Safety protection design method and device for community streets

Abstract

The invention discloses a safety protection design method and device for a community street. The safety protection design method for the community streets comprises the following steps: acquiring historical alarm record information of a community; acquiring frequent alarm position information; generating a to-be-monitored range in the virtual reality model of the community; acquiring range information with assistants; judging whether a range to be monitored meets a first preset condition or not according to the range information with the assistants, and if yes, setting a camera device, a simulated sound playing device and a light device for the range to be monitored meeting the first preset condition in the virtual reality model; and correspondingly arranging and associating a camera device, a simulated sound playing device and a light device in a real scene according to the virtual reality model. According to the application, when a problem occurs in a to-be-monitored range, the purposes of taking the video as evidence, performing identification by using the video, performing expelling and threatening by using the simulated sound playing device and the light device, and enabling a person in a central control room to know the situation at any time through the virtual reality model can be achieved.

Description

Technical Field

[0001] The present application relates to the field of street monitoring technology, and in particular to a safety protection design method for community streets, a community street monitoring method, and a safety protection design device for community streets. Background Art

[0002] Most of the existing communities are multifunctional communities, that is, the communities are relatively large, and generally may accommodate military and civilian buildings, commercial supporting facilities, community greening facilities and even kindergartens. This causes some areas to become sparsely populated and prone to danger at night. Although these areas may be within the community, they are relatively remote, which may lead to certain dangers and no assistance being available.

[0003] Therefore, it is desired to have a technical solution to overcome or at least alleviate at least one of the above-mentioned defects of the prior art.

[0004] Application Contents

[0005] The purpose of this application is to provide a safety protection design method for community streets to overcome or at least alleviate at least one of the above-mentioned defects of the prior art.

[0006] To achieve the above objectives, the present application provides a community street safety protection design method, the community street safety protection design method comprising:

[0007] Obtain community historical alarm record information;

[0008] Acquire the location information of frequent alarms according to the historical alarm record information of the community;

[0009] Get a virtual reality model of the community;

[0010] Generating a monitoring area in a virtual reality model of the community;

[0011] Obtain information about the scope of assistance provided by personnel;

[0012] According to the information of the assisting personnel range, it is determined whether there is a monitoring range that meets the first preset condition. If so, then

[0013] In the virtual reality model, a camera device, an onomatopoeia playback device, and a lighting device are set for the monitoring range that meets the first preset condition;

[0014] According to each camera device set in the virtual reality model, a camera device is set at a corresponding position of the real scene and associated with the camera device in the virtual reality model;

[0015] According to each camera device set in the virtual reality model, an onomatopoeia playback device is set at a corresponding position of the real scene and is associated with the onomatopoeia playback device in the virtual reality model;

[0016] According to each lighting device set in the virtual reality model, the lighting device is set at the corresponding position of the real scene and associated with the lighting device in the virtual reality model.

[0017] Optionally, the community historical alarm record information includes case type information and location coordinate information corresponding to each case type information;

[0018] Acquiring the frequent alarm location information according to the community historical alarm record information includes:

[0019] Clustering each location coordinate information according to the location coordinate information corresponding to each case type information, thereby obtaining multiple clusters;

[0020] A virtual circle capable of containing each position coordinate information under the cluster is set for each cluster, and the radius information of the virtual circle is obtained, and the coordinate information included in each virtual circle is the frequent alarm position information.

[0021] Optionally, generating a monitoring range in the virtual reality model of the community includes:

[0022] Obtaining the center coordinates of each cluster in the virtual reality model of the community;

[0023] Each of the central coordinates is taken as a circle point and the radius information of the virtual circle corresponding to each central coordinate is taken as a radius to obtain each monitoring range in the virtual reality model of the community. A central coordinate and a radius information of a virtual circle are used to generate a monitoring range.

