A special scene early warning shielding method and device, electronic equipment and storage medium

Abstract

The application discloses a special scene early warning shielding method and device, electronic equipment and a storage medium, and the method comprises the steps of obtaining a fire image to be identified and a special scene reference image; adopting a preset scale invariant feature transformation algorithm to determine matching feature points between the fire image to be identified and the special scene reference image, and determining a Hausdorff distance between the fire image to be identified and the special scene reference image according to the matching feature points; judging the size relationship between the Hausdorff distance and a preset threshold value; if the Hausdorff distance is smaller than the preset threshold value, it is determined that the fire image to be identified is a special scene image, and a fire early warning shielding program is started. The application solves the technical problem that repeated alarms are frequently received in the prior art under special scenes such as hot work, fire drill, facility maintenance and the like.

Description

Technical Field

[0001] This invention relates to the field of fire early warning technology, specifically to a method, device, electronic equipment, and storage medium for early warning and shielding in special scenarios. Background Technology

[0002] Automatic fire alarm systems, in the early stages of a fire, convert physical quantities such as smoke, heat, and light radiation generated by combustion into electrical signals through fire detectors (such as heat detectors, smoke detectors, and light detectors). These signals are then transmitted to the fire alarm controller, which simultaneously displays the location of the fire and records the time of its occurrence. Automatic fire alarm systems play a crucial role in building fire prevention.

[0003] With the widespread application of urban fire remote monitoring systems, problems have emerged in the reception of alarms from automatic fire alarm systems. In special scenarios such as hot work, fire drills, and routine facility maintenance, the urban fire remote monitoring system may receive frequent, repetitive alarms from a specific area on the fire alarm control panel within a short period. This necessitates personnel first making phone calls to confirm the actual situation on-site and then continuously handling the alarms. This process of handling repeated alarms can easily lead to desensitization among personnel, potentially causing them to mistake other genuine alarms for false alarms, resulting in unnecessary accidents and losses.

[0004] Therefore, it is essential to research a special scenario early warning and shielding method by combining Internet of Things and artificial intelligence technologies. Summary of the Invention

[0005] The purpose of this invention is to overcome the above-mentioned technical deficiencies and provide a special scenario early warning and shielding method, device, electronic device and storage medium to solve the technical problem of frequent repeated alarms in special scenarios such as hot work, fire drills and facility maintenance in the prior art.

[0006] To achieve the above-mentioned technical objectives, the present invention adopts the following technical solution:

[0007] In a first aspect, the present invention provides a special scenario early warning shielding method, comprising:

[0008] Acquire images of the fire to be identified and reference images of special scenes;

[0009] A preset scale-invariant feature transformation algorithm is used to determine the matching feature points between the fire image to be identified and the special scene reference image, and the Hausdorf distance between the fire image to be identified and the special scene reference image is determined based on the matching feature points.

[0010] Determine the relationship between the Hausdorff distance and a preset threshold;

[0011] If the Hausdorf distance is less than the preset threshold, the fire image to be identified is determined to be a special scene image, and the fire warning shielding program is activated.

[0012] In some embodiments, determining the Hausdorff distance between the fire image to be identified and the special scene reference image using a preset scale-invariant feature transform algorithm includes:

[0013] Using a preset Gaussian differential function, the feature points to be identified in the fire image to be identified, and the reference feature points in the special scene reference image are determined, wherein the feature points to be identified and the reference feature points are matched pairwise.

[0014] Determine the bidirectional Hausdorff distance between the feature point to be identified and the reference feature point.

[0015] In some embodiments, determining the feature points to be identified in the fire image and the reference feature points in the special scene reference image based on a preset Gaussian differential function includes:

[0016] Based on a preset Gaussian differential function, the feature points to be identified in the fire image to be identified, as well as the reference feature points in the special scene reference image, are extracted.

