Monitoring method based on AI holder searchlight and related equipment

Abstract

The invention discloses a monitoring method based on an AI holder searchlight and related equipment, relates to the technical field of computer vision, and discloses the monitoring method based on the AI holder searchlight, and the method comprises the steps: obtaining a video image in a preset monitoring range in real time; detecting whether a target object presented in the video image is a risk target; and if the target object is the risk target, controlling a searchlight to irradiate the target object and generate an alarm sound until the target object cannot be detected. When the camera device detects the risk target in the monitoring range, the searchlight is controlled to irradiate the target object and generate the alarm sound, so that the risk target is alarmed and repelled, the safety protection effect of the camera is improved, and the use experience of a user is improved.

Description

Technical Field

[0001] The present application relates to the field of computer vision technology, and in particular to a monitoring method and related equipment based on an AI pan-tilt searchlight. Background Art

[0002] At present, with the development of society and the advancement of science and technology, surveillance cameras have become an important part of home and business security. Among them, surveillance cameras are not only used in the fields of business and public security, but also widely used in personal residences to enhance home security. Specifically, home users install surveillance cameras mainly for anti-theft, fire prevention, monitoring the safety of children and the elderly, etc.

[0003] In the related art, the camera usually sends real-time images within the monitoring range to the user end so that the user can view the monitoring images in real time. However, this method is not effective in preventing strangers from intruding, that is, the security prevention effect of the camera is low, which leads to poor user experience.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of this application is to provide a monitoring method based on AI pan-tilt searchlight, aiming to solve the technical problem that the security prevention effect of the camera is poor, resulting in poor user experience.

[0006] To achieve the above purpose, the present application proposes a monitoring method based on an AI PTZ searchlight, and the monitoring method based on the PTZ searchlight includes:

[0007] Acquire video images within the preset monitoring range in real time;

[0008] Detecting whether a target object presented in the video image is a risky target;

[0009] If the target object is a risky target, the searchlight is controlled to illuminate the target object and generate an alarm sound until the target object cannot be detected.

[0010] Optionally, the step of controlling the searchlight to illuminate the target object and generate an alarm sound until the target object cannot be detected includes:

[0011] Collecting the dynamic motion trajectory of the target object;

[0012] While continuously generating the alarm sound, the searchlight is controlled to illuminate the target object according to the dynamic motion trajectory until the target object cannot be detected.

[0013] Optionally, the step of collecting the dynamic motion trajectory of the target object includes:

[0014] Converting the video image into a plurality of image frames;

[0015] Based on the image frame, feature data detection is performed through a preset target tracking model to obtain a 3D detection frame of the target object;

[0016] Based on the 3D detection frame, the target object is tracked to obtain a target tracking result, and based on the target tracking result, a position prediction is performed on the target object to obtain a prediction result;

[0017] Based on the target tracking result and the prediction result, a dynamic motion trajectory of the target object is generated.

[0018] Optionally, if the target object is a risky target, the step of controlling a searchlight to illuminate the target object and generate an alarm sound until the target object cannot be detected includes:

[0019] If the target object is a risky target, determining first color temperature information;

[0020] While generating the alarm sound, the searchlight is controlled to illuminate the target object with light corresponding to the first color temperature information until the target object cannot be detected.

[0021] Optionally, after the step of controlling the searchlight to illuminate the target object and generate an alarm sound if the target object is a risky target until the target object cannot be detected, the method includes:

[0022] If the target object is not a risky target, determining second color temperature information;

[0023] The lighting lamp is turned on to generate light corresponding to the second color temperature information, and the searchlight is controlled to irradiate light corresponding to the second color temperature information in the direction of the preset movement range of the target object, rather than irradiating the target object.

[0024] Optionally, the step of controlling the searchlight to illuminate the target object in a direction of a preset movement range according to the second color temperature information includes:

[0025] Collecting the dynamic motion trajectory of the target object;

[0026] According to the dynamic motion trajectory, the searchlight is controlled to illuminate the target object in the direction of the preset motion range corresponding to the second color temperature information.

[0027] Optionally, the step of determining the second color temperature information includes:

[0028] Converting the video image into a plurality of image frames, and extracting environmental features from the image frames;

[0029] Based on the environmental characteristics, a color temperature adaptation analysis is performed through a preset color temperature control model to obtain second color temperature information, wherein the color temperature control model is obtained by training a preset model to be trained based on environmental feature samples and color temperature information labels of the environmental feature samples.

[0030] Optionally, before the step of converting the video image into a plurality of image frames and extracting environmental features from the image frames, the method includes:

[0031] Acquire an environmental characteristic sample and a color temperature information label of the environmental characteristic sample;

[0032] Based on the environmental feature samples and the color temperature information labels, the preset model to be trained is iteratively trained to obtain a color temperature control model.

[0033] Optionally, the step of iteratively training a preset model to be trained based on the environmental feature sample and the color temperature information label to obtain a color temperature control model includes:

[0034] Determining time information of the environmental characteristic sample;

[0035] Based on the time information, determining a corresponding time weight;

[0036] Based on the environmental feature samples, the color temperature information labels and the time weights, the preset model to be trained is iteratively trained to obtain a color temperature control model.

[0037] Optionally, the step of iteratively training a preset model to be trained based on the environmental feature sample, the color temperature information label and the time weight to obtain a color temperature control model includes:

[0038] Based on the environmental feature samples and the time weight, a color temperature adaptation analysis is performed through a preset model to be trained to obtain a color temperature output result;

[0039] Calculate the difference between the color temperature output result and the color temperature information label to obtain an error result;

[0040] Based on the error result, determining whether the error result meets an error standard indicated by a preset error threshold range;

[0041] If the error result does not meet the error standard indicated by the preset error threshold range, return to the step of performing color temperature adaptation analysis based on the environmental feature sample and the time weight through the preset model to be trained to obtain the color temperature output result, and stop training until the error result meets the error standard indicated by the preset error threshold range to obtain the color temperature control model.

[0042] In addition, to achieve the above purpose, the present application also proposes a monitoring device based on a pan-tilt searchlight, and the monitoring device based on a pan-tilt searchlight includes:

[0043] An acquisition module is used to acquire video images within a preset monitoring range in real time;

[0044] A detection module, used to detect whether the target object presented in the video image is a risk target;

[0045] The control module is used to control the searchlight to illuminate the target object and generate an alarm sound if the target object is a risky target until the target object cannot be detected.