[0024] Optionally, each of the assisting personnel range information includes a plurality of range coordinate points;

[0025] The step of judging whether a monitoring range meets the first preset condition according to the assisting personnel range information includes:

[0026] Perform the following processing for each range to be monitored:

[0027] Compare each coordinate point within the range to be monitored with each range coordinate point with assisting personnel range information, so as to obtain the number of coordinate points within the range to be monitored that are different from any range coordinate point with assisting personnel range information, and the coordinate point that is different from any range coordinate point with assisting personnel range information is called an uncovered coordinate point;

[0028] Determine whether the percentage of uncovered coordinate points to the total coordinate points within the monitoring range is higher than the preset percentage. If so,

[0029] Confirm that the range to be monitored meets the first preset condition.

[0030] The present application also provides a community street monitoring method, which is used by the community street security protection design method as described above, and the community street monitoring method includes:

[0031] The cloud obtains the video stream information transmitted by each camera device respectively;

[0032] The cloud performs image recognition and audio recognition on each video stream information to determine whether there are special circumstances. If so,

[0033] Get the current time point information;

[0034] Interference information is generated according to the current time point information and is sent to the onomatopoeia playing device and / or the lighting device.

[0035] Optionally, the cloud performs image recognition and audio recognition on each video stream information respectively, so as to determine whether there are special circumstances including:

[0036] Recognize each frame image in the video stream information to obtain a first recognition result;

[0037] Identify the audio information in the video stream information to obtain a second identification result;

[0038] Determine whether there are special circumstances based on the first recognition result and the second recognition result.

[0039] Optionally, identifying each frame image in the video stream information to obtain a first identification result includes:

[0040] Get the improved YOLOv8 model;

[0041] Input each frame of image into the improved YOLOv8 model to obtain human target information in the image;

[0042] Get the trained SVM action classifier;

[0043] Extract feature information of each human-shaped target information;

[0044] The feature information is input into the trained SVM action classifier to obtain action classification information, and the action classification information is used as the first recognition result.

[0045] Optionally, the identifying the audio information in the video stream information to obtain a second identification result includes:

[0046] Obtain a semantic recognition model;

[0047] Extracting audio features from the acquired audio information;

[0048] The audio feature is input into the semantic recognition model to obtain a semantic recognition result, and the semantic recognition result is used as the second recognition result.

[0049] Optionally, judging whether there is a special situation according to the first recognition result and the second recognition result includes:

[0050] When the first recognition result is the same as the second recognition result, it is determined that there is a special case.

[0051] The present application also provides a safety protection design device for community streets, the safety protection design device for community streets comprising:

[0052] A community historical alarm record information acquisition module, the community historical alarm record information acquisition module is used to acquire community historical alarm record information;

[0053] A frequent alarm location information acquisition module, the frequent alarm location information acquisition module is used to acquire frequent alarm location information based on the community historical alarm record information;

[0054] A virtual reality model acquisition module, wherein the virtual reality model acquisition module is used to acquire a virtual reality model of a community;

[0055] A module for acquiring a range to be monitored, the module for acquiring a range to be monitored being used to generate a range to be monitored in a virtual reality model of the community;

[0056] An assisting personnel range information acquisition module, the assisting personnel range information acquisition module is used to acquire assisting personnel range information;

[0057] A judgment module, the judgment module is used to judge whether there is a monitoring range that meets a first preset condition according to the assisting personnel range information;

[0058] A virtual reality model installation module, the virtual reality model installation module is used to set a camera device, an onomatopoeia playback device, and a lighting device for a monitoring range that meets the first preset condition in the virtual reality model;

[0059] A real camera device installation module, the real camera device installation module is used to set the camera device at the corresponding position of the real scene according to each camera device set in the virtual reality model and associate it with the camera device in the virtual reality model;

[0060] A real-life onomatopoeia playback device installation module, the real-life onomatopoeia playback device installation module is used to set an onomatopoeia playback device at a corresponding position of the real scene according to each camera device set in the virtual reality model and associate it with the onomatopoeia playback device in the virtual reality model;

[0061] A real lighting device installation module is used to set lighting devices at corresponding positions of the real scene according to the lighting devices set in the virtual reality model and associate them with the lighting devices in the virtual reality model.