[0017] Determine the positions of the feature point to be identified and the reference feature point, as well as the direction of the feature to be identified and the direction of the reference feature;

[0018] Based on the position of the feature point to be identified and the orientation of the feature to be identified, a feature vector to be identified is constructed;

[0019] Based on the position and orientation of the reference feature points, a reference feature vector is constructed;

[0020] Based on the feature vector to be identified and the reference feature vector, the feature points to be identified and the reference feature points that match each other are determined.

[0021] In some embodiments, the Gaussian differential function can be expressed by the following formula:

[0022] Where σ is a parameter related to size, x and y represent the coordinates of pixels in the image information, and m and n are parameters related to feature points.

[0023] In some embodiments, determining the bidirectional Hausdorff distance between the feature point to be identified and the reference feature point includes:

[0024] Construct the identification set of the feature points to be identified and the reference set of the reference feature points;

[0025] Traverse all feature points to be identified in the identification set, calculate the distance between the feature point to be identified and all feature points in the reference set, determine the corresponding first shortest distance, and construct a first target set of the plurality of first shortest distances;

[0026] Traverse the reference feature points in the reference set, calculate the distance between the reference feature points and all feature points in the identification set, determine the corresponding second shortest distance, and construct the second target set of the multiple second shortest distances;

[0027] Based on the first target set, determine the first one-way Hausdorff distance; based on the second target set, determine the second one-way Hausdorff distance.

[0028] The larger of the first one-way Hausdorff distance and the second one-way Hausdorff distance is determined to be the two-way Hausdorff distance.

[0029] In some embodiments, obtaining a reference image for a specific scene includes:

[0030] Acquire raw images from multiple different scenarios, including hot work scenarios, fire drills, and regular facility maintenance.

[0031] The multiple original images are used to construct a special scene reference image set.

[0032] In some embodiments, determining the difference value between the fire image to be identified and the special scene reference image based on the scale-invariant feature transformation algorithm further includes determining the difference value between the fire image to be identified and each original image in the special scene reference image set.

[0033] Secondly, the present invention also provides a special scene early warning shielding device, comprising:

[0034] The acquisition module is used to acquire images of fires to be identified and reference image sets for special scenes;

[0035] The Hausdorff distance determination module is used to determine the matching feature points between the fire image to be identified and the special scene reference image by using a preset scale-invariant feature transformation algorithm, and to determine the Hausdorff distance between the fire image to be identified and the special scene reference image based on the matching feature points.

[0036] The judgment module is used to determine the relationship between the Hausdorf distance and the threshold.

[0037] If the Hausdorff distance is less than the threshold, the target module determines that the fire image to be identified is a special scene image and initiates the fire early warning shielding procedure.

[0038] Thirdly, the present invention also provides an electronic device, comprising: a processor and a memory;

[0039] The memory stores a computer-readable program that can be executed by the processor;

[0040] When the processor executes the computer-readable program, it implements the steps in the special scenario early warning and shielding method described above.

[0041] Fourthly, the present invention also provides a computer-readable storage medium storing one or more programs that can be executed by one or more processors to implement the steps in the special scenario warning and shielding method described above.

[0042] Compared with existing technologies, the special scene early warning and shielding method, device, electronic device, and storage medium provided by this invention first identify special scenes that do not require fire alarm early warning, and then acquire images of the special scenes to form special scene reference images, and acquire fire images to be identified. Subsequently, a preset scale-invariant feature transformation algorithm is used to determine matching feature points between the fire images to be identified and the special scene reference images. The Hausdorff distance between the fire images to be identified and the special scene reference images is determined by matching feature points. Finally, the similarity between the fire images to be identified and the special scene reference images is determined by comparing the Hausdorff distance with a preset threshold. The magnitude of the similarity determines whether the actual scene corresponding to the image to be identified is a special scene. When the Hausdorff distance is less than the preset threshold, it indicates that the similarity between the fire images to be identified and the special scene reference images is the greatest, meaning that the actual application scene corresponding to the fire images to be identified may be a non-fire scene such as hot work or equipment maintenance. At this point, a shielding procedure is initiated to prevent the system from receiving alarm information for that area. Attached Figure Description