[0046] Optionally, the control module includes:

[0047] A first acquisition module, used to acquire the dynamic motion trajectory of the target object;

[0048] The irradiation module is used to control the searchlight to irradiate the target object according to the dynamic motion trajectory while continuously generating the alarm sound until the target object cannot be detected.

[0049] Optionally, the first acquisition module includes:

[0050] A first conversion module, used for converting the video image into a plurality of image frames;

[0051] A target detection module is used to detect feature data based on the image frame through a preset target tracking model to obtain a 3D detection frame of the target object;

[0052] A tracking module, configured to track the target object based on the 3D detection frame to obtain a target tracking result, and predict the position of the target object based on the target tracking result to obtain a prediction result;

[0053] A generation module is used to generate a dynamic motion trajectory of the target object based on the target tracking result and the prediction result.

[0054] Optionally, the control module further includes:

[0055] a determination module, configured to determine first color temperature information if the target object is a risky target;

[0056] The first lighting irradiation module is used to control the searchlight to irradiate the target object with light corresponding to the first color temperature information while generating an alarm sound until the target object cannot be detected.

[0057] Optionally, the monitoring device based on the AI ​​PTZ searchlight further includes:

[0058] a color temperature determination module, configured to determine second color temperature information if the target object is not a risky target;

[0059] The searchlight control module is used to turn on the lighting lamp to generate light corresponding to the second color temperature information, and control the searchlight to irradiate light corresponding to the second color temperature information in the direction of a preset movement range of the target object, rather than irradiating the target object.

[0060] Optionally, the searchlight control module includes:

[0061] A second acquisition module, used to acquire the dynamic motion trajectory of the target object;

[0062] The second lighting irradiation module is used to control the searchlight to irradiate the target object in the direction of the preset movement range according to the dynamic motion trajectory, corresponding to the second color temperature information.

[0063] Optionally, the color temperature determination module includes:

[0064] An environmental feature extraction module, used for converting the video image into a plurality of image frames and extracting environmental features from the image frames;

[0065] The analysis module is used to perform color temperature adaptation analysis based on the environmental characteristics through a preset color temperature control model to obtain second color temperature information, wherein the color temperature control model is obtained by training a preset model to be trained based on environmental feature samples and color temperature information labels of the environmental feature samples.

[0066] Optionally, the monitoring device based on the AI ​​PTZ searchlight further includes:

[0067] A sample acquisition module, used to acquire an environmental feature sample and a color temperature information label of the environmental feature sample;

[0068] The training module is used to iteratively train the preset model to be trained based on the environmental feature samples and the color temperature information labels to obtain a color temperature control model.

[0069] Optionally, the training module includes:

[0070] A time information determination module, used to determine the time information of the environmental feature sample;

[0071] A time weight determination module, used to determine a corresponding time weight based on the time information;

[0072] The color temperature control model training module is used to iteratively train the preset model to be trained based on the environmental feature samples, the color temperature information labels and the time weights to obtain the color temperature control model.

[0073] Optionally, the color temperature control model training module includes:

[0074] A color temperature adaptation analysis module, used to perform color temperature adaptation analysis based on the environmental feature samples and the time weight through a preset model to be trained to obtain a color temperature output result;

[0075] A difference calculation module, used for performing difference calculation between the color temperature output result and the color temperature information label to obtain an error result;

[0076] A judgment module, configured to judge, based on the error result, whether the error result satisfies an error standard indicated by a preset error threshold range;

[0077] The iterative training module is used to return to the step of performing color temperature adaptation analysis based on the environmental feature sample and the time weight through a preset model to be trained to obtain a color temperature output result if the error result does not meet the error standard indicated by the preset error threshold range, and stop training until the error result meets the error standard indicated by the preset error threshold range to obtain a color temperature control model.

[0078] In addition, to achieve the above-mentioned purpose, the present application also proposes a monitoring device based on a pan-tilt searchlight, the device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the monitoring method based on the AI ​​pan-tilt searchlight as described above.

[0079] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the monitoring method based on the AI ​​pan-tilt searchlight as described above are implemented.

[0080] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the monitoring method based on the AI ​​pan-tilt searchlight as described above.

[0081] One or more technical solutions proposed in this application have at least the following technical effects:

[0082] Compared with the related art, the camera usually sends real-time images within the monitoring range to the user end so that the user can view the monitoring images in real time. However, this method is not effective in preventing intrusion by strangers, that is, the security prevention effect of the camera is low, which leads to a poor user experience. In comparison, the present application obtains video images within a preset monitoring range in real time, detects whether the target object presented in the video image is a risk target, and if the target object is a risk target, controls the searchlight to illuminate the target object and generate an alarm sound until the target object cannot be detected. It is understandable that when the camera device of the present application detects a risk target within the monitoring range, it controls the searchlight to illuminate the target object and generate an alarm sound to warn and drive away the risk target, thereby improving the security prevention effect of the camera and thus improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0084] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0085] Figure 1 A flowchart diagram of the first embodiment of the monitoring method based on the AI ​​PTZ searchlight of the present application;

[0086] Figure 2 This is a schematic diagram of an application scenario of the monitoring method based on the AI ​​PTZ searchlight of this application;

[0087] Figure 3 This is a schematic diagram of color temperature division for the monitoring method based on AI PTZ searchlight in this application;

[0088] Figure 4 A flowchart diagram of the second embodiment of the monitoring method based on the AI ​​PTZ searchlight of the present application;

[0089] Figure 5 A schematic diagram of the structure of a surveillance camera for the surveillance method based on the AI ​​PTZ searchlight of this application;

[0090] Figure 6 A flowchart diagram of the third embodiment of the monitoring method based on the AI ​​PTZ searchlight of the present application;

[0091] Figure 7 This is a schematic diagram of the module structure of a monitoring device based on a pan-tilt searchlight according to an embodiment of the present application;

[0092] Figure 8 This is a schematic diagram of the device structure of the hardware operating environment involved in the monitoring method based on the AI ​​PTZ searchlight in the embodiment of the present application.