[0062] The community street safety protection design method of the present application first generates the scope that needs to be monitored, and then after determining the scope that needs to be supervised, the corresponding camera device, onomatopoeia playback device, and lighting device are installed in the scope that needs to be supervised, so that once problems occur in these scopes again, there will be video evidence, video identification, and onomatopoeia playback devices and lighting devices to expel and intimidate, and the virtual reality model allows people in the control room to understand the situation at any time. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 It is a flow chart of a safety protection design method for community streets according to an embodiment of the present application.

[0064] Figure 2 It is a schematic diagram of the structure of an electronic device in one embodiment of the present application. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical scheme and advantages of the implementation of this application clearer, the technical scheme in the embodiment of this application will be described in more detail below in conjunction with the drawings in the embodiment of this application. In the drawings, the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. The described embodiments are part of the embodiments of this application, not all of them. The embodiments described below with reference to the drawings are exemplary and are intended to be used to explain this application, and should not be construed as limitations on this application. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. The embodiments of this application are described in detail below in conjunction with the drawings.

[0066] In the description of the present application, it should be understood that the terms "center", "longitudinal", "lateral", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the scope of protection of the present application.

[0067] Figure 1 It is a flow chart of a safety protection design method for community streets according to an embodiment of the present application.

[0068] like Figure 1 The community street safety protection design methods shown include:

[0069] Step 1: Obtain community historical alarm record information;

[0070] Step 2: Obtaining the location information of frequent alarms based on the historical alarm record information of the community;

[0071] Step 3: Obtain a virtual reality model of the community;

[0072] Step 4: Generate a monitoring range in the virtual reality model of the community;

[0073] Step 5: Obtain information about the scope of assisting personnel;

[0074] Step 6: Determine whether there is a monitoring range that meets the first preset condition based on the information of the assisting personnel range. If so,

[0075] Step 7: In the virtual reality model, a camera device, an onomatopoeia playback device, and a lighting device are set for the monitoring range that meets the first preset condition;

[0076] Step 8: Setting a camera device at a corresponding position of the real scene according to each camera device set in the virtual reality model and associating it with the camera device in the virtual reality model;

[0077] Step 9: setting an onomatopoeia playback device at a corresponding position of the real scene according to each camera device set in the virtual reality model and associating it with the onomatopoeia playback device in the virtual reality model;

[0078] Step 10: According to each lighting device set in the virtual reality model, the lighting device is set at the corresponding position of the real scene and associated with the lighting device in the virtual reality model.

[0079] In this embodiment, the community historical alarm record information includes case type information and location coordinate information corresponding to each case type information. It is understandable that the community historical alarm record information may also include other information, such as the number of personnel, personnel face images, appearance images, etc.

[0080] In this embodiment, obtaining the frequent alarm location information according to the community historical alarm record information includes:

[0081] Clustering each location coordinate information according to the location coordinate information corresponding to each case type information, thereby obtaining multiple clusters;

[0082] A virtual circle capable of containing each position coordinate information under the cluster is set for each cluster, and the radius information of the virtual circle is obtained, and the coordinate information included in each virtual circle is the frequent alarm position information.

[0083] In this embodiment, the present application performs clustering by using a k-means clustering algorithm.

[0084] In this embodiment, after clustering is completed, a virtual circle is set with the center point of each cluster as the center, and the radius of the virtual circle enables all points belonging to the cluster to be located within the virtual circle.