[0043] Figure 1 This is a flowchart of an embodiment of the special scene early warning and shielding method provided by the present invention;

[0044] Figure 2 This is a flowchart of an embodiment of step S102 in the special scene early warning and shielding method provided by the present invention;

[0045] Figure 3 This is a flowchart of an embodiment of step S201 in the special scene early warning and shielding method provided by the present invention;

[0046] Figure 4 This is a flowchart of an embodiment of step S202 in the special scene early warning and shielding method provided by the present invention;

[0047] Figure 5This is a schematic diagram of an embodiment of the special scene early warning shielding device provided by the present invention;

[0048] Figure 6 This is a schematic diagram of the operating environment of an embodiment of the electronic device provided by the present invention. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0050] The present invention relates to a special scenario early warning and shielding method, device, electronic equipment and storage medium, which can be applied to various industries and places, such as large warehouses, office buildings, shops, hotels, streets, etc. Through the fire early warning system, the surrounding environment can be monitored in real time to keep potential hazards out. At present, fire detectors detect fires with different parameters, mainly including: temperature detectors, light detectors, smoke detectors, gas detectors and composite detectors. By connecting the fire alarm system and the public monitoring system together, fires can be detected and warned in a timely and accurate manner, which can minimize losses.

[0051] However, in special situations such as hot work operations, equipment maintenance, or fire drills, fire warnings are not necessary. In these situations, excessively frequent fire warnings can lead to worker fatigue, reduced vigilance, and hinder the implementation of fire warning systems. Therefore, there is a need to provide a special scenario warning shielding method, device, electronic device, and storage medium to solve the aforementioned problems. The method, device, equipment, or computer-readable storage medium involved in this invention can be integrated with the aforementioned system or operate relatively independently.

[0052] Figure 1 This is a flowchart of a special scenario early warning and shielding method provided in an embodiment of the present invention. Please refer to it. Figure 1 Special scenario warning and shielding methods include:

[0053] S101. Obtain the fire image to be identified and the reference image for special scenes;

[0054] S102. Using a preset scale-invariant feature transformation algorithm, determine the matching feature points between the fire image to be identified and the special scene reference image, and determine the Hausdorff distance between the fire image to be identified and the special scene reference image based on the matching feature points.

[0055] S103. Determine the relationship between the Hausdorf distance and the preset threshold.

[0056] S104. If the Hausdorf distance is less than the preset threshold, the fire image to be identified is determined to be a special scene image, and the fire warning shielding procedure is activated.

[0057] In this embodiment, special scenarios that do not require fire alarm warnings are first identified, and images of these special scenarios are acquired to form special scenario reference images. A fire image to be identified is then obtained. A preset scale-invariant feature transform algorithm is then used to determine matching feature points between the fire image to be identified and the special scenario reference image. The Hausdorff distance between the two images is determined using these matching feature points. Finally, the similarity between the Hausdorff distance and a preset threshold is compared to determine whether the actual scenario corresponding to the image to be identified is a special scenario. When the Hausdorff distance is less than the preset threshold, it indicates that the similarity between the fire image to be identified and the special scenario reference image is the highest, meaning that the actual application scenario corresponding to the fire image to be identified may be a non-fire scenario such as hot work or equipment maintenance. In this case, a blocking procedure is initiated to prevent the system from receiving alarm information for that area.

[0058] In some embodiments, please refer to Figure 2 The step of using a preset scale-invariant feature transform algorithm to determine the matching feature points between the fire image to be identified and the special scene reference image includes:

[0059] S201. Using a preset Gaussian differential function, determine the feature points to be identified in the fire image to be identified, and the reference feature points in the special scene reference image, wherein the feature points to be identified and the reference feature points are matched pairwise.

[0060] S202. Determine the bidirectional Hausdorff distance between the feature point to be identified and the reference feature point.