[0093] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0094] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0095] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0096] The main solution of the embodiment of the present application is: to acquire video images within a preset monitoring range in real time; to detect whether the target object presented in the video image is a risky target; if the target object is a risky target, to control the searchlight to illuminate the target object and generate an alarm sound until the target object cannot be detected.

[0097] In this embodiment, a monitoring device based on a pan-tilt searchlight is used as the execution subject. For the convenience of description, it will be described as a "device" hereinafter.

[0098] In the related art, the camera usually sends real-time images within the monitoring range to the user end so that the user can view the monitoring images in real time. However, this method has poor effect in preventing strangers from intruding, that is, the security prevention effect of the camera is low, which leads to poor user experience.

[0099] This application provides a solution to achieve the warning and expulsion of risky targets, thereby improving the security prevention effect of the camera and further improving the user experience.

[0100] From the above embodiments, it can be seen that the present application acquires the video image within the preset monitoring range in real time, detects whether the target object presented in the video image is a risk target, and if the target object is a risk target, controls the searchlight to illuminate the target object and generates an alarm sound until the target object cannot be detected. It is understandable that when the camera device of the present application detects a risk target within the monitoring range, it controls the searchlight to illuminate the target object and generates an alarm sound to warn and drive away the risk target, thereby improving the safety precautions of the camera and further enhancing the user experience.

[0101] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device, a terminal device, etc. that can realize the above functions. The following takes a monitoring device based on a pan-tilt searchlight as an example to illustrate this embodiment and the following embodiments.

[0102] Based on this, the embodiment of the present application provides a monitoring method based on AI PTZ searchlight, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the monitoring method based on the AI ​​PTZ searchlight of the present application.

[0103] In this embodiment, the monitoring method based on the AI ​​PTZ searchlight includes steps S100 to S300:

[0104] Step S100, acquiring video images within a preset monitoring range in real time;

[0105] It should be noted that the preset monitoring range refers to a monitoring area that is determined and set in advance. This area is selected based on security considerations, monitoring needs or other purposes. The preset monitoring range can be fixed or an electronic fence set by software; the video image refers to a continuous image sequence captured by a surveillance camera, and these image sequences constitute a video stream.

[0106] In the specific implementation, the specific application scenarios refer to Figure 2 , the monitoring method based on AI PTZ searchlight is applied to the camera installed at the door of the user's residence. The device can obtain video images within the preset monitoring range in real time, and instantly capture and process the situation within the monitoring range without significant delay, that is, the video stream is continuous and as close to the actual time as possible. Specifically, the above describes the monitoring function of the device, that is, it can continuously capture and display real-time video images within a pre-defined monitoring area. The device is specifically used in security monitoring, remote monitoring and other fields to ensure that any abnormal activities in the monitoring area can be discovered and responded to in a timely manner.

[0107] Step S200, detecting whether the target object presented in the video image is a risky target;

[0108] It should be noted that the target object refers to a specific target in the video, specifically a person or animal within the monitoring range; the risk target refers to an unauthorized intruder or a target with suspicious behavior.

[0109] In a specific implementation, the device detects whether the target object presented in the video image is a risky target. Specifically, the device uses computer vision and deep learning algorithms to analyze the video stream, automatically identify and locate specific targets in the video, and perform risk assessment on these targets.

[0110] Furthermore, the step of the device detecting whether the target object presented in the video image is a risk target includes:

[0111] 1. Video acquisition: obtain real-time video stream through the camera;

[0112] 2. Video preprocessing: denoising, enhancing and decoding the video to obtain clear and usable video images;

[0113] 3. Video segmentation: divide the video into continuous frames and extract relevant information;

[0114] 4. Video feature extraction: Extract key features in the video, such as people, vehicles, scenes, etc., through computer vision algorithms;

[0115] 5. Target detection and tracking: Use target detection algorithms, such as YOLOv8, to identify and locate specific targets in the video and track them between consecutive frames. This step may involve the use of deep learning models, such as the YOLO series of models, which can analyze video content in real time, detect abnormal information, and thus make risk predictions and construct intelligent monitoring devices;

[0116] 6. Behavior analysis: Analyze and classify the target's behavior based on its trajectory and movements, such as human activity detection and abnormal behavior identification;

[0117] 7. Event recognition and alarm: By identifying specific events in the video, such as traffic accidents, thefts, etc., alarm notifications can be issued in a timely manner. For example, behavioral analysis can be used to understand and analyze people's behaviors and activities, sentiment analysis can be used to identify emotions and feelings, and scene analysis can be used to understand and reason about scenes, thereby achieving intelligent analysis and decision-making of video data;

[0118] 8. Risk assessment: Based on the detected targets and behavior analysis results, assess whether there is a risk or threat. For example, if an unauthorized intruder or suspicious behavior is detected, the device will trigger an alarm.

[0119] Step S300: If the target object is a risky target, the searchlight is controlled to illuminate the target object and generate an alarm sound until the target object cannot be detected.

[0120] It should be noted that a searchlight is a high-power lighting device that can produce a strong, concentrated light beam to illuminate distant objects or areas; the alarm sound can be a siren, beep or other preset sound mode to warn that a risky target has illegally entered a designated monitoring area.

[0121] In a specific implementation, the device analyzes the identified target object to determine whether it poses a security risk or threat. The risk target can be preset, such as unauthorized personnel, suspicious objects, abnormal behavior, etc. If the device determines that the target object is a risk target, it will automatically control the searchlight to illuminate the target object, that is, the device uses strong light to illuminate the risk target, combined with the generated alarm sound, to achieve the purpose of alarming and driving away the risk target, until the risk target disappears from the monitoring range, that is, the device cannot detect the target object, then stop the light beam irradiation and generate the alarm sound.

[0122] In a specific implementation, when the camera device of the present application detects a risky target within the monitoring range, it controls the searchlight to illuminate the target object and generate an alarm sound to warn and drive away the risky target, thereby improving the security prevention effect of the camera and further enhancing the user experience.

[0123] In a specific implementation, the device controls the searchlight to illuminate the target object and generate an alarm sound until the target object cannot be detected, including:

[0124] The dynamic motion trajectory of the target object is collected; while continuously generating an alarm sound, the searchlight is controlled to illuminate the target object according to the dynamic motion trajectory until the target object cannot be detected.

