Geological disaster safety alarm anti-misentry method, device and equipment and storage medium

Abstract

The application provides a geological disaster safety alarm anti-misentry method, device, equipment and storage medium, wherein the method comprises the following steps: monitoring hidden danger risks in an activity area in real time through positioning navigation; starting human body real-time detection when the hidden danger risks are monitored, obtaining a shooting image in the activity area, and pre-processing the shooting image; selecting a corresponding custom detection method according to environmental shielding, identifying and judging whether the image after preprocessing contains a human body contour through the custom detection method combined with infrared thermal imaging, if the human body contour is detected, verifying whether the identified human body contour is correct through a feature extraction method, and starting an alarm if the human body contour is correct. The application combines positioning navigation technology and image recognition technology, starts human body detection when hidden danger risks are detected, effectively prevents pedestrians from misentering specific areas with hidden danger risks, and improves safety performance.

Description

Technical Field

[0001] This invention relates to the field of security alarm technology, and in particular to a method, device, equipment and storage medium for preventing accidental entry in geological disaster security alarms. Background Technology

[0002] Geological disasters are geological phenomena formed under the influence of natural or human factors. While damaging the environment, they also cause losses to human life and property.

[0003] Among related technologies, global satellite navigation technology can effectively detect spatiotemporal change patterns in a specific area, thereby identifying the possibility of geological disasters. However, after identifying a possible geological disaster, manual alarms are often used, that is, to remind pedestrians not to enter areas with potential risks through broadcasts or text messages. This is inefficient and cannot guarantee that pedestrians will not accidentally enter dangerous areas due to negligence.

[0004] Based on the above analysis of the development status of this technology, the existing technologies lack solutions for identifying areas with potential risks, monitoring pedestrians within those areas, and providing alarm prompts. Summary of the Invention

[0005] The purpose of this invention is to provide a method, device, equipment, and storage medium for preventing accidental entry in geological disaster safety alarms, aiming to solve the above-mentioned problems in the prior art.

[0006] According to a first aspect of the present invention, a method for preventing accidental entry into a geological disaster safety alarm system is provided, comprising:

[0007] Real-time monitoring of potential risks within the activity area via location navigation;

[0008] When potential risks are detected, real-time human body detection is activated to acquire images within the activity area and preprocess the images.

[0009] The corresponding custom detection method is selected based on the environmental occlusion. The custom detection method is combined with infrared thermal imaging to determine whether there is a human body outline in the preprocessed image. If a human body outline is detected, the feature extraction method is used to verify whether the identified human body outline is correct. If it is correct, an alarm is triggered.

[0010] According to a second aspect of the present invention, a geological disaster safety alarm and anti-accidental entry device is provided, comprising:

[0011] The risk monitoring module is used to monitor potential risks in the activity area in real time through positioning and navigation.

[0012] The startup and preprocessing module is used to start real-time human body detection when potential risks are detected, acquire images in the activity area, and preprocess the captured images.

[0013] The recognition and verification module is used to select the corresponding custom detection method based on environmental occlusion. It uses the custom detection method combined with infrared thermal imaging to determine whether there is a human outline in the preprocessed image. If a human outline is detected, the feature extraction method is used to verify whether the recognized human outline is correct. If it is correct, an alarm is triggered.

[0014] According to a third aspect of the present invention, an electronic device is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the geological disaster safety alarm and anti-accidental entry method provided in the first aspect of the present disclosure.

[0015] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which an information transmission implementation program is stored, which, when executed by a processor, implements the steps of the geological disaster safety alarm and anti-accidental entry method provided in the first aspect of the present disclosure.

[0016] The technical solution provided by the embodiments of the present invention has the following beneficial effects: it effectively combines positioning and navigation technology with image recognition technology, and initiates human body detection when a potential hazard is detected, effectively preventing pedestrians from accidentally entering a specific area with a potential hazard. Furthermore, both hazard detection and human body detection are performed in real time, further improving safety performance.

[0017] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in one or more embodiments of this specification or in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart of the geological disaster safety alarm and anti-accidental entry method according to an embodiment of the present invention;

[0020] Figure 2 This is a schematic diagram of a geological disaster safety alarm and anti-accidental entry device according to an embodiment of the present invention;

[0021] Figure 3 This is a schematic diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0022] To enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of this document.

