Methods, devices, equipment and storage media for projectile warning

Abstract

This application provides a method, apparatus, device, and storage medium for early warning of projectile falling objects, belonging to the field of security technology. The method includes: acquiring video signals from a building area using a camera device; detecting projectile falling events based on the video signals; if a pre-projectile falling event is detected based on a first video frame in the video signal, predicting the location of a first falling object on the ground based on the pre-projectile falling event; determining the audio-visual device corresponding to the location of the first falling object from multiple candidate audio-visual devices, and sending a preparatory command to the audio-visual device, the preparatory command instructing the audio-visual device to enter an alarm preparatory state; if a projectile falling event corresponding to the pre-projectile falling event is detected based on the first video frame and a second video frame following the first video frame, sending an activation command to the audio-visual device that has entered the alarm preparatory state, the activation command instructing the audio-visual device that has entered the alarm preparatory state to issue an audio-visual alarm. This method improves the effectiveness and timeliness of early warning for projectile falling events.

Description

Technical Field

[0001] This application relates to the field of security technology, and in particular to a method, device, equipment and storage medium for projectile warning. Background Technology

[0002] With societal development, buildings are becoming increasingly numerous and taller. Objects thrown from these high-rises pose a significant safety hazard. Current technology typically relies on surveillance footage to trace the source after an incident of objects being thrown from a height, but this cannot completely eliminate the safety risks. Therefore, a method for early warning of objects being thrown is needed, capable of providing timely alerts when such incidents occur. Summary of the Invention

[0003] This application provides a method, apparatus, device, and storage medium for projectile warning, which can improve the effectiveness and timeliness of warning for projectile events. The technical solution is as follows:

[0004] On the one hand, a method for early warning of parabolic eclipses is provided, the method comprising:

[0005] Video signals from the building area are collected using camera equipment, and projectile events are detected based on the video signals.

[0006] If a pre-projection event is detected based on the first video frame in the video signal, the location of the first falling object on the ground is predicted based on the pre-projection event;

[0007] Determine the sound and light device corresponding to the location of the first falling object from multiple candidate sound and light devices, and send a preparatory command to the sound and light device. The preparatory command is used to instruct the sound and light device to enter the alarm preparatory state.

[0008] If a parabolic event corresponding to the pre-parabolic event is detected based on the first video frame and the second video frame following the first video frame, a start command is sent to the audio-visual device that has entered the alarm preparation state. The start command is used to instruct the audio-visual device that has entered the alarm preparation state to issue an audio-visual alarm.

[0009] In some embodiments, there are multiple audible and visual devices corresponding to the first falling object location, and sending a start command to the audible and visual devices that have entered the alarm preparation state includes:

[0010] Based on the predicted location of the second falling object on the ground based on the parabolic event, at least one audio-visual device corresponding to the second falling object location is determined from among the multiple audio-visual devices corresponding to the first falling object location, and a start command is sent to the at least one audio-visual device.

[0011] In some embodiments, determining the acoustic-optical device corresponding to the location of the first falling object from a plurality of candidate acoustic-optical devices includes:

[0012] Based on the first falling object location and the first reference distance, the candidate audio-visual devices that are no more than the first reference distance from the first falling object location are selected as the multiple audio-visual devices corresponding to the first falling object location.

[0013] Determining at least one audio-visual device corresponding to the second falling object position from among multiple audio-visual devices corresponding to the first falling object position includes:

[0014] Based on the second falling object location and the second reference distance, among the multiple audio-visual devices corresponding to the first falling object location, the audio-visual device that is no more than the second reference distance from the second falling object location is regarded as at least one audio-visual device corresponding to the second falling object location, and the first reference distance is greater than the second reference distance.

[0015] In some embodiments, the method further includes:

[0016] Based on the event occurrence height of the pre-parabolic event, the first reference distance and the second reference distance are determined respectively, and the first reference distance and the second reference distance are positively correlated with the event occurrence height.

[0017] In some embodiments, determining the process of detecting a pre-parabolic event includes:

[0018] If a first object is detected in the building area based on the first video frame in the video signal, a pre-parabolic event is determined to be detected, wherein the first object is an object that appears from a non-edge position in the building area;

[0019] The process of determining the detection of a parabolic event includes:

[0020] If, based on the first video frame and the second video frame following the first video frame, it is determined that the motion trajectory of the first object conforms to the reference motion trajectory, a parabolic event corresponding to the pre-parabolic event is detected.

[0021] In some embodiments, determining the process of detecting a parabolic event includes:

[0022] If a second object is detected in the building area based on the first video frame of the video signal, the motion trajectory of the second object is determined. If the motion trajectory of the second object matches the reference motion trajectory, a parabolic event is detected. The second object is an object that appears from the edge of the building area.

[0023] The method further includes:

[0024] Based on the trajectory of the second object, the location of the third falling object on the ground is predicted, and a start command is sent to the audio-visual device corresponding to the location of the third falling object.

[0025] In some embodiments, the audio-visual device includes a lighting device and a sound device, wherein the lighting device is used to project light onto the location of the falling object, and the sound device is used to emit a voice signal.

[0026] In some embodiments, there are multiple lighting devices corresponding to the first falling object location, and the method further includes:

[0027] Based on the environmental information of the location of the first falling object, determine the shape of the light to be projected that matches the environmental information;

[0028] Based on the light shape, the light projection information of each of the multiple lighting devices is determined. The light projection information includes the light projection angle, the light projection area, and the light projection shape. The light projection shapes of the multiple lighting devices constitute the light shape.

[0029] Sending a preparatory command to the audio-visual device includes:

[0030] Based on the light projection information of each of the multiple lighting devices, a light preparation command including the light projection information is sent to each of the multiple lighting devices.

[0031] In some embodiments, there are multiple sound devices corresponding to the first falling object location, including a first sound device and a second sound device. The distance between the first sound device and the first falling object location does not exceed a third reference distance, and the distance between the second sound device and the first falling object location exceeds the third reference distance but does not exceed the first reference distance, wherein the third reference distance is less than the first reference distance. Sending a preparatory command to the sound and light device includes:

[0032] A first voice command is sent to the first sound device, and a second voice command is sent to the second sound device. The first voice command instructs the first sound device to emit a first voice signal, and the second voice command instructs the second sound device to emit a second voice signal. The first voice signal is used to indicate the projectile event, and the second voice signal is used to indicate the projectile event and the location of the first falling object; or...

[0033] A third voice command is sent to each of the plurality of sound devices, wherein the third voice command is used to instruct the first sound device to emit a first voice signal and to instruct the second sound device to emit a second voice signal.

[0034] In some embodiments, the parabolic event detection based on the video signal includes:

[0035] Parabolic events are detected based on the video signal using an event detection model.

[0036] In some embodiments, the method further includes:

[0037] Acquire multiple video frames from a sample video that include parabolic events, the sample video including videos of parabolic events occurring at multiple windows in the building area;

[0038] The event detection model is trained based on the multiple video frames.

[0039] On the other hand, a projectile warning device is provided, the device comprising:

[0040] The event detection module is used to collect video signals from the building area through camera equipment and to detect parabolic events based on the video signals.

[0041] The position prediction module is used to predict the position of a first falling object on the ground based on the pre-projectile event if a pre-projectile event is detected based on the first video frame in the video signal.

[0042] The device determination module is used to determine the acoustic and optical device corresponding to the location of the first falling object from a plurality of candidate acoustic and optical devices;

[0043] The instruction sending module is used to send a preparatory instruction to the audio-visual device, the preparatory instruction being used to instruct the audio-visual device to enter an alarm preparatory state;

[0044] The instruction sending module is further configured to send a start instruction to the audio-visual device that has entered the alarm preparation state if a parabolic event corresponding to the pre-parabolic event is detected based on the first video frame and the second video frame after the first video frame. The start instruction is used to instruct the audio-visual device that has entered the alarm preparation state to issue an audio-visual alarm.

[0045] In some embodiments, there are multiple audio-visual devices corresponding to the first falling object location, and the device determination module is configured to:

[0046] Based on the predicted location of the second falling object on the ground based on the parabolic event, at least one audio-visual device corresponding to the second falling object location is determined from a plurality of audio-visual devices corresponding to the first falling object location.

[0047] The instruction sending module is used to send a start instruction to the at least one audio-visual device.

[0048] In some embodiments, the device determining module is configured to:

[0049] Based on the first falling object location and the first reference distance, the candidate audio-visual devices that are no more than the first reference distance from the first falling object location are selected as the multiple audio-visual devices corresponding to the first falling object location.