[0125] In the specific implementation, when the device determines that the target object is a risk target, it captures the image in real time through the video monitoring equipment, and uses computer vision technology to identify and track the target object in the image. As the target object moves, the device will record its position changes in the monitoring area, thereby collecting the dynamic motion trajectory of the target object.

[0126] In the specific implementation, after the device determines the dynamic motion trajectory of the target object, it will trigger the alarm mechanism and emit a continuous alarm sound. In addition, the device will adjust the direction of the searchlight in real time according to the dynamic motion trajectory of the target object collected to ensure that the searchlight beam is always irradiated on the target object. When the target object is no longer detected, the device will automatically stop the alarm sound and the tracking irradiation of the searchlight and restore the normal monitoring state. It is understandable that the purpose of this tracking irradiation is to keep the target object within the lighting range at all times, which is convenient for monitoring and driving away risky targets, that is, to further realize the alarm and driving away risky targets, thereby improving the security prevention effect of the camera and thus improving the user experience.

[0127] In a specific implementation, the step of collecting the dynamic motion trajectory of the target object by the device includes:

[0128] The video image is converted into multiple image frames; based on the image frames, feature data detection is performed through a preset target tracking model to obtain a 3D detection frame of the target object; based on the 3D detection frame, the target object is tracked to obtain a target tracking result, and based on the target tracking result, the position of the target object is predicted to obtain a prediction result; based on the target tracking result and the prediction result, a dynamic motion trajectory of the target object is generated.

[0129] In a specific implementation, the device first converts the video stream into a series of image frames, wherein the video is composed of continuous image frames, and each frame represents a moment of the video. Secondly, the device uses a preset target tracking model to analyze each frame of the image to detect the target object in the image and extract its feature data, wherein the detection process involves the use of a deep learning model, such as a convolutional neural network (CNN), to identify and locate the target in the image.

[0130] Furthermore, the device generates a 3D detection frame based on the detected feature data of the target object. The 3D detection frame includes not only the position of the target object in the two-dimensional image (x, y coordinates), but also the depth information of the object (z coordinate), so that the position of the target object in three-dimensional space can be more accurately described. Secondly, the device tracks the target object using a target tracking algorithm, such as a Kalman filter or a Mean-Shift algorithm. This involves matching and tracking the movement of the target object in consecutive image frames to obtain the position information of the target object over time.

[0131] In a specific implementation, the device uses a prediction algorithm to predict the position of the target object in the next few frames based on the target tracking results. The above prediction algorithm allows the device to prepare and adjust the camera or other sensors in advance to continuously track fast-moving targets. Finally, the device combines the target tracking results and the position prediction results to generate a dynamic motion trajectory of the target object. This trajectory can be two-dimensional (on the image plane) or three-dimensional (in real space), depending on the needs of the application scenario.

[0132] In the specific implementation, the above process enables the device to automatically detect, track and predict the target object in the video. In this way, the device can monitor the behavior of the target object in real time and predict its future position and movement.

[0133] In a specific implementation, if the target object is a risky target, the step of controlling the searchlight to illuminate the target object and generate an alarm sound until the target object cannot be detected includes:

[0134] If the target object is a risky target, first color temperature information is determined; while generating an alarm sound, the searchlight is controlled to illuminate the target object with light corresponding to the first color temperature information until the target object cannot be detected.

[0135] In a specific implementation, after the device identifies the risk target, the device determines the color temperature information corresponding to the risk situation. Figure 3 ,Color temperature is a physical quantity that describes the color of the light source. Different color temperatures can produce different lighting effects. For example, a warmer color temperature (such as 3000K) can create a comfortable and alert atmosphere, while a colder color temperature (such as 5000K) gives people a clear and serious feeling.

[0136] In a specific implementation, since the target object is a risky target, for the purpose of warning and driving away the risky target, the device uses cold color temperature or flashing lights to improve visibility and warning effects, and can also set high-brightness flashing lights to effectively deter suspected targets.

[0137] It should be noted that the first color temperature information and the second color temperature information are the color temperatures of light in different scenarios. The first color temperature information scenario is a scenario where the target object is a risk target, and usually a cold color temperature flashing light or a high-brightness strobe light is set, while the second color temperature information scenario is a scenario where the target object is not a risk target, and usually a warm color temperature is used to welcome guests or help the target object illuminate the road in the dark.

[0138] In the specific implementation, after identifying the risky target, this application also proposes a method of controlling the color temperature based on the light exposure, so as to further realize the warning and expulsion of the risky target, thereby improving the security prevention effect of the camera and further improving the user experience.

[0139] Compared with the related art, the camera usually sends real-time images within the monitoring range to the user end so that the user can view the monitoring images in real time. However, this method is not effective in preventing intrusion by strangers, that is, the security prevention effect of the camera is low, which leads to a poor user experience. In comparison, the present application obtains video images within a preset monitoring range in real time, detects whether the target object presented in the video image is a risk target, and if the target object is a risk target, controls the searchlight to illuminate the target object and generate an alarm sound until the target object cannot be detected. It is understandable that when the camera device of the present application detects a risk target within the monitoring range, it controls the searchlight to illuminate the target object and generate an alarm sound to warn and drive away the risk target, thereby improving the security prevention effect of the camera and thus improving the user experience.

[0140] Based on the above first embodiment, the present application also proposes another embodiment, referring to Figure 4 , the monitoring method based on AI PTZ searchlight also includes:

[0141] In a specific implementation, if the target object is a risky target, after the step of controlling the searchlight to illuminate the target object and generate an alarm sound until the target object cannot be detected, the method includes:

[0142] Step A100, if the target object is not a risk target, determining second color temperature information;

[0143] It should be noted that the first color temperature information and the second color temperature information are the color temperatures of light in different scenarios. The first color temperature information scenario is a scenario where the target object is a risk target, and usually a cold color temperature flashing light or a high-brightness strobe light is set, while the second color temperature information scenario is a scenario where the target object is not a risk target, and usually a warm color temperature is used to welcome guests or help the target object illuminate the road in the dark.

[0144] Step A200, turning on the lighting lamp to generate light corresponding to the second color temperature information, and controlling the searchlight to irradiate light corresponding to the second color temperature information in the direction of the preset movement range of the target object, rather than irradiating the target object.