[0023] Method Implementation Examples

[0024] According to an embodiment of the present invention, a method for preventing accidental entry in geological disaster safety alarms is provided. Figure 1 This is a flowchart of the geological disaster safety alarm and anti-accidental entry method according to an embodiment of the present invention, such as... Figure 1 As shown, the geological disaster safety alarm method for preventing accidental entry according to an embodiment of the present invention specifically includes:

[0025] In step S110, the potential risks within the activity area are monitored in real time through positioning and navigation, specifically including:

[0026] The positioning and navigation receiver receives satellite signals in real time and transmits them to the positioning and navigation data processing module through a data communication network. The data processing module decomposes and calculates to determine the current three-dimensional coordinates of the navigation device. By comparing the difference between the hidden danger index under the three-dimensional coordinates and the hidden danger index under the initial coordinates of the navigation device, it is determined whether there is a hidden danger risk based on whether the difference is within the threshold range. The hidden danger index includes landslide index, settlement index and collapse index.

[0027] In this embodiment, the positioning and navigation system adopts the BeiDou satellite navigation system, which is not limited by weather conditions and can form a fully automated detection system that is unattended.

[0028] In step S120, when a potential risk is detected, real-time human body detection is initiated to acquire images within the activity area. The acquired images are then preprocessed, specifically including:

[0029] Human body detection continues until the potential risks are eliminated. This means that it is necessary to monitor in real time whether anyone enters the dangerous area, acquire images of the area, and then perform noise reduction, brightness adjustment, and contrast adjustment on the captured images to obtain pre-processed images.

[0030] In step S130, a corresponding custom detection method is selected based on environmental occlusion. The custom detection method is combined with infrared thermal imaging to determine whether a human body contour exists in the preprocessed image. If a human body contour is detected, a feature extraction method is used to verify whether the identified human body contour is correct. If correct, an alarm is triggered. Specifically, this includes:

[0031] When the interference occlusion rate of the environment to be judged is higher than the occlusion threshold, the Haar cascade gradient judgment method is used as a custom detection method; otherwise, the YOLO model is used as a custom detection algorithm. The Haar cascade gradient judgment method calculates the texture features within the sliding window of the Haar cascade classifier using the HOG gradient direct method, concatenates the texture features of all windows into the total texture features, and determines the contour based on the total texture features.

[0032] The first contour is obtained using a custom detection method;

[0033] The preprocessed image is converted into an infrared image, and the area in the infrared image whose temperature is outside the human body threshold is removed to obtain the second contour. In this embodiment, the human body threshold is 36℃-37℃.

[0034] The regions of the first and second contours are merged to obtain the overall recognition contour. Based on the pre-established contour library, it is initially determined whether the overall recognition contour is a human contour. If it is not a human contour, the determination is stopped and real-time detection continues. If it is initially determined that the overall recognition contour is a human contour, feature extraction methods are used for further confirmation.

[0035] If the overall recognition contour is determined to be a human body contour, a feature extraction method is used to extract the key parts of the overall recognition contour. The key parts include the head, shoulders, hands, and feet. The feature extraction method is a convolutional neural network. If the key parts can be identified, it proves that the initially identified human body contour is correct and someone has entered the activity area. An alarm is then set off using a loudspeaker to indicate that someone has entered the activity area with potential risks. Otherwise, real-time human body detection continues until the positioning and navigation system can no longer detect any potential risks.

[0036] In this embodiment of the invention, key parts of multiple consecutive frames can be identified to obtain continuous motion features, thereby further improving the accuracy of feature extraction and judgment.

[0037] In summary, addressing the existing problems, this invention, a geological disaster safety alarm method to prevent accidental entry, effectively combines positioning and navigation technology with image recognition technology. When a potential hazard is detected, human detection is initiated, effectively preventing pedestrians from accidentally entering specific areas with potential risks. Image processing algorithms improve the clarity of the acquired images. Human detection methods and infrared detection technology are used to identify the contours. During human detection, the appropriate detection method is selected based on interference and occlusion. Haar cascade classifiers and HOG gradient orientation histograms are suitable for confined environments. The Haar cascade internal gradient judgment method integrates the advantages of both methods. After obtaining the initial judgment result, feature extraction is used to further confirm whether the obtained contour corresponds to a person, avoiding errors in human detection and improving the accuracy of recognition. Furthermore, both hazard detection and human detection are performed in real time, further enhancing safety performance.

[0038] Device Examples

[0039] According to an embodiment of the present invention, a geological disaster safety alarm device to prevent accidental entry is provided. Figure 2 This is a schematic diagram of a geological disaster safety alarm and anti-accidental entry device according to an embodiment of the present invention, as shown below. Figure 2 As shown, the geological disaster safety alarm and anti-accidental entry device according to an embodiment of the present invention specifically includes:

[0040] Risk monitoring module 20 is used to monitor potential risks in the activity area in real time through positioning and navigation;

[0041] The startup and preprocessing module 22 is used to start real-time human body detection when a potential hazard is detected, acquire images in the activity area, and preprocess the captured images.