[0050] Based on the second falling object location and the second reference distance, among the multiple audio-visual devices corresponding to the first falling object location, the audio-visual device that is no more than the second reference distance from the second falling object location is regarded as at least one audio-visual device corresponding to the second falling object location, and the first reference distance is greater than the second reference distance.

[0051] In some embodiments, the apparatus further includes:

[0052] The distance determination module is used to determine the first reference distance and the second reference distance based on the event occurrence height of the pre-parabolic event, wherein the first reference distance and the second reference distance are positively correlated with the event occurrence height.

[0053] In some embodiments, the event detection module is configured to:

[0054] If a first object is detected in the building area based on the first video frame in the video signal, a pre-parabolic event is determined to be detected, wherein the first object is an object that appears from a non-edge position in the building area;

[0055] If, based on the first video frame and the second video frame following the first video frame, it is determined that the motion trajectory of the first object conforms to the reference motion trajectory, a parabolic event corresponding to the pre-parabolic event is detected.

[0056] In some embodiments, the event detection module is configured to:

[0057] If a second object is detected in the building area based on the first video frame of the video signal, the motion trajectory of the second object is determined. If the motion trajectory of the second object matches the reference motion trajectory, a parabolic event is detected. The second object is an object that appears from the edge of the building area.

[0058] The instruction sending module is also used for:

[0059] Based on the trajectory of the second object, the location of the third falling object on the ground is predicted, and a start command is sent to the audio-visual device corresponding to the location of the third falling object.

[0060] In some embodiments, the audio-visual device includes a lighting device and a sound device, wherein the lighting device is used to project light onto the location of the falling object, and the sound device is used to emit a voice signal.

[0061] In some embodiments, there are multiple lighting devices corresponding to the first falling object location, and the device further includes:

[0062] A shape determination module is used to determine the shape of the light to be projected that matches the environmental information based on the environmental information of the location of the first falling object.

[0063] The information determination module is used to determine the light projection information of each of the multiple lighting devices based on the light shape. The light projection information includes the light projection angle, the light projection area, and the light projection shape. The light projection shapes of the multiple lighting devices constitute the light shape.

[0064] The instruction sending module is used for:

[0065] Based on the light projection information of each of the multiple lighting devices, a light preparation command including the light projection information is sent to each of the multiple lighting devices.

[0066] In some embodiments, the sound device corresponding to the first falling object location is multiple, including a first sound device and a second sound device. The distance between the first sound device and the first falling object location does not exceed a third reference distance, and the distance between the second sound device and the first falling object location exceeds the third reference distance but does not exceed the first reference distance, wherein the third reference distance is less than the first reference distance; the instruction sending module is configured to:

[0067] A first voice command is sent to the first sound device, and a second voice command is sent to the second sound device. The first voice command instructs the first sound device to emit a first voice signal, and the second voice command instructs the second sound device to emit a second voice signal. The first voice signal is used to indicate the projectile event, and the second voice signal is used to indicate the projectile event and the location of the first falling object; or...

[0068] A third voice command is sent to each of the plurality of sound devices, wherein the third voice command is used to instruct the first sound device to emit a first voice signal and to instruct the second sound device to emit a second voice signal.

[0069] In some embodiments, the event detection module is configured to:

[0070] Parabolic events are detected based on the video signal using an event detection model.

[0071] In some embodiments, the apparatus further includes a model training module for:

[0072] Acquire multiple video frames from a sample video that include parabolic events, the sample video including videos of parabolic events occurring at multiple windows in the building area;

[0073] The event detection model is trained based on the multiple video frames.

[0074] On the other hand, a computer device is provided, the computer device including one or more processors and one or more memories, the one or more memories storing at least one piece of program code, the at least one piece of program code being loaded and executed by the one or more processors to implement the parabolic warning method described in any of the above implementations.

[0075] On the other hand, a computer-readable storage medium is provided, wherein at least one piece of program code is stored in the computer-readable storage medium, the at least one piece of program code being loaded and executed by a processor to implement the parabolic warning method described in any of the above implementations.

[0076] On the other hand, a computer program product is provided, the computer program product including computer program code stored in a computer-readable storage medium, a processor of a computer device reading the computer program code from the computer-readable storage medium, the processor executing the computer program code, causing the computer device to perform the parabolic warning method described in any of the above implementations.

[0077] In this embodiment, pre-projection events in the building area are first detected. When a suspected pre-projection event is detected, the audible and visual equipment is instructed to enter an alarm standby state. Then, when a projectile event corresponding to the pre-projection event is detected, i.e., when the projectile event actually occurs, an activation command is sent to the audible and visual equipment. Since the audible and visual equipment has already entered the alarm standby state, it can promptly issue an audible and visual alarm based on the activation command, thereby improving the effectiveness and timeliness of early warning for projectile events. Attached Figure Description

[0078] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying 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.

[0079] Figure 1 This is a schematic diagram of an implementation environment provided in an embodiment of this application;

[0080] Figure 2 This is a flowchart of a parabolic warning method provided in an embodiment of this application;

[0081] Figure 3 This is a flowchart of another parabolic warning method provided in the embodiments of this application;

[0082] Figure 4 This is a flowchart of another parabolic warning method provided in the embodiments of this application;

[0083] Figure 5 This is a flowchart of another parabolic warning method provided in the embodiments of this application;

[0084] Figure 6 This is a block diagram of a parabolic warning device provided in an embodiment of this application;

[0085] Figure 7 This is a block diagram of a control device provided in an embodiment of this application;

[0086] Figure 8 This is a block diagram of a server provided in an embodiment of this application. Detailed Implementation

[0087] 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.

[0088] The terms "first," "second," "third," and "fourth," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0089] It should be noted that all information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.), and signals involved in this application have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. For example, the video signals involved in this application were all obtained with full authorization.

[0090] The projectile warning method provided in this application can be executed by a computer device. In this application, the computer device can be configured as a control device or a server. When the computer device is configured as a control device, the control device can act as the execution subject to implement the technical solution provided in this application. When the computer device is configured as a server, the server can act as the execution subject to implement the technical solution provided in this application. Alternatively, the technical solution provided in this application can be implemented through interaction between the control device and the server. This application does not limit this approach. The following is a schematic diagram of the implementation environment of the projectile warning method provided in this application.

[0091] join Figure 1 The implementation environment includes a computer device 10, a camera device 20, and an audio-visual device 30. The camera device 20 is used to acquire video signals and send them to the computer device 10. The computer device 10 is used to detect projectile events based on the video signals, and upon detecting a projectile event, sends a command to the audio-visual device 30. The audio-visual device 30 is used to issue an audible and visual alarm based on the command. The computer device 10, the camera device 20, and the audio-visual device 30 can be directly or indirectly connected via wired or wireless communication, and this application does not impose any restrictions on this connection.

[0092] Figure 2 This is a flowchart of a parabolic warning method provided in an embodiment of this application. The method is executed by a computer device and includes the following steps.

[0093] 201. Computer equipment collects video signals from building areas through camera equipment and performs projectile event detection based on the video signals.

[0094] In this embodiment, multiple camera devices are used to collect video signals from the entire building area. The camera devices transmit the collected video signals to a computer in real time for real-time detection and early warning.

[0095] In this embodiment of the disclosure, the detection of projectile events includes the detection of pre-projectile events and the detection of projectile events. A projectile event refers to an event in which an object has actually been thrown. A pre-projectile event refers to an event that is suspected of being thrown but has not yet occurred. Examples of pre-projectile events include a person standing at a window, a person standing at a window holding an object, an object appearing at a window, or a person standing at a window holding an object and extending the object out of the window. A projectile event can be an object falling from a window.

[0096] 202. If a pre-parabolic event is detected based on the first video frame in the video signal, the computer device predicts the location of the first falling object on the ground based on the pre-parabolic event.

[0097] In the embodiments of this application, the first video frame can be any video frame in the video signal, and the number of first video frames can also be multiple, without specific limitation. The first falling object position refers to the landing position of the object to be thrown on the ground in the pre-throwing event.

[0098] 203. The computer equipment determines the sound and light device corresponding to the first falling object location from multiple candidate sound and light devices, and sends a preparatory command to the sound and light device. The preparatory command is used to instruct the sound and light device to enter the alarm preparatory state.

[0099] In this embodiment, multiple candidate audio-visual devices are distributed in the ground area below the building. Furthermore, these devices are spaced apart around the road in the ground area, allowing them to overlap and cover the road below the building, thus enabling projectile warnings for the corresponding area.