[0145] In the specific implementation, refer to Figure 5, the light above the camera is a wide-range lighting light, and the light below the camera is a searchlight (tracking light). After the device determines that the target object is not a risk target and the second color temperature information, the lighting light is turned on to generate light corresponding to the second color temperature information, and the searchlight is controlled to illuminate the target object in the direction of the preset action range corresponding to the second color temperature information, rather than irradiating the target object. Among them, the searchlight does not directly illuminate the target object, but is used to illuminate the preset action range of the target object, that is, the light beam of the searchlight is directed to the area where the target object may move or enter, rather than directly irradiating the target object.

[0146] It should be noted that the searchlight beam is directed to the area where the target object may move or enter, rather than directly shining on the target object, in order to avoid strong light shining directly on the body and / or face of the legitimate user, while illuminating his possible path of movement. The lighting can highlight the vicinity of the destination (i.e., the house), so that the legitimate user can comfortably see the road ahead, thereby improving the user experience of the legitimate user.

[0147] In a specific implementation, the step of controlling the searchlight to perform light irradiation corresponding to the second color temperature information in the direction of the preset action range of the target object includes:

[0148] The dynamic motion trajectory of the target object is collected; and according to the dynamic motion trajectory, the searchlight is controlled to illuminate the target object in the direction of a preset motion range according to the second color temperature information.

[0149] In a specific implementation, the device uses a video surveillance system to collect the movement trajectory of the target object in the surveillance area. This usually involves video analysis technology, such as target detection and tracking algorithms, to identify the target object and track its position in continuous image frames, and according to the dynamic movement trajectory of the target object collected, the device automatically controls the illumination direction of the searchlight to illuminate the preset action range where the target object may move, rather than directly irradiating the target object.

[0150] Furthermore, the searchlight not only adjusts the direction of illumination, but also the color temperature of the illumination light to meet specific monitoring needs. Specifically, the illumination direction of the searchlight is set to the preset range of motion of the target object, which means that the system predicts the possible movement path of the target object and illuminates the area in advance.

[0151] In the specific implementation, the above process describes an automated monitoring system that can track the motion trajectory of the target object in real time and intelligently control the illumination direction and color temperature of the searchlight based on this information to improve the monitoring efficiency and effect.

[0152] In a specific implementation, the step of determining the second color temperature information by the device includes:

[0153] The video image is converted into a plurality of image frames, and environmental features are extracted from the image frames; based on the environmental features, a color temperature adaptation analysis is performed through a preset color temperature control model to obtain second color temperature information, wherein the color temperature control model is obtained by training a preset model to be trained based on environmental feature samples and color temperature information labels of the environmental feature samples.

[0154] In a specific implementation, the device first converts the video stream into a series of image frames. This is achieved through video processing technology, where each frame represents a moment in the video and provides basic data for subsequent processing. Secondly, the device extracts environmental features from these image frames, where the environmental features may include objects in the scene, light conditions, color distribution, etc. These features help the device understand the current environmental conditions.

[0155] Furthermore, based on the extracted environmental features, the device will perform color temperature adaptation analysis through a preset color temperature control model. This model may be trained based on previously collected environmental feature samples and their corresponding color temperature information labels, and it can determine the most suitable color temperature based on the current environmental features. The result of the color temperature adaptation analysis is the determined "second color temperature information", which is the optimal color temperature value calculated by the device based on the current environmental features and the preset model.

[0156] In a specific implementation, the device can automatically adjust the color temperature of the lighting according to real-time video images and environmental characteristics, and intelligently control the illumination direction of the searchlight to adapt to the needs of the monitoring scene, thereby improving the user experience.

[0157] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the monitoring method based on the AI ​​PTZ searchlight of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0158] Based on the above first and second embodiments, the present application also proposes another embodiment, referring to Figure 6 , the monitoring method based on AI PTZ searchlight also includes:

[0159] Before the step of converting the video image into a plurality of image frames and extracting environmental features from the image frames, the method comprises:

[0160] Step B100, obtaining an environmental feature sample and a color temperature information label of the environmental feature sample;

[0161] It should be noted that the device first obtains environmental feature samples, which involves using cameras, sensors or other data acquisition devices to collect image or video data under different environmental conditions. These data will serve as the basis for analysis and subsequent model training. Among them, environmental feature samples may include various visual elements, such as the shape, size, color, texture of objects, as well as the lighting conditions of the scene, background noise, etc.

[0162] Furthermore, for each collected environmental feature sample, the corresponding color temperature information label needs to be obtained. Color temperature is a physical quantity that describes the color of the light source, usually expressed in Kelvin (K). The color temperature information label can be manually marked or automatically measured by a device such as a color thermometer. These labels describe the lighting conditions of the sample at a specific color temperature.

[0163] Step B200, based on the environmental feature samples and the color temperature information labels, iteratively train the preset model to be trained to obtain a color temperature control model.

[0164] In the specific implementation, the device first selects or designs a preset model structure, which can accept the input environmental feature samples and output the corresponding color temperature prediction. This model is untrained before the training begins, or "to be trained", and its parameters have not yet been adjusted to the optimal state, that is, the model to be trained.

[0165] In a specific implementation, the device uses the collected environmental feature samples and color temperature information labels to train the model. The training process generally includes the following steps:

[0166] Forward propagation: input sample data and obtain predicted output through model calculation;

[0167] Loss calculation: Compare the model’s predicted output with the actual color temperature information label and calculate the loss function to evaluate the model’s prediction accuracy;

[0168] Back propagation: Based on the loss function, calculate the gradient of the model parameters to determine how to adjust the parameters to reduce the loss;

[0169] Parameter update: Update the model’s parameters using an optimization algorithm such as gradient descent.

[0170] This process goes through multiple iterations, with each iteration aiming to improve the model’s performance until the model reaches a satisfactory level of accuracy on the given dataset.

[0171] In the specific implementation, after multiple iterations of training, the model parameters are adjusted to a better state. At this time, the model can accurately predict the appropriate color temperature based on the input environmental feature samples. This trained model is called a color temperature control model, which can be used in practical applications to automatically adjust the color temperature of the light source according to real-time environmental characteristics.