[0042] The identification and verification module 24 is used to select a corresponding custom detection method based on environmental occlusion. It combines the custom detection method with infrared thermal imaging to determine whether a human silhouette exists in the preprocessed image. If a human silhouette is detected, a feature extraction method is used to verify the accuracy of the identified silhouette. If correct, an alarm is triggered. Specifically, it is used for:

[0043] When the interference occlusion rate of the environment to be judged is higher than the occlusion threshold, the Haar cascade gradient judgment method is used as a custom detection method; otherwise, the YOLO model is used as a custom detection algorithm. The Haar cascade gradient judgment method calculates the texture features within the sliding window of the Haar cascade classifier using the HOG gradient direct method, concatenates all window texture features into a total texture feature, and determines the contour based on the total texture feature.

[0044] The first contour is obtained using a custom detection method;

[0045] The preprocessed image is converted into an infrared image, and areas in the infrared image with temperatures outside the human body threshold are removed to obtain the second contour.

[0046] The regions of the first and second contours are merged to obtain the overall recognition contour. Based on the pre-established contour library, it is initially determined whether the overall recognition contour is a human body contour.

[0047] Feature extraction methods are used to extract key parts from the overall recognition contour. These key parts include the head, shoulders, hands, and feet. If the key parts can be identified, it proves that the initially identified human contour is correct and that someone has entered the activity area. Otherwise, real-time human detection continues until the positioning and navigation system can no longer detect any potential risks.

[0048] In summary, addressing the existing problems, this invention, a geological disaster safety alarm and anti-accidental entry device, effectively combines positioning and navigation technology with image recognition technology. When a potential hazard is detected, human detection is initiated, effectively preventing pedestrians from accidentally entering specific areas with potential risks. Image processing algorithms improve the clarity of the acquired images. Human detection methods and infrared detection technology are combined to identify the contours. During human detection, the appropriate detection method is selected based on interference and occlusion. The Haar cascade classifier and HOG gradient orientation histogram are suitable for confined environments. The Haar cascade internal gradient judgment method integrates the advantages of both methods. After obtaining the initial judgment result, feature extraction is used to further confirm whether the obtained contour corresponds to a person, avoiding errors in human detection and improving the accuracy of recognition. Furthermore, both hazard detection and human detection are performed in real time, further enhancing safety performance.

[0049] Electronic device examples

[0050] Figure 3 This is a schematic diagram of an electronic device according to an embodiment of the present invention. The electronic device 300 may include at least one processor 310 and a memory 320. The processor 310 can execute instructions stored in the memory 320. The processor 310 is communicatively connected to the memory 320 via a data bus. In addition to the memory 320, the processor 310 can also be communicatively connected to an input device 330, an output device 340, and a communication device 350 via the data bus.

[0051] Processor 310 can be any conventional processor, such as a commercially available CPU. The processor may also include, for example, a Graphics Processing Unit (GPU), a Field Programmable Gate Array (FPGA), a System on Chip (SOC), an Application Specific Integrated Circuit (ASIC), or a combination thereof.

[0052] The memory 320 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0053] In this embodiment of the present disclosure, the memory 320 stores executable instructions, and the processor 310 can read the executable instructions from the memory 320 and execute the instructions to implement all or part of the steps of the geological disaster safety alarm and anti-accidental entry method in any of the above exemplary embodiments.

[0054] Computer-readable storage medium embodiments

[0055] In addition to the methods and apparatus described above, exemplary embodiments of this disclosure may also be computer program products or computer-readable storage media storing such computer program products, wherein the computer program products include computer program instructions that can be executed by a processor to implement all or part of the steps described in any of the above exemplary embodiments of the geological disaster safety alarm and anti-accidental entry method.

[0056] Computer program products can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. Programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages, and scripting languages ​​(e.g., Python). The program code can be executed entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0057] Computer-readable storage media may take the form of any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media include: static random access memory (SRAM) having one or more electrically connected wires, electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk, or any suitable combination thereof.