[0100] In this embodiment, the computer device selects the acoustic-optical device whose distance from the first falling object location meets the distance requirement from a plurality of candidate acoustic-optical devices as the acoustic-optical device corresponding to the first falling object location. The acoustic-optical device corresponding to the first falling object location can be one or more.

[0101] In this embodiment, the sound and light device entering the alarm preparation state means that the sound and light device is turned on and ready to issue an sound and light alarm. The sound and light device in the alarm preparation state responds to the start command and can immediately issue an sound and light alarm.

[0102] 204. If a parabolic event corresponding to a pre-parabolic event is detected based on the first video frame and the second video frame following the first video frame, the computer device sends a start command to the audible and visual device that has entered the alarm preparation state. The start command is used to instruct the audible and visual device that has entered the alarm preparation state to issue an audible and visual alarm.

[0103] In this embodiment, the audio-visual device corresponding to the first falling object location is an audio-visual device near the first falling object location. This device is used to warn of an impending object throwing event at that location. In this embodiment, upon receiving a activation command, the audio-visual device immediately emits corresponding lights and sounds to alert nearby pedestrians to the impending object throwing event.

[0104] In this embodiment of the application, since the video signal is a real-time video signal, the computer device detects the pre-parabolic event based on the first video frame, and then detects the parabolic event corresponding to the pre-parabolic event based on the second video frame that is subsequently acquired.

[0105] In this embodiment, pre-projection events in the building area are first detected. When a suspected pre-projection event is detected, the audible and visual equipment is instructed to enter an alarm standby state. Then, when a projectile event corresponding to the pre-projection event is detected, i.e., when the projectile event actually occurs, an activation command is sent to the audible and visual equipment. Since the audible and visual equipment has already entered the alarm standby state, it can promptly issue an audible and visual alarm based on the activation command, thereby improving the effectiveness and timeliness of early warning for projectile events.

[0106] based on Figure 2 The implementation examples illustrate the basic process of parabolic warning. The following is based on... Figure 3 The following examples further illustrate the process of parabolic warning. Figure 3 This is a flowchart of a parabolic warning method provided in an embodiment of this application. The method is executed by a computer device and includes the following steps.

[0107] 301. Computer equipment collects video signals from building areas through camera equipment and performs projectile event detection based on the video signals.

[0108] In this embodiment of the application, there are multiple camera devices, which are distributed in an array on the exterior wall area of ​​the building, so that the camera angles of the camera devices can cover all floors of the building.

[0109] In some embodiments, the computer device detects projectile events using an event detection model. Accordingly, the process of detecting projectile events based on video signals by the computer device includes the following steps: the computer device detects projectile events based on video signals using an event detection model. Specifically, after the computer device inputs the video signal into the event detection model, the event detection model identifies pre-projectile events and projectile events based on the video signal. In this embodiment, detecting projectile events based on an event detection model improves detection efficiency.

[0110] In some embodiments, during the training of the event detection model, a computer device acquires multiple video frames from sample videos that include parabolic events. These sample videos include videos of parabolic events occurring at multiple windows within a building area. The computer device trains the event detection model based on these multiple video frames. In this embodiment, parabolic events in buildings typically occur at windows. Therefore, the event detection model is trained based on videos of parabolic events occurring at windows, enabling the trained event detection model to accurately identify parabolic events within the building area, thereby improving the accuracy of detection based on the event detection model.

[0111] The sample videos are multiple, and each sample video corresponds to multiple windows in a building area. Each window can correspond to multiple sample videos of multiple different parabolic events that occur in that window, thereby improving the richness and diversity of the sample videos.

[0112] In some embodiments, the process of acquiring sample videos includes the following steps: After installing camera equipment and audio-visual equipment in the building area, the equipment is manually adjusted to better collect video signals and provide audio-visual alarms. Then, a projectile action is performed in the windows of each room on each floor of the building, and the video signal of the projectile action is collected by the camera equipment, i.e., targeted training samples are collected by the camera equipment to obtain sample videos. The collected sample videos are then manually labeled, and the model is trained based on the labeled sample videos to improve the performance of the event detection model. The training process is completed when the recognition success rate of the event detection model reaches the expected recognition success rate, and then the event detection model is put into use. During the use of the event detection model, it can also be updated and maintained based on the actual projectile event videos to further improve the recognition success rate of the event detection model.

[0113] In the embodiments of this application, the event detection model includes, but is not limited to, the decision tree model.

[0114] 302. If a pre-parabolic event is detected based on the first video frame in the video signal, the computer device predicts the location of the first falling object on the ground based on the pre-parabolic event.

[0115] In the embodiments of this application, the process by which the computer device predicts the location of the first falling object on the ground based on the pre-projectile event includes, but is not limited to, the following two implementation methods.

[0116] In one implementation, the computer device designates the location directly below the point where the projectile event occurs as the first falling object location. In another implementation, the computer device designates both the location directly below the point where the projectile event occurs and the area at a preset distance from the location directly below as the first falling object location, thereby increasing the coverage of the warning and improving its effectiveness.

[0117] In some embodiments, the process by which a computer device determines that a pre-projection event has been detected includes the following steps: if the computer device detects a first object appearing in a building area based on a first video frame in a video signal, the computer device determines that a pre-projection event has been detected, wherein the first object is an object appearing from a non-edge location in the building area.

[0118] In this embodiment, the first object is an object that suddenly appears in the video frame, such as an object thrown out of a room. There can be multiple first video frames. The computer device detects whether a suddenly appearing first object appears in the frame based on the video frames of these multiple first video frames. Optionally, the computer device uses an event detection model to detect a pre-projection event of the first object appearing in the building area. The event detection model can detect video frames in the video signal where the first object appears, thereby detecting the pre-projection event.

[0119] In this embodiment, if an object suddenly appears in the building area, there is a high probability that a projectile event will occur based on the object, which will then be identified as a pre-projectile event, and an alarm will be prepared in time to facilitate timely alarm when the actual projectile event occurs.

[0120] 303. The computer equipment determines the audio-visual device corresponding to the location of the first falling object from multiple candidate audio-visual devices.

[0121] In the embodiments of this application, the process by which the computer device determines the acoustic and optical device corresponding to the location of the first falling object from a plurality of candidate acoustic and optical devices includes the following implementation methods.

[0122] In the first implementation, the audio-visual device is a device capable of projecting light and emitting voice signals. If there is only one audio-visual device corresponding to the first falling object location, the computer device selects the candidate audio-visual device closest to the first falling object location from among multiple candidate audio-visual devices as the audio-visual device corresponding to the first falling object location. If there are multiple audio-visual devices corresponding to the first falling object location, the computer device, based on the first falling object location and a first reference distance, selects the candidate audio-visual devices whose distance from the first falling object location does not exceed the first reference distance from the first falling object location as the multiple audio-visual devices corresponding to the first falling object location.

[0123] In this implementation, the audio-visual equipment is integrated into a single unit, thereby reducing the number of devices and improving the ease of control. One or more audio-visual devices closest to the first falling object location are designated as the corresponding devices for that location. This ensures that the identified devices are close enough to the first falling object location to effectively provide early warning of projectiles.

[0124] The first reference distance can be set and changed as needed. Optionally, the first reference distance is a fixed value. Alternatively, the computer device determines the first reference distance based on the event height of the projectile event. The first reference distance is positively correlated with the event height; that is, the higher the event height, the larger the first reference distance. Further, the computer device determines the first reference distance based on the correspondence between the event height and the first reference distance, and the event height itself. In this embodiment, the first reference distance is determined based on the event height, so that the higher the projectile height, the larger the range of the selected audio-visual equipment, and thus the larger the warning range. This embodiment can compensate for the prediction error of the falling object's location caused by the high event height, thereby improving the flexibility and accuracy of the warning.

[0125] In the second implementation, the audio-visual equipment includes lighting equipment and sound equipment. The lighting equipment projects light towards the location of the fallen object, and the sound equipment emits a voice signal. The lighting equipment is located above the road to project light downwards. The sound equipment can be a speaker or a loudspeaker.

[0126] If there is one light and one sound device corresponding to the first falling object location, the computer will select the candidate light device closest to the first falling object location from among multiple candidate light devices as the corresponding light device. Similarly, the computer will select the candidate sound device closest to the first falling object location from among multiple candidate sound devices as the corresponding sound device.