[0172] It is understandable that the above process describes how to use machine learning methods to train a model that can predict color temperature using labeled environmental feature sample data. This model can automatically adjust the color temperature of the light source under different environmental conditions to adapt to the comfort of the human eye or specific application requirements.

[0173] In a specific implementation, the device iteratively trains a preset model to be trained based on the environmental feature sample and the color temperature information label to obtain a color temperature control model, including:

[0174] Determine the time information of the environmental feature sample; determine the corresponding time weight based on the time information; iteratively train the preset model to be trained based on the environmental feature sample, the color temperature information label and the time weight to obtain a color temperature control model.

[0175] In a specific implementation, the present application further proposes that when the device collects environmental characteristic samples, it also records the time information of each sample, including the specific date, time, season, and even specific time period of the day (such as morning, noon, and evening) when the sample was collected.

[0176] In a specific implementation, the device assigns a time weight to each sample based on the time information of the sample. This weight reflects the degree of influence of the time factor on the model prediction. For example, if the environmental characteristics of a certain period of time have a greater impact on the color temperature, then the samples of this period may be assigned a higher time weight.

[0177] In the specific implementation, since the same environmental feature information will have different effects in different time periods, the feature weights of the same feature information will also be different in different time periods. Therefore, it is necessary to introduce time weights to improve the accuracy of model analysis. For example, when the season when the legitimate user is monitored is summer from May to July, and the emitted light beam is warm, it will enhance the user's feeling of heat, making people feel more hot, thus generating an irritated mood, and thus reducing the user experience. Therefore, in the above case, when the season is summer from May to July, the weight of warm tones will be reduced and the weight of cold tones will be increased. Correspondingly, in winter from September to December, the weight of cold tones will be reduced and the weight of warm tones will be increased.

[0178] In a specific implementation, the device iteratively trains a preset model to be trained based on the environmental feature sample, the color temperature information label and the time weight to obtain a color temperature control model, including:

[0179] Based on the environmental feature samples and the time weights, a color temperature adaptation analysis is performed through a preset model to be trained to obtain a color temperature output result; a difference is calculated between the color temperature output result and the color temperature information label to obtain an error result; based on the error result, it is determined whether the error result meets the error standard indicated by a preset error threshold range; if the error result does not meet the error standard indicated by the preset error threshold range, the step of performing a color temperature adaptation analysis based on the environmental feature samples and the time weights through a preset model to be trained to obtain a color temperature output result is returned, and training is stopped until the error result meets the error standard indicated by the preset error threshold range to obtain a color temperature control model.

[0180] It should be noted that, first, the device performs color temperature adaptation analysis based on the environmental feature samples and the time weights through a preset model to be trained to obtain a color temperature output result. Specifically, the device uses a preset model to be trained, combined with environmental feature samples and corresponding time weights, to perform color temperature adaptation analysis. This process is the process of the model learning how to predict the appropriate color temperature based on the input environmental features and time information. After the model analysis, a color temperature prediction result is output. This result is based on the current learning state of the model and the input data.

[0181] It is understandable that the second device calculates the difference between the color temperature output result and the color temperature information label to obtain an error result, that is, verifies whether the result obtained by the model in training is consistent with the known result, and calculates the difference between the results to obtain the error result.

[0182] It should be noted that the device determines whether the error result meets the error standard indicated by the preset error threshold range based on the error result. Specifically, since there is an error between the result after model training and the actual result, the error result is allowed to be within the preset error threshold range, so as to further determine whether the error result meets the error standard indicated by the preset error threshold range.

[0183] It is understandable that if the error result does not meet the error standard indicated by the preset error threshold range, it means that the error of the model is too large in this training. The device returns to the step of performing color temperature adaptation analysis based on the environmental feature sample and the time weight through the preset model to be trained to obtain the color temperature output result, that is, iterative training is performed until the error result meets the error standard indicated by the preset error threshold range, and the training is stopped to obtain the color temperature control model. The above iterative process ensures that the final color temperature control model can provide accurate color temperature prediction in practical applications.

[0184] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the monitoring method based on the AI ​​PTZ searchlight of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0185] This application also provides a monitoring device based on a pan-tilt searchlight, please refer to Figure 7 , the monitoring device based on the pan-tilt searchlight includes:

[0186] An acquisition module 10 is used to acquire video images within a preset monitoring range in real time;

[0187] A detection module 20, used to detect whether the target object presented in the video image is a risk target;

[0188] The control module 30 is used to control the searchlight to illuminate the target object and generate an alarm sound if the target object is a risky target until the target object cannot be detected.

[0189] Optionally, the control module 30 includes:

[0190] A first acquisition module, used to acquire the dynamic motion trajectory of the target object;

[0191] The irradiation module is used to control the searchlight to irradiate the target object according to the dynamic motion trajectory while continuously generating the alarm sound until the target object cannot be detected.

[0192] Optionally, the first acquisition module includes:

[0193] A first conversion module, used for converting the video image into a plurality of image frames;

[0194] A target detection module is used to detect feature data based on the image frame through a preset target tracking model to obtain a 3D detection frame of the target object;

[0195] A tracking module, configured to track the target object based on the 3D detection frame to obtain a target tracking result, and predict the position of the target object based on the target tracking result to obtain a prediction result;

[0196] A generation module is used to generate a dynamic motion trajectory of the target object based on the target tracking result and the prediction result.

[0197] Optionally, the control module 30 further includes:

[0198] a determination module, configured to determine first color temperature information if the target object is a risky target;

[0199] The first lighting irradiation module is used to control the searchlight to irradiate the target object with light corresponding to the first color temperature information while generating an alarm sound until the target object cannot be detected.

[0200] Optionally, the monitoring device based on the AI ​​PTZ searchlight further includes:

[0201] a color temperature determination module, configured to determine second color temperature information if the target object is not a risky target;

[0202] The searchlight control module is used to turn on the lighting lamp to generate light corresponding to the second color temperature information, and control the searchlight to irradiate light corresponding to the second color temperature information in the direction of a preset movement range of the target object, rather than irradiating the target object.

[0203] Optionally, the searchlight control module includes:

[0204] A second acquisition module, used to acquire the dynamic motion trajectory of the target object;

[0205] The second lighting irradiation module is used to control the searchlight to irradiate the target object in the direction of the preset movement range according to the dynamic motion trajectory, corresponding to the second color temperature information.

