel data corresponding to each of the at least one target UI control; The refresh pixel data is written into the display buffer corresponding to the target illuminated area to update the display state of the at least one target UI control.

8. The method according to claim 1, characterized in that, The acquisition of audio and video data includes: Image data is acquired through an image sensor, and audio data is acquired through a sound sensor. The image data and audio data are then aligned with timestamps to generate audio and video data.

9. A display control device for a video surveillance equipment, characterized in that, include: The acquisition module is used to acquire audio and video data and send the audio and video data to the cloud server; receive AI detection events returned by the cloud server and write the AI ​​detection events into the event queue; wherein, the event queue is also used to store user operation events and timer events, and the AI ​​detection events, the user operation events and the timer events each carry their respective event type identifiers; The calculation module is used to calculate the scheduling score of each pending event based on the priority and waiting time of each pending event in the event queue, and to dequeue the pending event with the highest scheduling score from the event queue as the target event. The determination module is used to determine the target display duration corresponding to the event type identifier from a preset mapping relationship based on the event type identifier carried by the target event, and to determine at least one target UI control corresponding to the event type identifier; The determining module is further configured to determine a target illuminated area on the display screen based on the placement position of the at least one target UI control on the display screen; The control module is used to control the target illuminated area of ​​the display screen to be lit according to the target display duration; A refresh module is used to perform a display state refresh action only on the at least one target UI control within the target illuminated area of ​​the display screen, based on the state information of the target event.

10. A video surveillance device, characterized in that, include: The device includes a display screen, a battery, a processor, and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and execute the steps of the display control method of the video surveillance device as claimed in any one of claims 1 to 8.

Images