[0061] In this embodiment, the SIFT algorithm (i.e., scale-invariant feature transform algorithm) is used to extract the feature points to be identified from the fire image to be identified and the reference feature points from the special scene reference image. The feature points to be identified are the feature points on the fire image to be identified that best represent the actual scene represented by the image. That is, the feature points to be identified can intuitively reflect the similarity between the fire image to be identified and the special scene reference image. The reference feature points are the feature points on the special scene reference image that best represent the actual scene represented by the image. The bidirectional Hausdorff distance between the feature points to be identified and the reference feature points is calculated. The Hausdorff distance reflects the similarity between the fire image to be identified and the special scene reference image, thereby determining the fire situation at the location of the fire to be identified, and thus guiding the operation of the fire alarm.

[0062] In some embodiments, please refer to Figure 3 The determination of the feature points to be identified in the fire image and the reference feature points in the special scene reference image based on the preset Gaussian differential function includes:

[0063] S301. Based on the preset Gaussian differential function, extract the feature points to be identified from the fire image to be identified, and the reference feature points from the special scene reference image.

[0064] S302. Determine the positions of the feature point to be identified and the reference feature point, as well as the direction of the feature to be identified and the direction of the reference feature;

[0065] S303. Construct a feature vector to be identified based on the position of the feature point to be identified and the direction of the feature to be identified;

[0066] S304. Based on the position and direction of the reference feature points, construct a reference feature vector;

[0067] S305. Based on the feature vector to be identified and the reference feature vector, determine the feature points to be identified and the reference feature points that match each other.

[0068] In this embodiment, extracting the feature points to be identified and the reference feature points is to search for image locations across all scale spaces, and to identify potential interest points with scale and rotation invariance using a preset Gaussian differential function. The preset Gaussian differential function can be expressed by the following formula: Where σ is a parameter related to size, x and y represent the coordinates of pixels in the image information, and m and n are parameters related to feature points. For example, m and n can be randomly set parameter values ​​that conform to the definition requirements of Gaussian differential function parameters.

[0069] It should be noted that at each candidate location, the position and scale of the feature point to be identified and the reference feature point are determined by a finely fitted model, and then one or more directions are assigned to each feature point location based on the local gradient direction of the image.

[0070] Furthermore, based on the position and orientation of the feature points, a feature vector to be identified and a reference feature vector are constructed respectively. Finally, by comparing the feature points in the feature vector to be identified and the reference feature vector, several pairwise matching feature points to be identified and reference feature points are found.

[0071] In some embodiments, please refer to Figure 4 The step of determining the bidirectional Hausdorff distance between the feature point to be identified and the reference feature point includes:

[0072] S401. Construct the identification set of the feature points to be identified and the reference set of the reference feature points;

[0073] S402. Traverse all feature points to be identified in the identification set, calculate the distance between the feature point to be identified and all feature points in the reference set, determine the corresponding first shortest distance, and construct the first target set of the plurality of first shortest distances;

[0074] S403. Traverse the reference feature points in the reference set, calculate the distance between the reference feature points and all feature points in the identification set, determine the corresponding second shortest distance, and construct the second target set of the multiple second shortest distances;

[0075] S404. Determine the first one-way Hausdorf distance based on the first target set, and determine the second one-way Hausdorf distance based on the second target set.

[0076] S405. Determine the larger of the first one-way Hausdorf distance and the second one-way Hausdorf distance as the two-way Hausdorf distance.

[0077] In this embodiment, the identification set and the reference set are constructed based on the pairwise matching feature points in the feature vector to be identified and the reference feature vector, respectively. Specifically, the feature points to be identified in the identification set are the points that can be matched with the reference feature points, and the reference feature points in the reference set are the points that can be matched with the feature points to be identified.

[0078] In a specific embodiment, let the identification set be A = {a1, a2, ..., an} and the reference set be B = {b1, b2, ..., bn}. Then, the process of determining the bidirectional Hausdorff distance is as follows:

[0079] First, take a point a1 in set A, calculate the distance from a1 to all points in set B, and keep the shortest distance d1;

[0080] Then, iterate through all points in set A to calculate d2, ..., dn;

[0081] Then compare all the distances {d1, d2, ..., dn} and select the longest distance dx, which is the one-way Hausdorff distance from A to B, denoted as h(A, B).