[0206] Optionally, the color temperature determination module includes:

[0207] An environmental feature extraction module, used for converting the video image into a plurality of image frames and extracting environmental features from the image frames;

[0208] The analysis module is used to perform color temperature adaptation analysis based on the environmental characteristics through a preset color temperature control model to obtain second color temperature information, wherein the color temperature control model is obtained by training a preset model to be trained based on environmental feature samples and color temperature information labels of the environmental feature samples.

[0209] Optionally, the monitoring device based on the AI ​​PTZ searchlight further includes:

[0210] A sample acquisition module, used to acquire an environmental feature sample and a color temperature information label of the environmental feature sample;

[0211] The training module is used to iteratively train the preset model to be trained based on the environmental feature samples and the color temperature information labels to obtain a color temperature control model.

[0212] Optionally, the training module includes:

[0213] A time information determination module, used to determine the time information of the environmental feature sample;

[0214] A time weight determination module, used to determine a corresponding time weight based on the time information;

[0215] The color temperature control model training module is used to iteratively train the preset model to be trained based on the environmental feature samples, the color temperature information labels and the time weights to obtain a color temperature control model.

[0216] Optionally, the color temperature control model training module includes:

[0217] A color temperature adaptation analysis module, used to perform color temperature adaptation analysis based on the environmental feature samples and the time weight through a preset model to be trained to obtain a color temperature output result;

[0218] A difference calculation module, used for performing difference calculation between the color temperature output result and the color temperature information label to obtain an error result;

[0219] A judgment module, configured to judge, based on the error result, whether the error result satisfies an error standard indicated by a preset error threshold range;

[0220] The iterative training module is used to return to the step of performing color temperature adaptation analysis based on the environmental feature sample and the time weight through a preset model to be trained to obtain a color temperature output result if the error result does not meet the error standard indicated by the preset error threshold range, and stop training until the error result meets the error standard indicated by the preset error threshold range to obtain a color temperature control model.

[0221] The monitoring device based on the pan-tilt searchlight provided in the present application adopts the monitoring method based on the AI ​​pan-tilt searchlight in the above embodiment, which can solve the technical problems of monitoring based on the pan-tilt searchlight. Compared with the prior art, the beneficial effects of the monitoring device based on the pan-tilt searchlight provided in the present application are the same as the beneficial effects of the monitoring method based on the AI ​​pan-tilt searchlight provided in the above embodiment, and the other technical features of the monitoring device based on the pan-tilt searchlight are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0222] The present application provides a monitoring device based on a pan-tilt searchlight, and the monitoring device based on a pan-tilt searchlight includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the monitoring method based on the AI ​​pan-tilt searchlight in the above-mentioned embodiment one.

[0223] Reference below Figure 8 , which shows a schematic diagram of the structure of a monitoring device based on a PTZ searchlight suitable for implementing the embodiment of the present application. The monitoring device based on a PTZ searchlight in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 8 The monitoring device based on the pan-tilt searchlight shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0224] like Figure 8As shown, the monitoring device based on the PTZ searchlight may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 to the random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the monitoring device based on the PTZ searchlight are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the PTZ searchlight-based monitoring device to communicate wirelessly or wired with other devices to exchange data. Although the PTZ searchlight-based monitoring device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have instead.

[0225] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0226] The monitoring device based on the pan-tilt searchlight provided by the present application adopts the monitoring method based on the AI ​​pan-tilt searchlight in the above embodiment, which can solve the technical problems of monitoring based on the pan-tilt searchlight. Compared with the prior art, the beneficial effects of the monitoring device based on the pan-tilt searchlight provided by the present application are the same as the beneficial effects of the monitoring method based on the AI ​​pan-tilt searchlight provided by the above embodiment, and the other technical features of the monitoring device based on the pan-tilt searchlight are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0227] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0228] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0229] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the monitoring method based on the AI ​​PTZ searchlight in the above-mentioned embodiment.

[0230] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0231] The computer-readable storage medium may be included in the monitoring device based on the PTZ searchlight; or may exist independently without being assembled into the monitoring device based on the PTZ searchlight.

[0232] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the monitoring device based on the PTZ searchlight, the monitoring device based on the PTZ searchlight performs monitoring based on the PTZ searchlight.

[0233] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0234] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0235] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0236] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned monitoring method based on the AI ​​PTZ searchlight, and can solve the technical problems of monitoring based on the PTZ searchlight. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the monitoring method based on the AI ​​PTZ searchlight provided in the above-mentioned embodiment, and will not be repeated here.

[0237] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned monitoring method based on the AI ​​PTZ searchlight.

[0238] The computer program product provided in this application can solve the technical problem of monitoring based on PTZ searchlights. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the monitoring method based on AI PTZ searchlights provided in the above embodiment, which will not be repeated here.

[0239] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A monitoring method based on AI PTZ searchlight, characterized in that: The method for monitoring based on the pan-tilt searchlight includes: Acquire video images within the preset monitoring range in real time; Detecting whether a target object presented in the video image is a risky target; If the target object is a risky target, the searchlight is controlled to illuminate the target object and generate an alarm sound until the target object cannot be detected.

2. The monitoring method based on AI PTZ searchlight according to claim 1, characterized in that: The step of controlling the searchlight to illuminate the target object and generate an alarm sound until the target object cannot be detected includes: Collecting the dynamic motion trajectory of the target object; While continuously generating the alarm sound, the searchlight is controlled to illuminate the target object according to the dynamic motion trajectory until the target object cannot be detected.

3. The monitoring method based on AI PTZ searchlight according to claim 2, characterized in that: The step of collecting the dynamic motion trajectory of the target object includes: Converting the video image into a plurality of image frames; Based on the image frame, feature data detection is performed through a preset target tracking model to obtain a 3D detection frame of the target object; Based on the 3D detection frame, the target object is tracked to obtain a target tracking result, and based on the target tracking result, a position prediction is performed on the target object to obtain a prediction result; Based on the target tracking result and the prediction result, a dynamic motion trajectory of the target object is generated.

4. The monitoring method based on AI PTZ searchlight according to claim 1, characterized in that: If the target object is a risky target, the step of controlling the searchlight to illuminate the target object and generate an alarm sound until the target object cannot be detected includes: If the target object is a risky target, determining first color temperature information; While generating the alarm sound, the searchlight is controlled to illuminate the target object with light corresponding to the first color temperature information until the target object cannot be detected.