[0127] If there are multiple lighting and sound devices corresponding to the first falling object location, the computer device, based on the first falling object location and a first reference distance, identifies the candidate audio-visual devices whose distance from the first falling object location does not exceed the first reference distance as the multiple audio-visual devices corresponding to the first falling object location. Specifically, the computer device identifies the candidate lighting devices whose distance from the first falling object location does not exceed the first reference distance as the lighting devices corresponding to the first falling object location, and the computer device identifies the candidate sound devices whose distance from the first falling object location does not exceed the first reference distance as the sound devices corresponding to the first falling object location. The first reference distances corresponding to the lighting and sound devices can be the same or different, and are not specifically limited here.

[0128] In this implementation, lighting and sound devices are set up separately, allowing them to be asynchronous and non-interfering with each other. This enables precise control of the lighting and sound devices, thereby improving the accuracy of light and sound alarms. One or more lighting and sound devices closest to the first falling object location are designated as the corresponding lighting and sound devices for that location. This ensures that the identified lighting and sound devices are close enough to the first falling object location to effectively provide early warning.

[0129] 304. The computer equipment sends a preparatory command to the audible and visual equipment. The preparatory command is used to instruct the audible and visual equipment to enter the alarm preparatory state.

[0130] In some embodiments, when there are multiple lighting devices corresponding to the first falling object location, the light shapes projected by the multiple lighting devices form a complete shape. Accordingly, the computer device determines the light shape to be projected that matches the environmental information of the first falling object location; based on the light shape, it determines the light projection information of each of the multiple lighting devices, including the light projection angle, light projection area, and light projection shape, and the light projection shapes of the multiple lighting devices form the light shape. Accordingly, the process of the computer device sending a preparatory command to the audio-visual device includes the following steps: the computer device sends a light preparatory command, including the light projection information, to each of the multiple lighting devices based on their respective light projection information. In this embodiment, by cooperating with multiple lighting devices to project a light shape that matches the environmental information, the projected light is more in line with actual needs, that is, the projected light is more accurate, thereby improving the light alarm effect.

[0131] The computer equipment determines the light projection shape of each of the multiple lighting devices based on the number of lighting devices and the shape of the light to be projected, so that the light projection shapes of the multiple lighting devices can form the shape of the light to be projected.

[0132] In this embodiment, the environmental information of the first falling object location includes road shape information, road terrain information, etc. For example, the road shape can be circular, arc-shaped, straight, etc. The road terrain can be sloped, flat, etc. The light projection area of ​​multiple lighting devices covers the first falling object location. For example, if the shape of the light to be projected is circular, the circle formed by the light projection shapes of multiple lighting devices covers the first falling object location.

[0133] In some embodiments, the lighting device adjusts the light projection angle and the size of the light projection shape to be projected based on the light projection angle, light projection area, and light projection shape in the light preparation command, so that the projected light shape covers the light projection area in the light preparation command. In this embodiment, the light projection angle and light projection shape are adjusted during the preparation stage upon receiving the light preparation command, so that when the start command is subsequently received, the light can be projected directly, avoiding the time spent adjusting the light projection angle and light projection shape, thereby improving the efficiency and timeliness of light alarm based on the lighting device.

[0134] The process of a computer device sending lighting instructions, including lighting projection information, to multiple lighting devices based on their respective lighting projection information includes the following two implementation methods.

[0135] In one implementation, the computer device sends a lighting preparation command, including the lighting projection information, to each lighting device corresponding to the first falling object location, based on the lighting projection information of that lighting device. This implementation reduces the computational burden on the lighting devices, thereby improving their command response speed. In another implementation, the computer device sends a lighting preparation command to each lighting device separately, the lighting preparation command including the lighting projection information of each of the multiple lighting devices. The multiple lighting devices retrieve their respective lighting projection information from the lighting preparation command. Optionally, the multiple lighting preparation commands carry an identifier for each lighting device and its lighting projection information. Each lighting device retrieves its own lighting projection information based on its identifier. Optionally, the identifier for each lighting device is its device number. This implementation reduces the computational burden on the computer device and improves the convenience of sending commands.

[0136] In some embodiments, the light projection information also includes the light color, which can be set and changed as needed. For example, the light color can be a fixed color, such as red light. The light color can also be determined based on the time of the event. For example, if the event occurs during the day, the light is red; if the event occurs at night, the light is white. No specific limitation is made here.

[0137] In some embodiments, when there are multiple sound devices corresponding to the first falling object location, the sound devices at different distances from the first falling object location emit different voice signals. The multiple sound devices include a first sound device and a second sound device. The distance between the first sound device and the first falling object location does not exceed a third reference distance, and the distance between the second sound device and the first falling object location exceeds the third reference distance but does not exceed the first reference distance. The third reference distance is less than the first reference distance. Accordingly, the computer device sends a preparatory command to the audio-visual device, including the following two implementation methods.

[0138] In the first implementation, the computer device sends a first voice command to a first sound device and a second voice command to a second sound device. The first voice command instructs the first sound device to emit a first voice signal, and the second voice command instructs the second sound device to emit a second voice signal. The first voice signal indicates a projectile event, and the second voice signal indicates the projectile event and the location of the first falling object. This implementation reduces the computational burden on the sound device, thereby improving its command response speed.

[0139] In the second implementation, the computer device sends a third voice command to multiple sound devices respectively. The third voice command instructs the first sound device to emit a first voice signal and instructs the second sound device to emit a second voice signal. This implementation reduces the computational burden on the computer device and improves the convenience of sending commands.

[0140] In this implementation, the third voice command carries the identifiers of multiple sound devices and information about the voice signal of each sound device. Each sound device, based on its own identifier, locates its own voice signal information and performs a voice alarm based on that information. The identifier of the sound device can be a device number, and the voice signal information can be a specific voice signal or an identifier for the voice signal. For example, the third voice command may instruct devices numbered 1, 3, 5, and 9 to emit the same voice signal, or it may instruct devices numbered 1, 3, 5, and 9 to emit different voice signals; no specific limitation is made here.

[0141] In this embodiment, the first sound device is relatively close to the location of the first falling object, and a pedestrian is about to reach it. At this point, the first sound device needs to immediately alarm for the object being thrown. Therefore, it only alerts the pedestrian to the event, improving the timeliness and effectiveness of the alarm. The second sound device, on the other hand, is relatively far from the location of the first falling object, and the pedestrian is still some distance away. At this point, it alerts the pedestrian to the location of the first falling object and the event itself, serving as both a warning and preventing the pedestrian from walking towards that location. This embodiment improves the comprehensiveness and effectiveness of the voice alarm by having multiple sound devices coordinate to emit different voice signals at varying distances from the location of the first falling object.

[0142] The second voice signals of the second sound devices at different locations can be the same or different. For example, if the second voice signal indicates the specific geographical coordinates of the location of the first falling object, then the second voice signals of the second sound devices at different locations will be the same. If the second voice signal indicates the relative position between the location of the second sound device and the location of the first falling object, then the second voice signals of the second sound devices at different locations will be different. For example, different second voice signals could be "A projectile event has occurred ahead, please take cover" or "A projectile event has occurred behind, please take cover."

[0143] In some embodiments, different second voice signals have different voice identifiers. The sound device stores a first voice signal, multiple second voice signals, and voice identifiers for each of the multiple second voice signals. Accordingly, if a voice command carries a voice identifier, the sound device finds the corresponding second voice signal based on the voice identifier and then performs a voice alarm based on that second voice signal. If the voice command does not carry a voice identifier, the sound device selects the default first voice signal for the voice alarm. This embodiment allows voice commands to carry only a voice identifier, without needing to carry the specific voice signal, thereby improving the transmission efficiency of voice commands and saving transmission resources.

[0144] 305. If a parabolic event corresponding to a pre-parabolic event is detected based on the first video frame and the second video frame following the first video frame, the computer device sends a start command to the audible and visual device that has entered the alarm preparation state. The start command is used to instruct the audible and visual device that has entered the alarm preparation state to issue an audible and visual alarm.

[0145] In some embodiments, the process by which a computer device determines that a projectile event has been detected includes the following steps: if the computer device determines, based on a first video frame and a second video frame following the first video frame, that the motion trajectory of a first object conforms to a reference motion trajectory, it determines that a projectile event corresponding to a pre-projectile event has been detected.

[0146] In this embodiment, the reference motion trajectory can be a free-fall trajectory, meaning that when the first object is a non-self-driven object, a projectile event is detected. The computer device predicts the location of the second falling object based on the object's motion trajectory during the projectile event. Optionally, the computer device obtains the object's motion trajectory based on multiple video frames, including the first video frame and subsequent second video frames, and then predicts the location of the second falling object based on the motion trajectory and physical principles.