[0082] Then, following the steps above, calculate the one-way Hausdorff distance from B to A, denoted as h(B, A);

[0083] Finally, the longest distance between h(A, B) and h(B, A) is selected, which is the bidirectional Hausdorff distance between sets A and B.

[0084] In some embodiments, obtaining a reference image for a specific scene further includes:

[0085] Acquire raw images from multiple different scenarios, including hot work scenarios, fire drills, and regular facility maintenance.

[0086] The multiple original images are used to construct a special scene reference image set.

[0087] In this embodiment, for different special scenarios, including but not limited to hot work, equipment maintenance or fire drills, corresponding sample images need to be collected to form a special scenario reference image set in order to avoid omissions in the actual discrimination process.

[0088] In some embodiments, determining the difference between the fire image to be identified and the special scene reference image based on the scale-invariant feature transform algorithm further includes determining the difference between the fire image to be identified and each original image in the special scene reference image set.

[0089] In this embodiment, the fire image to be identified and the special scene are compared with each image in the reference image set for similarity until the most similar image is found or the comparison with all images is completed.

[0090] Based on the above-described special scenario warning and shielding method, this embodiment of the invention also provides a special scenario warning and shielding device 500. Please refer to [link / reference]. Figure 5 The special scenario early warning and shielding device 500 includes an acquisition module 510, a Hausdorf distance determination module 520, a judgment module 530, and a target module 540.

[0091] The acquisition module 510 is used to acquire images of the fire to be identified and a reference image set for special scenes;

[0092] The Hausdorff distance determination module 520 is used to determine the matching feature points between the fire image to be identified and the special scene reference image by using a preset scale-invariant feature transformation algorithm, and to determine the Hausdorff distance between the fire image to be identified and the special scene reference image based on the matching feature points.

[0093] The judgment module 530 is used to determine the relationship between the Hausdorf distance and the threshold.

[0094] If the Hausdorf distance is less than the threshold, the target module 540 determines that the fire image to be identified is a special scene image and initiates the fire early warning shielding procedure.

[0095] like Figure 6As shown, based on the above-mentioned special scenario warning and shielding method, the present invention also provides an electronic device, which can be a mobile terminal, desktop computer, laptop, handheld computer, server, or other computing device. The electronic device includes a processor 610, a memory 620, and a display 630. Figure 6 Only some components of the electronic device are shown; however, it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0096] In some embodiments, memory 620 may be an internal storage unit of the electronic device, such as a hard disk or memory. In other embodiments, memory 620 may be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc. Furthermore, memory 620 may include both internal and external storage units. Memory 620 is used to store application software and various types of data installed on the electronic device, such as program code installed on the electronic device. Memory 620 may also be used to temporarily store data that has been output or will be output. In one embodiment, memory 620 stores a special scene warning blocking program 640, which can be executed by processor 610 to implement the special scene warning blocking methods of the embodiments of this application.

[0097] In some embodiments, processor 610 may be a central processing unit (CPU), microprocessor or other data processing chip, used to run program code stored in memory 620 or process data, such as executing special scene warning shielding methods.

[0098] In some embodiments, display 630 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. Display 630 is used to display information about the warning shielding device in the special scenario and to display a visual user interface. Components 610-630 of the electronic device communicate with each other via a system bus.

[0099] Of course, those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.). The program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The storage medium can be a memory, magnetic disk, optical disk, etc.

[0100] The specific embodiments of the present invention described above do not constitute a limitation on the scope of protection of the present invention. Any other corresponding changes and modifications made in accordance with the technical concept of the present invention should be included within the scope of protection of the claims of the present invention.