[0085] In this embodiment, generating a monitoring range in the virtual reality model of the community includes:

[0086] Obtain the center coordinates of each cluster in the virtual reality model of the community;

[0087] Each of the central coordinates is taken as a circle point and the radius information of the virtual circle corresponding to each central coordinate is taken as a radius to obtain each monitoring range in the virtual reality model of the community. A central coordinate and a radius information of a virtual circle are used to generate a monitoring range.

[0088] In the present embodiment, each of the assisting personnel range information includes multiple range coordinate points. Specifically, the assisting personnel range information includes a coordinate point group and assisting personnel information. One coordinate point group corresponds to at least one assisting personnel information. The assisting personnel information represents the information of a person who can provide assistance. The coordinate point group represents the assisting personnel information that can correspond to the coordinate point group or the matters within the coordinate point group. In the present embodiment, the assisting personnel range information is set to determine densely populated areas. Although densely populated areas also require video surveillance, most densely populated areas will not use the design method of the present application, especially the onomatopoeia playback device and lighting device of the present application will not be installed, because the purpose of the present application is mainly for relatively remote areas away from densely populated areas. This is why the present application must first determine the range to be monitored.

[0089] The step of judging whether a monitoring range meets the first preset condition according to the assisting personnel range information includes:

[0090] Perform the following processing for each range to be monitored:

[0091] Compare each coordinate point within the range to be monitored with each range coordinate point with assisting personnel range information, so as to obtain the number of coordinate points within the range to be monitored that are different from any range coordinate point with assisting personnel range information, and the coordinate point that is different from any range coordinate point with assisting personnel range information is called an uncovered coordinate point;

[0092] Determine whether the percentage of uncovered coordinate points to the total coordinate points within the monitoring range is higher than the preset percentage. If so,

[0093] Confirm that the range to be monitored meets the first preset condition.

[0094] For example, suppose there are three coordinate points (ABC) within the range to be monitored, and there are 2 range coordinate points of the assisting personnel range information (DF respectively). Suppose coordinate point A is the same as coordinate point D, and coordinate point B is the same as coordinate point F. Suppose the preset percentage is 40%, and now one of the three coordinate points is different, which is about 33%, then it is judged as no. For example, if we have 4 coordinate points, but only 2 are the same, then it is judged as yes.

[0095] The present application also provides a community street monitoring method, which is used through the community street safety protection design method as described above, that is, the community streets designed through the community street safety protection design method of the present application can be monitored using the community street monitoring method of the present application.

[0096] The community street monitoring method of this application includes:

[0097] The cloud obtains the video stream information transmitted by each camera device respectively;

[0098] The cloud performs image recognition and audio recognition on each video stream information to determine whether there are special circumstances. If so,

[0099] Get the current time point information;

[0100] Interference information is generated according to the current time point information and is sent to the onomatopoeia playing device and / or the lighting device.

[0101] Through the method of the present application, when a special situation occurs, it is possible to determine which interference information to use based on the current time point information. For example, if the current time point is daytime, it is meaningless to use the lighting device. At this time, only the onomatopoeia playback device is used. If it is night, you can choose to use the onomatopoeia playback device and the lighting device at the same time, or use the lighting device alone.

[0102] It is understandable that the generation of interference information can be set as needed. For example, when the image recognition and audio recognition of each video stream information are judged by the cloud, the semantic recognition technology and image recognition technology are used, so the obtained results include action behaviors or sound behaviors. Action behaviors are such as fighting, and sound behaviors may also be quarrels. At this time, different interference information can be set according to different behaviors. It is understandable that the setting of interference information does not belong to the protection content of this application, so it will not be repeated. It is understandable that the interference information can be the playing of certain onomatopoeic sounds (such as sirens, barking dogs, etc.), and the lights can be some strong flashing lights.

[0103] In this embodiment, the cloud performs image recognition and audio recognition on each video stream information to determine whether there are special circumstances including:

[0104] Recognize each frame image in the video stream information to obtain a first recognition result;

[0105] Identify the audio information in the video stream information to obtain a second identification result;

[0106] Determine whether there are special circumstances based on the first recognition result and the second recognition result.