[0147] In this embodiment, the trajectory of an object can be used to determine whether the object is in free fall, and thus whether a projectile event has occurred, thereby improving the convenience and accuracy of detecting projectile events.

[0148] For example, see Figure 4 , Figure 4 This is a flowchart of a projectile warning method provided in an embodiment of this application. The computer device detects a pre-projectile event and the position of a human body within the pre-projectile event based on real-time video signals. Then, based on the position of the human body within the pre-projectile event, it detects whether a projectile event corresponding to the pre-projectile event has occurred. If not, the above process is repeated. If yes, lighting equipment in alarm preparation state is activated to project light towards the corresponding projectile location, and sound equipment in alarm preparation state is activated to emit a voice signal to issue an alarm.

[0149] In other embodiments, the process by which the computer device determines that a projectile event has been detected includes the following steps: If the computer device detects a second object appearing in a building area based on a first video frame in the video signal, it determines the trajectory of the second object. If the trajectory of the second object matches a reference trajectory, it determines that a projectile event has been detected. The second object is an object appearing from the edge of the building area. Accordingly, the computer device predicts the location of a third falling object on the ground based on the trajectory of the second object and sends a start command to the audio-visual device corresponding to the third falling object location.

[0150] In this embodiment, the second object is an object that enters the video frame from outside the video frame, such as a bird, raindrop, or leaf. Optionally, the computer device uses an event detection model to detect the parabolic event of the second object appearing in the building area. The event detection model is capable of detecting the event of the second object appearing in the building area; that is, the event detection model can detect video frames in the video signal containing the second object, thereby detecting the parabolic event.

[0151] In this embodiment, the second object is highly likely not to be part of the projectile event, but rather a self-propelled object. Therefore, projectile event detection is performed directly based on its motion trajectory, avoiding the process of pre-activating the audio-visual equipment based on an event that is highly unlikely to be a projectile event, thus reducing resource consumption. Furthermore, when a projectile event is detected based on the second object's motion trajectory, an activation command is directly sent to the audio-visual equipment to activate it, avoiding the delay caused by sending a pre-emptive command, improving the timeliness of activating the audio-visual equipment, and consequently improving the timeliness and effectiveness of the projectile warning.

[0152] In this embodiment, the first falling object location is directly taken as the falling object location corresponding to the projectile event. That is, a start command is directly sent to the sound and light device that has entered the alarm preparation state, and the sound and light device corresponding to the first falling object location will project light and emit voice signals.

[0153] In this embodiment, instructions are sent to the audio-visual device in two steps, so that the corresponding audio-visual device is in a preheated state that can be activated at any time, saving unnecessary processing time and thus improving the timeliness of the alarm.

[0154] In this embodiment, a background computer device is set up, including a processor and a display screen. The processor has high computing power and can handle real-time acquisition of video signals, scheduling lighting equipment to project lights into corresponding areas, and scheduling sound equipment to emit voice signals. This method, based on the rapidly developing computing power and high-performance hardware, combines to solve practical problems. It can provide early warnings of objects being thrown from heights, alerting pedestrians who have arrived or are about to arrive to areas with a risk of falling objects, thereby significantly reducing or even completely controlling the disastrous consequences caused by objects being thrown from heights.

[0155] In this embodiment, pre-projection events in the building area are first detected. When a suspected pre-projection event is detected, the audible and visual equipment is instructed to enter an alarm standby state. Then, when a projectile event corresponding to the pre-projection event is detected, i.e., when the projectile event actually occurs, an activation command is sent to the audible and visual equipment. Since the audible and visual equipment has already entered the alarm standby state, it can promptly issue an audible and visual alarm based on the activation command, thereby improving the effectiveness and timeliness of early warning for projectile events.

[0156] Figure 3 The following explanation uses the example of determining the location of a falling object based on a pre-projectile event. Figure 5 This explanation uses the determination of the falling object's location based on both the pre-projectile event and the projectile event as examples. (See also...) Figure 5 , Figure 5 This is a flowchart illustrating a parabolic warning method according to an exemplary embodiment, the method comprising the following steps.

[0157] 501. Computer equipment collects video signals from building areas using camera equipment and performs projectile event detection based on the video signals.

[0158] 502. If a pre-parabolic event is detected based on the first video frame in the video signal, the computer device predicts the location of the first falling object on the ground based on the pre-parabolic event.

[0159] 503. The computer equipment determines the audio-visual device corresponding to the location of the first falling object from multiple candidate audio-visual devices.

[0160] 504. The computer equipment sends a preparatory command to the audible and visual equipment. The preparatory command is used to instruct the audible and visual equipment to enter the alarm preparatory state.

[0161] In the embodiments of this application, steps 501-504 are the same as steps 301-304, and will not be described again here.

[0162] 505. If a parabolic event corresponding to a pre-parabolic event is detected based on a first video frame and a second video frame following the first video frame, the computer device predicts the location of a second falling object on the ground based on the parabolic event, and determines at least one audio-visual device corresponding to the location of the second falling object from among multiple audio-visual devices corresponding to the location of the first falling object.

[0163] In this embodiment of the application, the process of determining that a projectile event has been detected and determining the location of the second falling object in step 505 is the same as the process of determining that a projectile event has been detected and determining the location of the second falling object in step 305, and will not be described again here.

[0164] In this embodiment of the application, the process by which the computer device determines at least one audio-visual device corresponding to the second falling object position from among a plurality of audio-visual devices corresponding to the first falling object position includes the following two implementation methods.

[0165] In one implementation, the computer device identifies the audio-visual device closest to the second falling object location from among a plurality of audio-visual devices corresponding to the first falling object location. This implementation improves the accuracy and efficiency of determining the audio-visual device corresponding to the second falling object location.

[0166] In another implementation, the computer device, based on the second falling object location and a second reference distance, identifies at least one audio-visual device corresponding to the second falling object location from among multiple audio-visual devices corresponding to the first falling object location, provided that the distance between the device and the second falling object location does not exceed the second reference distance. The first reference distance is greater than the second reference distance. In this implementation, multiple audio-visual devices within a relatively large range are determined based on the pre-projection event, ensuring accurate alarms from all devices within this range. Furthermore, multiple audio-visual devices within a more precise, smaller range are determined based on the projectile event, and the actual audio-visual alarm is triggered based on these smaller devices. This embodiment improves the accuracy of the actual alarm audio-visual devices while reducing the number of devices actually triggering the alarm, thus lowering resource consumption.

[0167] In this embodiment, if the audio-visual device includes a lighting device and a sound device, the second reference distances corresponding to the lighting device and the sound device may be the same or different, and no specific limitation is made here.

[0168] The second reference distance can be set and changed as needed. Optionally, the second reference distance is a fixed value. Alternatively, the computer device determines the second reference distance based on the event occurrence height of the projectile event. The second reference distance is positively correlated with the event occurrence height; that is, the higher the event occurrence height, the larger the second reference distance. Optionally, the computer device determines the second reference distance based on the correspondence between the event occurrence height and the second reference distance, as well as the event occurrence height itself. In this embodiment, the second reference distance is determined based on the event occurrence height, so that the selected range of the audio-visual equipment is larger when the projectile height is higher. This embodiment can compensate for the prediction error problem of the falling object position caused by the high event occurrence height, thereby improving the flexibility and accuracy of the early warning.

[0169] 506. The computer equipment sends a start command to at least one audio-visual device corresponding to the second falling object location. The start command is used to instruct at least one audio-visual device corresponding to the second falling object location to issue an audio-visual alarm.

[0170] In this embodiment of the application, the computer device determines the second falling object position based on the motion trajectory of the object in the projectile event, and further determines the sound and light device corresponding to the second falling object position. Then, the sound and light device corresponding to the second falling object position projects light and emits voice signals.

[0171] Accordingly, before sending a start command to the audio-visual device corresponding to the second falling object location, if the second falling object location corresponds to multiple lighting devices, the computer device determines the shape of the light to be projected that matches the environmental information of the second falling object location; based on the light shape, it determines the light projection information of each of the multiple lighting devices, including the light projection angle, light projection area, and light projection shape, and the light projection shapes of the multiple lighting devices constitute the light shape. Accordingly, the computer device sends a start command to the lighting device corresponding to the second falling object location, including the following steps: based on the light projection information of each of the multiple lighting devices, the computer device sends a light start command including the light projection information to each of the multiple lighting devices. This process is the same as the process of determining the light projection information of each of the multiple lighting devices and sending the light preparation command to the multiple lighting devices in step 304, and will not be described again here.