[0058] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for preventing accidental entry in geological disaster safety alarms, characterized in that, include: Real-time monitoring of potential risks within the activity area via location navigation; When the aforementioned potential risks are detected, real-time human body detection is initiated, images are acquired within the activity area, and the acquired images are preprocessed. Based on environmental occlusion, a corresponding custom detection method is selected. This custom detection method, combined with infrared thermal imaging, is used to determine whether a human silhouette exists in the preprocessed image. If a human silhouette is detected, a feature extraction method is used to verify its accuracy. If correct, an alarm is triggered. Specifically, this includes: When the interference occlusion rate of the environment to be judged is higher than the occlusion threshold, the Haar cascade gradient judgment method is used as a custom detection method; otherwise, the YOLO model is used as a custom detection algorithm. The Haar cascade gradient judgment method is to calculate the texture features within the sliding window of the Haar cascade classifier using the HOG gradient direct method, stitch all window texture features together to form the total texture features, and determine the contour based on the total texture features. The first contour is obtained using the custom detection method described above; The preprocessed image is converted into an infrared image, and the area in the infrared image whose temperature is outside the human body threshold is removed to obtain the second contour. The regions of the first contour and the second contour are merged to obtain the overall recognition contour. Based on the pre-established contour library, it is initially determined whether the overall recognition contour is a human body contour.

2. The method according to claim 1, characterized in that, The real-time monitoring of potential risks within the activity area via positioning and navigation specifically includes: The current three-dimensional coordinates of the navigation device are determined by the positioning and navigation. By comparing the difference between the hidden danger index under the three-dimensional coordinates and the hidden danger index under the initial coordinates of the navigation device, it is determined whether there is a hidden danger risk based on whether the difference is within the threshold range. The hidden danger index includes landslide index, settlement index and collapse index.

3. The method according to claim 1, characterized in that, The preprocessing of the captured image specifically includes: sequentially performing noise reduction, brightness adjustment, and contrast adjustment on the captured image to obtain a preprocessed image.

4. The method according to claim 1, characterized in that, The step of verifying the accuracy of the identified human body contour using feature extraction methods specifically includes: The key parts in the overall recognition contour are extracted using a feature extraction method, which includes the head, shoulders, hands, and feet. The feature extraction method is a convolutional neural network. If the key parts can be identified, it proves that the initially identified human contour is correct and that someone has entered the activity area. Otherwise, real-time human detection continues until the positioning and navigation system can no longer detect any potential risks.

5. A geological disaster safety alarm and anti-accidental entry device, characterized in that, include: The risk monitoring module is used to monitor potential risks in the activity area in real time through positioning and navigation. The startup and preprocessing module is used to start real-time human body detection when the potential risk is detected, acquire images in the activity area, and preprocess the acquired images. The identification and verification module is used to select a corresponding custom detection method based on environmental occlusion. It then uses this custom detection method combined with infrared thermal imaging to determine whether a human silhouette exists in the preprocessed image. If a human silhouette is detected, a feature extraction method is used to verify the accuracy of the identified silhouette. If correct, an alarm is triggered. Specifically, this module is used for: When the interference occlusion rate of the environment to be judged is higher than the occlusion threshold, the Haar cascade gradient judgment method is used as a custom detection method; otherwise, the YOLO model is used as a custom detection algorithm. The Haar cascade gradient judgment method is to calculate the texture features within the sliding window of the Haar cascade classifier using the HOG gradient direct method, stitch all window texture features together to form the total texture features, and determine the contour based on the total texture features. The first contour is obtained using the custom detection method described above; The preprocessed image is converted into an infrared image, and the area in the infrared image whose temperature is outside the human body threshold is removed to obtain the second contour. The regions of the first contour and the second contour are merged to obtain the overall recognition contour. Based on the pre-established contour library, it is initially determined whether the overall recognition contour is a human body contour.

6. The apparatus according to claim 5, characterized in that, The identification and verification module is specifically used for: When the interference occlusion rate of the environment to be judged is higher than the occlusion threshold, the Haar cascade gradient judgment method is used as a custom detection method; otherwise, the YOLO model is used as a custom detection algorithm. The Haar cascade gradient judgment method is to calculate the texture features within the sliding window of the Haar cascade classifier using the HOG gradient direct method, stitch all window texture features together to form the total texture features, and determine the contour based on the total texture features. The first contour is obtained using the custom detection method described above; The preprocessed image is converted into an infrared image, and the area in the infrared image whose temperature is outside the human body threshold is removed to obtain the second contour. The regions of the first contour and the second contour are merged to obtain the total recognition contour. Based on the pre-established contour library, it is initially determined whether the total recognition contour is a human body contour. The key parts in the overall recognition contour are extracted using a feature extraction method. The key parts include the head, shoulders, hands, and feet. If the key parts can be identified, it proves that the initially identified human contour is correct and that someone has entered the activity area. Otherwise, real-time human detection continues until the positioning and navigation system can no longer detect any potential risks.

7. An electronic device, characterized in that, include: The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the geological disaster safety alarm and anti-accidental entry method as described in any one of claims 1 to 4.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores an information transmission implementation program, which, when executed by a processor, implements the steps of the geological disaster safety alarm and anti-accidental entry method as described in any one of claims 1 to 4.

Images