[0107] In this embodiment, the step of identifying each frame image in the video stream information to obtain a first identification result includes:

[0108] Get the improved YOLOv8 model;

[0109] Input each frame of image into the improved YOLOv8 model to obtain human target information in the image;

[0110] Get the trained SVM action classifier;

[0111] Extract feature information of each human-shaped target information;

[0112] The feature information is input into the trained SVM action classifier to obtain action classification information, and the action classification information is used as the first recognition result.

[0113] In this embodiment, the improved YOLOv8 model of the present application has the following characteristics:

[0114] The improved YOLOv8 model of this application modifies the existing C2f layer as follows:

[0115] The C2f module uses a chunking operation to evenly divide the input feature map into multiple sub-parts. Each sub-part is processed independently through a bottleneck layer or other convolution operations, and finally the processed features are spliced ​​together. The C2f module allows richer gradient flow, enhances feature extraction capabilities, and reduces computational complexity.

[0116] The present application replaces the bottleneck layer of the prior art. Specifically, the bottleneck layer of the prior art includes a depthwise separable convolution layer (depthwise conv), which is replaced by a ghost convolution module in the present application, and the last convolution layer of the bottleneck layer is replaced by a weighted convolution module in the present application.

[0117] Perform global average pooling on the feature map. Use a two-layer MLP (multi-layer perceptron) module with a softmax activation function to generate dynamic weights α. Then apply ghost convolution to generate "ghost features" on the "basic features". Then, concatenate the features. After concatenation, assign the dynamic weights α generated in the first step to the values ​​​​separately. In other words, assume that we have generated k dynamic weights from α1-α according to the input k At this time, each basic feature after ghost convolution generates a ghost feature. At this time, the basic feature and the ghost feature are spliced ​​to form a combined feature that has both basic features and ghost features. There are a total of k such combined features. After that, k dynamic weights are assigned to these k groups of combined features one by one, weighted, and finally summed.

[0118] Specifically, the formula of this application can be expressed as follows:

[0119]

[0120] where ω primary,k is the kth standard convolution kernel, is the number of ghost features generated for each input feature map, f i is a linear transformation function, α k is the kth dynamic weight and * indicates the convolution operation.

[0121] When calculating the loss function, the comprehensive loss function usually includes classification loss, positioning loss and key point loss. The definitions are as follows:

[0122] ζ=λ cls ζ cls +λ locζ loc +λ pose ζ pose ;

[0123] Among them, cls Refers to classification loss, which measures the gap between the predicted category and the true category. Use cross-entropy loss. ζ loc It refers to the position loss, which measures the difference between the predicted bounding box and the true bounding box. pose Refers to the pose estimation loss, which measures the difference between the predicted key point position and the true key point position. The mean squared error (MSE) is used. cls , loc , pose These are the weight hyperparameters for the corresponding loss terms, which are used to balance the contribution of different loss terms to the total loss.

[0124] ζ cls The classification loss calculation formula is as follows:

[0125]

[0126] Where N is the number of samples, C is the number of categories, and y i,c is the true label of sample i belonging to category c, is the probability of class c predicted by the model.

[0127] ζ loc The positioning loss calculation formula is as follows:

[0128]

[0129] Among them, b i is the true bounding box of sample i, is the bounding box predicted by the model.

[0130] ζ pose The posture estimation loss calculation formula is as follows:

[0131]

[0132] Among them, K is the number of key points, p i,j is the true position of the jth key point of sample i, is the position of the jth keypoint predicted by the model.

[0133] When using the improved YOLO model of the present application, the number of parameters of the model will increase significantly after adding weighted convolution and ghost convolution. Therefore, by combining ghost convolution and weighted convolution, replacing the C2f layer in yolov8n with a solution modified according to the present application, a lightweight model with greatly reduced parameters and computational complexity and basically unchanged accuracy can be obtained.