[0172] Accordingly, before sending a start command to the audio-visual device corresponding to the second falling object location, the computer device determines the third and fourth audio devices. The distance between the third audio device and the second falling object location does not exceed the fourth reference distance, and the distance between the fourth audio device and the second falling object location exceeds the fourth reference distance but does not exceed the second reference distance. Accordingly, the computer device sends a start command to the audio device corresponding to the second falling object location, including the following steps: the computer device sends a fifth voice command to the third audio device and a sixth voice command to the fourth audio device. The fifth voice command is used to instruct the third audio device to emit a third voice signal, and the fifth voice command is used to instruct the fourth audio device to emit a fourth voice signal. The third voice signal is used to indicate the falling object event, and the fourth voice signal is used to indicate the falling object event and the second falling object location. Alternatively, the computer device sends a sixth voice command to multiple audio devices corresponding to the second falling object location respectively. The sixth voice command is used to instruct the third audio device to emit a third voice signal and instruct the fourth audio device to emit a fourth voice signal. This process is the same as the process of determining the first and second audio devices and sending voice commands to multiple audio devices in step 304, and will not be described again here.

[0173] Optionally, when the sound and light device corresponding to the second falling object location projects light and emits voice signals, the computer device sends a preparatory command to the light and sound device corresponding to the first falling object location, instructing the sound and light device to issue an alarm with a preset light shape and preset voice signal. This preset light shape and preset voice signal are common to multiple falling object locations. This avoids wasting resources in the preparatory stage, as the projected light shape and voice signal need to be updated based on the second falling object location later. Furthermore, even if the light shape to be projected and the voice signal to be emitted by the sound and light device corresponding to the second falling object location cannot be determined in a timely manner, a timely and effective alarm can still be issued based on a common light shape and voice signal.

[0174] Alternatively, if the sound and light device corresponding to the second falling object location projects light and emits voice signals, the computer device sends a light preparation command that can form a light shape to the multiple light devices corresponding to the first falling object location. This process is the same as the process of sending the light preparation command to the multiple light devices corresponding to the first falling object location in step 304. The process of the computer device sending voice commands to the multiple sound devices corresponding to the first falling object location is the same as the process of sending voice commands to the first and second sound devices in step 304, and will not be described again here.

[0175] In this embodiment, a preparatory command that can form a light shape and a voice signal that can indicate the location of the falling object are sent to the audio-visual device corresponding to the first falling object location. In this way, if the audio-visual device corresponding to the second falling object location is the same as that corresponding to the first falling object location, or if the light shape to be projected and the voice signal to be emitted by the audio-visual device corresponding to the second falling object location cannot be determined in time, a timely and effective alarm can still be triggered based on the audio-visual device corresponding to the first falling object location.

[0176] It should be noted that step 305 is only one optional implementation of sending a start command to the audible and visual device that has entered the alarm preparation state. This process can also be implemented in other optional ways, which are not specifically limited here. For example, the computer device can directly send a start command to the audible and visual device corresponding to the first falling object location.

[0177] In this embodiment, pre-projection events in the building area are first detected. When a suspected pre-projection event is detected, the audible and visual equipment is instructed to enter an alarm standby state. Then, when a projectile event corresponding to the pre-projection event is detected, i.e., when the projectile event actually occurs, an activation command is sent to the audible and visual equipment. Since the audible and visual equipment has already entered the alarm standby state, it can promptly issue an audible and visual alarm based on the activation command, thereby improving the effectiveness and timeliness of early warning for projectile events.

[0178] This application also provides a projectile warning device, see [link to relevant documentation]. Figure 6 The device includes:

[0179] Event detection module 601 is used to collect video signals from the building area through camera equipment and to detect parabolic events based on the video signals;

[0180] The position prediction module 602 is used to predict the position of the first falling object on the ground based on the pre-parabolic event if a pre-parabolic event is detected based on the first video frame in the video signal.

[0181] The device determination module 603 is used to determine the acoustic and optical device corresponding to the location of the first falling object from a plurality of candidate acoustic and optical devices;

[0182] The instruction sending module 604 is used to send a preparatory instruction to the audible and visual device, which is used to instruct the audible and visual device to enter the alarm preparatory state.

[0183] The instruction sending module 604 is further configured to send a start instruction to the audible and visual device that has entered the alarm preparation state if a parabolic event corresponding to the pre-parabolic event is detected based on the first video frame and the second video frame after the first video frame. The start instruction is used to instruct the audible and visual device that has entered the alarm preparation state to issue an audible and visual alarm.

[0184] In some embodiments, there are multiple audio-visual devices corresponding to the first falling object location, and the device determination module 603 is used for:

[0185] Based on the prediction of the location of the second falling object on the ground based on the parabolic event, at least one audio-visual device corresponding to the location of the second falling object is determined from multiple audio-visual devices corresponding to the location of the first falling object;

[0186] The instruction sending module 604 is used to send a start instruction to at least one audio-visual device.

[0187] In some embodiments, the device determination module 603 is configured to:

[0188] Based on the first falling object location and the first reference distance, the candidate audio-visual devices among the multiple candidate audio-visual devices that are no more than the first reference distance from the first falling object location are taken as the multiple audio-visual devices corresponding to the first falling object location;

[0189] Based on the second falling object location and the second reference distance, among the multiple audio-visual devices corresponding to the first falling object location, the audio-visual device that is no more than the second reference distance from the second falling object location is regarded as at least one audio-visual device corresponding to the second falling object location, and the first reference distance is greater than the second reference distance.

[0190] In some embodiments, the apparatus further includes:

[0191] The distance determination module is used to determine a first reference distance and a second reference distance based on the event occurrence height of the pre-parabolic event. The first reference distance and the second reference distance are positively correlated with the event occurrence height.

[0192] In some embodiments, the event detection module 601 is configured to:

[0193] If a first object is detected in a building area based on the first video frame in the video signal, it is determined that a pre-parabolic event has been detected, and the first object is an object that appears from a non-edge position in the building area.

[0194] Based on the first video frame and the second video frame following the first video frame, if it is determined that the motion trajectory of the first object conforms to the reference motion trajectory, the parabolic event corresponding to the detected pre-parabolic event is determined.

[0195] In some embodiments, the event detection module 601 is further configured to:

[0196] If a second object is detected in the building area based on the first video frame of the video signal, the motion trajectory of the second object is determined. If the motion trajectory of the second object matches the reference motion trajectory, a parabolic event is detected. The second object is an object that appears from the edge of the building area.

[0197] The instruction sending module is also used for:

[0198] Based on the trajectory of the second object, the location of the third falling object on the ground is predicted, and a start command is sent to the audio-visual device corresponding to the location of the third falling object.

[0199] In some embodiments, the audio-visual device includes a lighting device and a sound device, wherein the lighting device is used to project light onto the location of the falling object, and the sound device is used to emit a voice signal.

[0200] In some embodiments, there are multiple lighting devices corresponding to the first falling object location, and the device further includes:

[0201] The shape determination module is used to determine the shape of the light to be projected that matches the environmental information based on the location of the first falling object.

[0202] The information determination module is used to determine the light projection information of multiple lighting devices based on the light shape. The light projection information includes the light projection angle, the light projection area, and the light projection shape. The light projection shapes of multiple lighting devices constitute the light shape.

[0203] Instruction sending module 604 is used for:

[0204] Based on the light projection information of each of the multiple lighting devices, a light preparation command, including the light projection information, is sent to each of the multiple lighting devices.

[0205] In some embodiments, there are multiple sound devices corresponding to the first falling object location, including a first sound device and a second sound device. The distance between the first sound device and the first falling object location does not exceed a third reference distance, and the distance between the second sound device and the first falling object location exceeds the third reference distance but does not exceed the first reference distance. The third reference distance is less than the first reference distance. The instruction sending module 604 is used for:

[0206] A first voice command is sent to a first sound device, and a second voice command is sent to a second sound device. The first voice command instructs the first sound device to emit a first voice signal, and the second voice command instructs the second sound device to emit a second voice signal. The first voice signal is used to indicate a projectile event, and the second voice signal is used to indicate the projectile event and the location of the first falling object; or...

[0207] A third voice command is sent to multiple sound devices respectively. The third voice command is used to instruct the first sound device to emit a first voice signal and to instruct the second sound device to emit a second voice signal.

[0208] In some embodiments, the event detection module 601 is configured to:

[0209] Parabolic events are detected based on video signals using an event detection model.