Claims

1. A special scenario early warning and shielding method, characterized in that, include: Acquire images of the fire to be identified and reference images of special scenes; A preset scale-invariant feature transformation algorithm is used to determine the matching feature points between the fire image to be identified and the special scene reference image, and the Hausdorff distance between the fire image to be identified and the special scene reference image is determined based on the matching feature points; the special scene is a non-fire scene corresponding to the fire image to be identified. Determine the relationship between the Hausdorff distance and a preset threshold; If the Hausdorf distance is less than the preset threshold, the fire image to be identified is determined to be a special scene image, and the fire warning shielding program is activated.

2. The special scenario early warning and shielding method according to claim 1, characterized in that, The step of using a preset scale-invariant feature transform algorithm to determine matching feature points between the fire image to be identified and the special scene reference image includes: Using a preset Gaussian differential function, the feature points to be identified in the fire image to be identified, and the reference feature points in the special scene reference image are determined, wherein the feature points to be identified and the reference feature points are matched pairwise.

3. The special scenario early warning and shielding method according to claim 2, characterized in that, The step of using a preset Gaussian differential function to determine the feature points to be identified in the fire image and the reference feature points in the special scene reference image includes: Based on a preset Gaussian differential function, the feature points to be identified in the fire image to be identified, as well as the reference feature points in the special scene reference image, are extracted. Determine the positions of the feature point to be identified and the reference feature point, as well as the direction of the feature to be identified and the direction of the reference feature; Based on the position of the feature point to be identified and the orientation of the feature to be identified, a feature vector to be identified is constructed; Based on the position and orientation of the reference feature points, a reference feature vector is constructed; Based on the feature vector to be identified and the reference feature vector, the feature points to be identified and the reference feature points that match each other are determined.

4. The special scenario early warning and shielding method according to claim 3, characterized in that, The Gaussian differential function is expressed by the following formula: , Where σ is a parameter related to size, x and y represent the coordinates of pixels in the image information, and m and n are parameters related to feature points.

5. The special scenario early warning and shielding method according to claim 2, characterized in that, The step of determining the Hausdorff distance between the fire image to be identified and the special scene reference image based on the matched feature points includes: Construct the identification set of the feature points to be identified and the reference set of the reference feature points; Traverse all feature points to be identified in the identification set, calculate the distance between the feature point to be identified and all feature points in the reference set, determine the corresponding first shortest distance, and construct a first target set of multiple first shortest distances; Traverse the reference feature points in the reference set, calculate the distance between the reference feature points and all feature points in the identification set, determine the corresponding second shortest distance, and construct a second target set with multiple second shortest distances; Based on the first target set, determine the first one-way Hausdorff distance; based on the second target set, determine the second one-way Hausdorff distance. The larger of the first one-way Hausdorff distance and the second one-way Hausdorff distance is determined to be the two-way Hausdorff distance.

6. The special scenario early warning and shielding method according to claim 1, characterized in that, The process of obtaining a reference image for a specific scene also includes: Acquire raw images from multiple different scenarios, including hot work scenarios, fire drills, and regular facility maintenance. The original images are constructed into a special scene reference image set.

7. A special scenario early warning and shielding device, characterized in that, include: The acquisition module is used to acquire images of fires to be identified and reference image sets for special scenes; The Hausdorff distance determination module is used to determine the matching feature points between the fire image to be identified and the special scene reference image using a preset scale-invariant feature transformation algorithm, and to determine the Hausdorff distance between the fire image to be identified and the special scene reference image based on the matching feature points; the special scene is a non-fire scene corresponding to the fire image to be identified. The judgment module is used to determine the relationship between the Hausdorf distance and the threshold. If the Hausdorff distance is less than the threshold, the target module determines that the fire image to be identified is a special scene image and initiates the fire early warning shielding procedure.

8. An electronic device, characterized in that, include: Processor and memory; The memory stores a computer-readable program that is executed by the processor; When the processor executes the computer-readable program, it implements the steps in the special scenario early warning and shielding method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores one or more programs, which are executed by one or more processors to implement the steps in the special scenario early warning and shielding method as described in any one of claims 1-6.

Images