[0134] In this embodiment, the step of identifying the audio information in the video stream information to obtain a second identification result includes:

[0135] Obtain a semantic recognition model;

[0136] Extracting audio features from the acquired audio information;

[0137] The audio feature is input into the semantic recognition model to obtain a semantic recognition result, and the semantic recognition result is used as the second recognition result.

[0138] In this embodiment, judging whether there is a special situation according to the first recognition result and the second recognition result includes:

[0139] When the first recognition result is the same as the second recognition result, it is determined that there is a special case.

[0140] It is understandable that other schemes may also be included. For example, when the first recognition result is different from the second recognition result, the time length of the currently acquired video stream information is obtained. If the time length is less than the first time length threshold (for example, 5 seconds), the recognition of the present application is continued until the second time length threshold (for example, 10 seconds) is reached. In this way, it is possible to prevent the present application from being unable to be recognized in a short period of time due to unclear actual circumstances and the occurrence of recognition errors due to less acquired content. In this way, by increasing the monitoring time, more video information and voice information can be obtained, which may further increase the accuracy of recognition.

[0141] It is understandable that other judgment methods may also be set, which will not be described in detail here.

[0142] The present application also provides a safety protection design device for community streets, which includes a community historical alarm record information acquisition module, a frequent alarm location information acquisition module, a virtual reality model acquisition module, a monitoring range acquisition module, an assisting personnel range information acquisition module, a judgment module, a virtual reality model installation module, a real camera device installation module, a real onomatopoeia playback device installation module, and a real lighting device installation module.

[0143] The community historical alarm record information acquisition module is used to obtain the community historical alarm record information;

[0144] The frequent alarm location information acquisition module is used to acquire the frequent alarm location information according to the community historical alarm record information;

[0145] The virtual reality model acquisition module is used to acquire the virtual reality model of the community;

[0146] The module for acquiring the range to be monitored is used to generate the range to be monitored in the virtual reality model of the community;

[0147] The assisting personnel scope information acquisition module is used to acquire the assisting personnel scope information;

[0148] The judging module is used to judge whether a monitoring range meets the first preset condition according to the assisting personnel range information;

[0149] The virtual reality model installation module is used to set a camera device, an onomatopoeia playback device, and a lighting device for the monitoring range that meets the first preset condition in the virtual reality model;

[0150] The real camera device installation module is used to set the camera device at the corresponding position of the real scene according to each camera device set in the virtual reality model and associate it with the camera device in the virtual reality model;

[0151] The real sound-onomatopoeia playback device installation module is used to set the sound-onomatopoeia playback device at the corresponding position of the real scene according to each camera device set in the virtual reality model and associate it with the sound-onomatopoeia playback device in the virtual reality model;

[0152] The real lighting device installation module is used to set the lighting devices at the corresponding positions of the real scene according to the lighting devices set in the virtual reality model and associate them with the lighting devices in the virtual reality model.

[0153] It should be noted that the above explanations of the method embodiment are also applicable to the device of this embodiment and will not be repeated here.

[0154] The present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor. When the processor executes the computer program, the above-mentioned community street safety protection design method is implemented.

[0155] The present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it can implement the above-mentioned community street safety protection design method.

[0156] Figure 2It is an exemplary structural diagram of an electronic device that can implement the community street safety protection design method provided according to an embodiment of the present application.

[0157] like Figure 2 As shown, the electronic device includes an input device 501, an input interface 502, a central processor 503, a memory 504, an output interface 505, and an output device 506. The input interface 502, the central processor 503, the memory 504, and the output interface 505 are interconnected through a bus 507, and the input device 501 and the output device 506 are connected to the bus 507 through the input interface 502 and the output interface 505, respectively, and then connected to other components of the electronic device. Specifically, the input device 504 receives input information from the outside, and transmits the input information to the central processor 503 through the input interface 502; the central processor 503 processes the input information based on the computer executable instructions stored in the memory 504 to generate output information, temporarily or permanently stores the output information in the memory 504, and then transmits the output information to the output device 506 through the output interface 505; the output device 506 outputs the output information to the outside of the electronic device for use by the user.