[0210] In some embodiments, the apparatus further includes a model training module for:

[0211] Acquire multiple video frames from sample videos that include parabolic events, where the sample videos include videos of parabolic events occurring at multiple windows in a building area;

[0212] The event detection model is trained based on multiple video frames.

[0213] In this embodiment, pre-projection events in the building area are first detected. When a suspected pre-projection event is detected, the audible and visual equipment is instructed to enter an alarm standby state. Then, when a projectile event corresponding to the pre-projection event is detected, i.e., when the projectile event actually occurs, an activation command is sent to the audible and visual equipment. Since the audible and visual equipment has already entered the alarm standby state, it can promptly issue an audible and visual alarm based on the activation command, thereby improving the effectiveness and timeliness of early warning for projectile events.

[0214] It should be noted that the projectile warning device provided in the above embodiments is only an example of the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the control device can be divided into different functional modules to complete all or part of the functions described above. In addition, the projectile warning device and the projectile warning method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0215] In some embodiments, the computer device is provided as a control device. Figure 7 A structural block diagram of a control device 700 provided in an exemplary embodiment of this application is shown. The control device 700 can be a portable mobile control device, such as a smartphone, tablet computer, MP3 player (Moving Picture Experts Group Audio Layer III), MP4 player (Moving Picture Experts Group Audio Layer IV), laptop computer, or desktop computer. The control device 700 may also be referred to as a user device, portable control device, laptop control device, desktop control device, or other names.

[0216] Typically, the control device 700 includes a processor 701 and a memory 702.

[0217] Processor 701 may include one or more processing cores, such as a quad-core processor, an octa-core processor, etc. Processor 701 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 701 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 701 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, processor 701 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0218] The memory 702 may include one or more computer-readable storage media, which may be non-transitory. The memory 702 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 702 are used to store at least one program code, which is executed by the processor 701 to implement the parabolic warning method provided in the method embodiments of this application.

[0219] In some embodiments, the control device 700 may also optionally include a peripheral device interface 703 and at least one peripheral device. The processor 701, memory 702, and peripheral device interface 703 can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface 703 via a bus, signal line, or circuit board. Specifically, the peripheral device includes at least one of the following: a radio frequency circuit 704, a display screen 705, a camera assembly 706, an audio circuit 707, and a power supply 708.

[0220] Peripheral device interface 703 can be used to connect at least one I / O (Input / Output) related peripheral device to processor 701 and memory 702. In some embodiments, processor 701, memory 702 and peripheral device interface 703 are integrated on the same chip or circuit board; in some other embodiments, any one or two of processor 701, memory 702 and peripheral device interface 703 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0221] The radio frequency (RF) circuit 704 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 704 communicates with communication networks and other communication devices via electromagnetic signals. The RF circuit 704 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals back into electrical signals. Optionally, the RF circuit 704 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc. The RF circuit 704 can communicate with other control devices via at least one wireless communication protocol. This wireless communication protocol includes, but is not limited to: the World Wide Web, metropolitan area networks, intranets, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and / or WiFi (Wireless Fidelity) networks. In some embodiments, the RF circuit 704 may also include circuitry related to NFC (Near Field Communication), which is not limited in this application.

[0222] Display screen 705 is used to display a UI (User Interface). This UI may include graphics, text, icons, videos, and any combination thereof. When display screen 705 is a touch display screen, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 701 for processing. In this case, display screen 705 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, there may be one display screen 705, disposed on the front panel of control device 700; in other embodiments, there may be at least two display screens, disposed on different surfaces of control device 700 or in a folded design; in still other embodiments, display screen 705 may be a flexible display screen, disposed on a curved or folded surface of control device 700. Furthermore, display screen 705 may be configured as a non-rectangular irregular shape, i.e., a non-rectangular screen. Display screen 705 may be made of materials such as LCD (Liquid Crystal Display) or OLED (Organic Light-Emitting Diode).

[0223] The camera assembly 706 is used to acquire images or videos. Optionally, the camera assembly 706 includes a front-facing camera and a rear-facing camera. Typically, the front-facing camera is located on the front panel of the control device, and the rear-facing camera is located on the back of the control device. In some embodiments, there are at least two rear-facing cameras, which are any one of a main camera, a depth-sensing camera, a wide-angle camera, and a telephoto camera, to achieve background blurring by fusion of the main camera and the depth-sensing camera, panoramic shooting by fusion of the main camera and the wide-angle camera, VR (Virtual Reality) shooting, or other fusion shooting functions. In some embodiments, the camera assembly 706 may also include a flash. The flash can be a single-color temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm-light flash and a cool-light flash, which can be used for light compensation at different color temperatures.

[0224] The audio circuit 707 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, converting the sound waves into electrical signals that are input to the processor 701 for processing, or input to the radio frequency circuit 704 for voice communication. For stereo sound acquisition or noise reduction purposes, multiple microphones may be used, each located at a different part of the control device 700. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert the electrical signals from the processor 701 or the radio frequency circuit 704 into sound waves. The speaker may be a conventional diaphragm speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can convert electrical signals not only into audible sound waves but also into inaudible sound waves for purposes such as distance measurement. In some embodiments, the audio circuit 707 may also include a headphone jack.

[0225] Power supply 708 is used to supply power to the various components in control device 700. Power supply 708 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When power supply 708 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery that is charged via a wired line, while a wireless rechargeable battery is a battery that is charged via a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0226] In some embodiments, the control device 700 further includes one or more sensors 709. The one or more sensors 709 include, but are not limited to, an acceleration sensor 710, a gyroscope sensor 711, a pressure sensor 712, an optical sensor 713, and a proximity sensor 714.

[0227] Accelerometer 710 can detect the magnitude of acceleration along the three coordinate axes of a coordinate system established by control device 700. For example, accelerometer 710 can be used to detect the components of gravitational acceleration along the three coordinate axes. Processor 701 can control display screen 705 to display the user interface in either a landscape or portrait view based on the gravitational acceleration signal acquired by accelerometer 710. Accelerometer 710 can also be used for games or for acquiring user motion data.

[0228] The gyroscope sensor 711 can detect the orientation and rotation angle of the control device 700. The gyroscope sensor 711, in conjunction with the accelerometer sensor 710, can collect 3D motion data from the user on the control device 700. Based on the data collected by the gyroscope sensor 711, the processor 701 can perform the following functions: motion sensing (e.g., changing the UI based on the user's tilt), image stabilization during shooting, game control, and inertial navigation.

[0229] The pressure sensor 712 can be disposed on the side bezel of the control device 700 and / or the lower layer of the display screen 705. When the pressure sensor 712 is disposed on the side bezel of the control device 700, it can detect the user's grip signal on the control device 700, and the processor 701 can perform left / right hand recognition or quick operation based on the grip signal collected by the pressure sensor 712. When the pressure sensor 712 is disposed on the lower layer of the display screen 705, the processor 701 can control the operable controls on the UI interface based on the user's pressure operation on the display screen 705. The operable controls include at least one of button controls, scroll bar controls, icon controls, and menu controls.

[0230] An optical sensor 713 is used to collect ambient light intensity. In one embodiment, the processor 701 can control the display brightness of the display screen 705 based on the ambient light intensity collected by the optical sensor 713. Specifically, when the ambient light intensity is high, the display brightness of the display screen 705 is increased; when the ambient light intensity is low, the display brightness of the display screen 705 is decreased. In another embodiment, the processor 701 can also dynamically adjust the shooting parameters of the camera assembly 706 based on the ambient light intensity collected by the optical sensor 713.

[0231] The proximity sensor 714, also known as a distance sensor, is typically mounted on the front panel of the control device 700. The proximity sensor 714 is used to detect the distance between the user and the front of the control device 700. In one embodiment, when the proximity sensor 714 detects that the distance between the user and the front of the control device 700 is gradually decreasing, the processor 701 controls the display screen 705 to switch from a screen-on state to a screen-off state; when the proximity sensor 714 detects that the distance between the user and the front of the control device 700 is gradually increasing, the processor 701 controls the display screen 705 to switch from a screen-off state to a screen-on state.

[0232] Those skilled in the art will understand that Figure 7 The structure shown does not constitute a limitation on the control device 700, and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0233] In some embodiments, the computer device is provided as a server. Figure 8This is a block diagram of a server provided in an embodiment of this application. The server 800 can vary significantly due to different configurations or performance. It may include one or more Central Processing Units (CPUs) 801 and one or more memories 802. The memories 802 are used to store executable program code, and the processors 801 are configured to execute the executable program code to implement the projectile warning method provided in the various method embodiments described above. Of course, the server may also have wired or wireless network interfaces, a keyboard, and input / output interfaces for input and output. The server may also include other components for implementing device functions, which will not be elaborated here.