5. The monitoring method based on AI PTZ searchlight according to claim 1, characterized in that: After the step of controlling the searchlight to illuminate the target object and generate an alarm sound if the target object is a risky target until the target object cannot be detected, the method includes: If the target object is not a risky target, determining second color temperature information; The lighting lamp is turned on to generate light corresponding to the second color temperature information, and the searchlight is controlled to irradiate light corresponding to the second color temperature information in the direction of the preset movement range of the target object, rather than irradiating the target object.

6. The monitoring method based on AI PTZ searchlight according to claim 5, characterized in that: The step of controlling the searchlight to illuminate the target object in the direction of the preset movement range according to the second color temperature information includes: Collecting the dynamic motion trajectory of the target object; According to the dynamic motion trajectory, the searchlight is controlled to illuminate the target object in the direction of the preset motion range corresponding to the second color temperature information.

7. The monitoring method based on AI PTZ searchlight according to claim 5, characterized in that: The step of determining the second color temperature information includes: Converting the video image into a plurality of image frames, and extracting environmental features from the image frames; Based on the environmental characteristics, a color temperature adaptation analysis is performed through a preset color temperature control model to obtain second color temperature information, wherein the color temperature control model is obtained by training a preset model to be trained based on environmental feature samples and color temperature information labels of the environmental feature samples.

8. The monitoring method based on AI PTZ searchlight according to claim 7, characterized in that: Before the step of converting the video image into a plurality of image frames and extracting environmental features from the image frames, the method comprises: Acquire an environmental characteristic sample and a color temperature information label of the environmental characteristic sample; Based on the environmental feature samples and the color temperature information labels, the preset model to be trained is iteratively trained to obtain a color temperature control model.

9. The monitoring method based on AI PTZ searchlight according to claim 8, characterized in that: The step of iteratively training a preset model to be trained based on the environmental feature sample and the color temperature information label to obtain a color temperature control model includes: Determining time information of the environmental characteristic sample; Based on the time information, determining a corresponding time weight; Based on the environmental feature samples, the color temperature information labels and the time weights, the preset model to be trained is iteratively trained to obtain a color temperature control model.

10. The monitoring method based on AI PTZ searchlight according to claim 9, characterized in that: The step of iteratively training the preset model to be trained based on the environmental feature sample, the color temperature information label and the time weight to obtain the color temperature control model includes: Based on the environmental feature samples and the time weight, a color temperature adaptation analysis is performed through a preset model to be trained to obtain a color temperature output result; Calculate the difference between the color temperature output result and the color temperature information label to obtain an error result; Based on the error result, determining whether the error result meets an error standard indicated by a preset error threshold range; If the error result does not meet the error standard indicated by the preset error threshold range, return to the step of performing color temperature adaptation analysis based on the environmental feature sample and the time weight through the preset model to be trained to obtain the color temperature output result, and stop training until the error result meets the error standard indicated by the preset error threshold range to obtain the color temperature control model.

11. A monitoring device based on a pan-tilt searchlight, characterized in that: The device comprises: An acquisition module is used to acquire video images within a preset monitoring range in real time; A detection module, used to detect whether the target object presented in the video image is a risk target; The control module is used to control the searchlight to illuminate the target object and generate an alarm sound if the target object is a risky target until the target object cannot be detected.

12. The monitoring device based on the AI ​​PTZ searchlight according to claim 11, characterized in that: The control module comprises: A first acquisition module, used to acquire the dynamic motion trajectory of the target object; The irradiation module is used to control the searchlight to irradiate the target object according to the dynamic motion trajectory while continuously generating the alarm sound until the target object cannot be detected.

13. The monitoring device based on the AI ​​PTZ searchlight according to claim 12, characterized in that: The first acquisition module includes: A first conversion module, used for converting the video image into a plurality of image frames; A target detection module is used to detect feature data based on the image frame through a preset target tracking model to obtain a 3D detection frame of the target object; A tracking module, configured to track the target object based on the 3D detection frame to obtain a target tracking result, and predict the position of the target object based on the target tracking result to obtain a prediction result; A generation module is used to generate a dynamic motion trajectory of the target object based on the target tracking result and the prediction result.

14. The monitoring device based on the AI ​​PTZ searchlight according to claim 11, characterized in that: The control module further includes: a determination module, configured to determine first color temperature information if the target object is a risky target; The first lighting irradiation module is used to control the searchlight to irradiate the target object with light corresponding to the first color temperature information while generating an alarm sound until the target object cannot be detected.

15. The monitoring device based on AI PTZ searchlight according to claim 11, characterized in that: The device also includes: a color temperature determination module, configured to determine second color temperature information if the target object is not a risky target; The searchlight control module is used to turn on the lighting lamp to generate light corresponding to the second color temperature information, and control the searchlight to irradiate light corresponding to the second color temperature information in the direction of a preset movement range of the target object, rather than irradiating the target object.

16. The monitoring device based on the AI ​​PTZ searchlight according to claim 15, characterized in that: The searchlight control module comprises: A second acquisition module, used to acquire the dynamic motion trajectory of the target object; The second lighting irradiation module is used to control the searchlight to irradiate the target object in the direction of the preset movement range according to the dynamic motion trajectory, corresponding to the second color temperature information.

17. The monitoring device based on AI PTZ searchlight according to claim 15, characterized in that: The color temperature determination module comprises: An environmental feature extraction module, used for converting the video image into a plurality of image frames and extracting environmental features from the image frames; The analysis module is used to perform color temperature adaptation analysis based on the environmental characteristics through a preset color temperature control model to obtain second color temperature information, wherein the color temperature control model is obtained by training a preset model to be trained based on environmental feature samples and color temperature information labels of the environmental feature samples.

18. A monitoring device based on a pan-tilt searchlight, characterized in that: The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the monitoring method based on the AI ​​PTZ searchlight as described in any one of claims 1 to 10.

19. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the monitoring method based on the AI ​​PTZ searchlight as described in any one of claims 1 to 10 are implemented.

20. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the monitoring method based on the AI ​​PTZ searchlight as described in any one of claims 1 to 10 are implemented.

Images