[0158] That is to say, Figure 2 The electronic device shown can also be implemented as comprising: a memory storing computer executable instructions; and one or more processors, which can implement the combination when executing the computer executable instructions. Figure 1 Describes a community street safety design approach.

[0159] In one embodiment, Figure 2 The electronic device shown can be implemented to include: a memory 504, configured to store executable program code; one or more processors 503, configured to run the executable program code stored in the memory 504 to execute the safety protection design method for community streets in the above-mentioned embodiment.

[0160] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0161] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0162] Computer readable media include permanent and non-permanent, removable and non-removable, and the media can be implemented by any method or technology to store information. The information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), data versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0163] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0164] In addition, it is obvious that the word "comprising" does not exclude other units or steps. Multiple units, modules or devices stated in the device claim can also be implemented by one unit or the overall device through software or hardware.

[0165] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and a module, a program segment or a part of a code includes one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes identified in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or the total flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0166] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0167] In addition, it is obvious that the word "comprising" does not exclude other units or steps. Multiple units, modules or devices stated in the device claim can also be implemented by one unit or the overall device through software or hardware.

[0168] Although the present application is disclosed as above in terms of a preferred embodiment, it is not intended to limit the present application. Any technical personnel in this field may make possible changes and modifications without departing from the spirit and scope of the present application. Therefore, the scope of protection of the present application shall be based on the scope defined by the claims of the present application.

[0169] Finally, it should be pointed out that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application is described in detail with reference to the above embodiments, a person skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A safety protection design method for community streets, characterized in that: The community street safety protection design method includes: Obtain community historical alarm record information; Acquire the location information of frequent alarms according to the historical alarm record information of the community; Get a virtual reality model of the community; Generating a monitoring area in a virtual reality model of the community; Obtain information about the scope of assistance provided by personnel; According to the information of the assisting personnel range, it is determined whether there is a monitoring range that meets the first preset condition. If so, then In the virtual reality model, a camera device, an onomatopoeia playback device, and a lighting device are set for the monitoring range that meets the first preset condition; According to each camera device set in the virtual reality model, a camera device is set at a corresponding position of the real scene and associated with the camera device in the virtual reality model; According to each camera device set in the virtual reality model, an onomatopoeia playback device is set at a corresponding position of the real scene and is associated with the onomatopoeia playback device in the virtual reality model; According to each lighting device set in the virtual reality model, the lighting device is set at the corresponding position of the real scene and associated with the lighting device in the virtual reality model.

2. The community street safety protection design method according to claim 1, characterized in that: The community historical alarm record information includes case type information and location coordinate information corresponding to each case type information; Acquiring the frequent alarm location information according to the community historical alarm record information includes: Clustering each location coordinate information according to the location coordinate information corresponding to each case type information, thereby obtaining multiple clusters; A virtual circle capable of containing each position coordinate information under the cluster is set for each cluster, and the radius information of the virtual circle is obtained, and the coordinate information included in each virtual circle is the frequent alarm position information.

3. The community street safety protection design method according to claim 2, characterized in that: The generating of the monitoring range in the virtual reality model of the community includes: Obtaining the center coordinates of each cluster in the virtual reality model of the community; Each of the central coordinates is taken as a circle point, and the radius information of the virtual circle corresponding to each central coordinate is taken as a radius to obtain each monitoring range in the virtual reality model of the community. A central coordinate and a radius information of a virtual circle are used to generate a monitoring range.