[0234] In an exemplary embodiment, a storage medium including program code is also provided, such as a memory 802 including program code, which can be executed by the processor 801 of the server 800 to complete the above-described projectile warning method. Optionally, the storage medium can be a non-transitory computer-readable storage medium, such as ROM (Read-Only Memory), RAM (Random Access Memory), CD-ROM (Compact Disc Read-Only Memory), magnetic tape, floppy disk, and optical data storage device.

[0235] This application also provides a computer-readable storage medium storing at least one piece of program code, which is loaded and executed by a processor to implement the parabolic warning method of any of the above implementations.

[0236] This application also provides a computer program product, which includes computer program code. The computer program code is stored in a computer-readable storage medium. The processor of the computer device reads the computer program code from the computer-readable storage medium and executes the computer program code, causing the computer device to execute the parabolic warning method of any of the above implementations.

[0237] In some embodiments, the computer program product involved in the present application can be deployed and executed on a computer device, or on multiple computer devices located in one location, or on multiple computer devices distributed in multiple locations and interconnected through a communication network. Multiple computer devices distributed in multiple locations and interconnected through a communication network can form a blockchain system.

[0238] The above are merely optional embodiments of this application and are not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for early warning of parabolic events, characterized in that, The method includes: Video signals from the building area are collected using camera equipment, and projectile events are detected based on the video signals. If a pre-projection event is detected based on the first video frame in the video signal, the location of the first falling object on the ground is predicted based on the pre-projection event; The sound and light device corresponding to the first falling object location is determined from multiple candidate sound and light devices, and a preparatory command is sent to the sound and light device. The preparatory command is used to instruct the sound and light device to enter the alarm preparatory state. The sound and light device includes a light device and a sound device. The light device is used to project light onto the falling object location, and the sound device is used to emit a voice signal. If a parabolic event corresponding to the pre-parabolic event is detected based on the first video frame and the second video frame after the first video frame, a start command is sent to the audio-visual device that has entered the alarm preparation state. The start command is used to instruct the audio-visual device that has entered the alarm preparation state to issue an audio-visual alarm. The method further includes: (The first location of the falling object corresponds to multiple lighting devices.) Based on the environmental information of the location of the first falling object, determine the shape of the light to be projected that matches the environmental information; Based on the light shape, the light projection information of each of the multiple lighting devices is determined. The light projection information includes the light projection angle, the light projection area, and the light projection shape. The light projection shapes of the multiple lighting devices constitute the light shape. Sending a preparatory command to the audio-visual device includes: Based on the light projection information of each of the multiple lighting devices, a light preparation command including the light projection information is sent to each of the multiple lighting devices.

2. The method according to claim 1, characterized in that, There are multiple audible and visual devices corresponding to the first falling object location. Sending an activation command to the audible and visual devices that have entered the alarm preparation state includes: Based on the predicted location of the second falling object on the ground based on the parabolic event, at least one audio-visual device corresponding to the second falling object location is determined from among the multiple audio-visual devices corresponding to the first falling object location, and a start command is sent to the at least one audio-visual device.

3. The method according to claim 2, characterized in that, The step of determining the acoustic-optical device corresponding to the location of the first falling object from a plurality of candidate acoustic-optical devices includes: Based on the first falling object location and the first reference distance, the candidate audio-visual devices that are no more than the first reference distance from the first falling object location are selected as the multiple audio-visual devices corresponding to the first falling object location. Determining at least one audio-visual device corresponding to the second falling object position from among multiple audio-visual devices corresponding to the first falling object position includes: Based on the second falling object location and the second reference distance, among the multiple audio-visual devices corresponding to the first falling object location, the audio-visual device that is no more than the second reference distance from the second falling object location is regarded as at least one audio-visual device corresponding to the second falling object location, and the first reference distance is greater than the second reference distance.

4. The method according to claim 3, characterized in that, The method further includes: Based on the event occurrence height of the pre-parabolic event, the first reference distance and the second reference distance are determined respectively, and the first reference distance and the second reference distance are positively correlated with the event occurrence height.

5. The method according to claim 1, characterized in that, The process of determining the detection of a pre-parabolic event includes: If a first object is detected in the building area based on the first video frame in the video signal, a pre-parabolic event is determined to be detected, wherein the first object is an object that appears from a non-edge position in the building area; The process of determining the detection of a parabolic event includes: If, based on the first video frame and the second video frame following the first video frame, it is determined that the motion trajectory of the first object conforms to the reference motion trajectory, a parabolic event corresponding to the pre-parabolic event is detected.

6. The method according to claim 1, characterized in that, The process of determining the detection of a parabolic event includes: If a second object is detected in the building area based on the first video frame of the video signal, the motion trajectory of the second object is determined. If the motion trajectory of the second object matches the reference motion trajectory, a parabolic event is detected. The second object is an object that appears from the edge of the building area. The method further includes: Based on the trajectory of the second object, the location of the third falling object on the ground is predicted, and a start command is sent to the audio-visual device corresponding to the location of the third falling object.

7. The method according to claim 1, characterized in that, There are multiple sound devices corresponding to the first falling object location. The multiple sound devices include a first sound device and a second sound device. The distance between the first sound device and the first falling object location does not exceed a third reference distance. The distance between the second sound device and the first falling object location exceeds the third reference distance but does not exceed the first reference distance. The third reference distance is less than the first reference distance. Sending a preparatory command to the audio-visual device includes: A first voice command is sent to the first sound device, and a second voice command is sent to the second sound device. The first voice command instructs the first sound device to emit a first voice signal, and the second voice command instructs the second sound device to emit a second voice signal. The first voice signal is used to indicate the projectile event, and the second voice signal is used to indicate the projectile event and the location of the first falling object; or... A third voice command is sent to each of the plurality of sound devices, wherein the third voice command is used to instruct the first sound device to emit a first voice signal and to instruct the second sound device to emit a second voice signal.

8. The method according to claim 1, characterized in that, The parabolic event detection based on the video signal includes: Parabolic events are detected based on the video signal using an event detection model.

9. The method according to claim 8, characterized in that, The method further includes: Acquire multiple video frames from a sample video that include parabolic events, the sample video including videos of parabolic events occurring at multiple windows in the building area; The event detection model is trained based on the multiple video frames.

10. A projectile warning device, characterized in that, The device includes: The event detection module is used to collect video signals from the building area through camera equipment and to detect parabolic events based on the video signals. The position prediction module is used to predict the position of a first falling object on the ground based on the pre-projectile event if a pre-projectile event is detected based on the first video frame in the video signal. The device determination module is used to determine the acoustic and optical device corresponding to the location of the first falling object from a plurality of candidate acoustic and optical devices; The instruction sending module is used to send a preparatory instruction to the sound and light device. The preparatory instruction is used to instruct the sound and light device to enter the alarm preparatory state. The sound and light device includes a light device and a sound device. The light device is used to project light onto the location of the falling object. The sound device is used to emit a voice signal. The instruction sending module is further configured to send a start instruction to the audio-visual device that has entered the alarm preparation state if a parabolic event corresponding to the pre-parabolic event is detected based on the first video frame and the second video frame after the first video frame. The start instruction is used to instruct the audio-visual device that has entered the alarm preparation state to issue an audio-visual alarm. The device includes multiple lighting devices corresponding to the first location of the falling object, and the device also includes: A shape determination module is used to determine the shape of the light to be projected that matches the environmental information based on the environmental information of the location of the first falling object. The information determination module is used to determine the light projection information of each of the multiple lighting devices based on the light shape. The light projection information includes the light projection angle, the light projection area, and the light projection shape. The light projection shapes of the multiple lighting devices constitute the light shape. The instruction sending module is used for: Based on the light projection information of each of the multiple lighting devices, a light preparation command including the light projection information is sent to each of the multiple lighting devices.

11. A computer device, characterized in that, The computer device includes one or more processors and one or more memories, wherein at least one piece of program code is stored in the one or more memories, and the at least one piece of program code is loaded and executed by the one or more processors to implement the parabolic warning method as described in any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, The storage medium stores at least one piece of program code, which is loaded and executed by a processor to implement the parabolic warning method as described in any one of claims 1 to 9.

13. A computer program product, characterized in that, The computer program product includes computer program code stored in a computer-readable storage medium. A processor of a computer device reads the computer program code from the computer-readable storage medium and executes the computer program code, causing the computer device to perform the parabolic warning method as described in any one of claims 1 to 9.

Images