4. The community street safety protection design method according to claim 3, characterized in that: Each of the assisting personnel range information includes a plurality of range coordinate points; The step of judging whether a monitoring range meets the first preset condition according to the assisting personnel range information includes: Perform the following processing for each range to be monitored: Compare each coordinate point within the range to be monitored with each range coordinate point with assisting personnel range information, so as to obtain the number of coordinate points within the range to be monitored that are different from any range coordinate point with assisting personnel range information, and the coordinate point that is different from any range coordinate point with assisting personnel range information is called an uncovered coordinate point; Determine whether the percentage of uncovered coordinate points to the total coordinate points within the monitoring range is higher than the preset percentage. If so, Confirm that the range to be monitored meets the first preset condition.

5. A community street monitoring method, said community street monitoring method is used to design a community street safety protection method according to any one of claims 1 to 4, characterized in that: The community street monitoring method comprises: The cloud obtains the video stream information transmitted by each camera device respectively; The cloud performs image recognition and audio recognition on each video stream information to determine whether there are special circumstances. If so, Get the current time point information; Interference information is generated according to the current time point information and is sent to the onomatopoeia playing device and / or the lighting device.

6. The community street monitoring method according to claim 5, characterized in that: The cloud performs image recognition and audio recognition on each video stream information to determine whether there are special circumstances including: Recognize each frame image in the video stream information to obtain a first recognition result; Identify the audio information in the video stream information to obtain a second identification result; It is determined whether there are special circumstances based on the first recognition result and the second recognition result.

7. The community street monitoring method according to claim 6, characterized in that: The identifying each frame image in the video stream information to obtain a first identification result includes: Get the improved YOLOv8 model; Input each frame of image into the improved YOLOv8 model to obtain human target information in the image; Get the trained SVM action classifier; Extract feature information of each human-shaped target information; The feature information is input into the trained SVM action classifier to obtain action classification information, and the action classification information is used as the first recognition result.

8. The community street monitoring method according to claim 7, characterized in that: The identifying the audio information in the video stream information to obtain a second identification result includes: Obtain a semantic recognition model; Extracting audio features from the acquired audio information; The audio feature is input into the semantic recognition model to obtain a semantic recognition result, and the semantic recognition result is used as the second recognition result.

9. The community street monitoring method according to claim 8, characterized in that: Judging whether there is a special situation according to the first recognition result and the second recognition result includes: When the first recognition result is the same as the second recognition result, it is determined that there is a special case.

10. A safety protection design device for community streets, characterized in that: The community street safety protection design device includes: A community historical alarm record information acquisition module, the community historical alarm record information acquisition module is used to acquire community historical alarm record information; A frequent alarm location information acquisition module, the frequent alarm location information acquisition module is used to acquire frequent alarm location information according to the community historical alarm record information; A virtual reality model acquisition module, wherein the virtual reality model acquisition module is used to acquire a virtual reality model of a community; A module for acquiring a range to be monitored, the module for acquiring a range to be monitored being used to generate a range to be monitored in a virtual reality model of the community; An assisting personnel range information acquisition module, the assisting personnel range information acquisition module is used to acquire assisting personnel range information; A judgment module, the judgment module is used to judge whether there is a monitoring range that meets a first preset condition according to the assisting personnel range information; A virtual reality model installation module, the virtual reality model installation module is used to set a camera device, an onomatopoeia playback device, and a lighting device for a monitoring range that meets the first preset condition in the virtual reality model; A real camera device installation module, the real camera device installation module is used to set the camera device at the corresponding position of the real scene according to each camera device set in the virtual reality model and associate it with the camera device in the virtual reality model; A real-life onomatopoeia playback device installation module, the real-life onomatopoeia playback device installation module is used to set an onomatopoeia playback device at a corresponding position of the real scene according to each camera device set in the virtual reality model and associate it with the onomatopoeia playback device in the virtual reality model; A real lighting device installation module is used to set lighting devices at corresponding positions of the real scene according to the lighting devices set in the virtual reality model and associate them with the lighting devices in the virtual reality model.

Images