A collaborative acquisition and analysis method and device for the characteristics of melted marks at a fire scene

Abstract

The present invention relates to the technical field of image recognition, and particularly to a method and device for collaborative acquisition and analysis of the characteristics of molten marks at a fire scene. The method includes the following steps: performing image acquisition on the surface of the preprocessed molten mark to obtain a molten mark surface image containing the appearance characteristics and metallographic structure characteristics of the molten mark; extracting the outer contour line, transition boundary line, and grain boundary contour line from the molten mark surface image; assigning values to the lengths and included areas of the outer contour line, transition boundary line, and grain boundary contour line, and calculating to obtain the bead characteristics parameters and grain boundary characteristics parameters; based on the bead characteristics parameters and grain boundary characteristics parameters, determining the type of molten mark corresponding to the molten mark surface image. The present invention uses the molten mark surface image containing the appearance characteristics and metallographic structure characteristics of the molten mark as an analysis sample, and determines the type of molten mark from different angles based on the extracted various characteristic parameters, realizing the collaboration and cross-verification between different determination methods, and further ensuring the reliability of the qualitative result of the molten mark.

Description

Technical Field

[0001] The present invention relates to the technical field of image recognition, and particularly to a method and device for collaborative acquisition and analysis of molten trace characteristics at a fire scene. Background Art

[0002] Disclosing the information of this background art section is only intended to enhance the overall understanding of the present invention, and it is not necessarily regarded as an admission or any form of implication that this information constitutes the prior art already known to those of ordinary skill in the art.

[0003] In actual fire investigation work, wire molten traces are the most numerous and typical types of physical evidence of molten traces at the fire scene. Molten traces can be divided into three melting properties according to their formation reasons: primary short - circuit molten traces, secondary short - circuit molten traces, and fire - burned molten traces. Among them, primary short - circuit molten traces are melting traces formed by electrical faults such as short - circuits of conductors under normal environmental conditions, secondary short - circuit molten traces are melting traces formed by electrical faults such as short - circuits of conductors under fire environmental conditions, and fire - burned molten traces are melting traces formed by the heating of conductors during a fire. Therefore, accurately determining the melting property of the conductor molten traces at the fire scene is the key to scientifically and accurately analyzing and determining the cause of the fire.

[0004] Currently, the qualitative determination of molten traces is carried out according to GB / T16840.1 - 2008 "Technical Identification Methods for Physical Evidence of Electrical Fire Traces - Part 1: Macroscopic Method" and GB / T16840.4 - 2021 "Technical Identification Methods for Physical Evidence of Electrical Fire Traces - Part 4: Metallographic Analysis Method". The former conducts qualitative determination by comparing the ratio of the molten bead diameter to the wire diameter, and the latter uses the metallographic tissue characteristics including grain morphology as the judgment basis. However, the molten trace qualitative determination method based on the above standards still has the following problems:

[0005] (1) There are ambiguous areas in the definition of key parameters. For core parameters such as molten bead diameter, wire diameter, and grain morphology, the specific acquisition methods and reasonable value ranges are not clearly stated or there are overlaps, which are prone to disputes in understanding and use, and different investigators may draw different conclusions for the same sample;

[0006] (2) When analyzing molten traces using the metallographic method, it is necessary to collect metallographic images of the cross - section of the molten trace. Only after the operator accurately prepares the sample and obtains a metallographic image available for analysis can the analysis be carried out according to the standard. When the collected metallographic image does not meet the requirements of the analysis, the subsequent conclusions are inaccurate.

[0007] Although the automatic recognition method is used in the prior art to avoid the errors caused by the subjective judgment of investigators, it still cannot avoid the defects brought by the macroscopic method and the metallographic method: based on the macroscopic method (such as 202011321909.9), only appearance features are used for analysis, and the appearance features are poorly defined and the judgment criteria are based on artificial definitions; based on the metallographic method (such as 202310315581.7), it is necessary to collect metallographic images of the melt mark cross-section for analysis, and the analysis results are still subject to the strict requirements of the metallographic images. Moreover, due to the different image standards and positions collected by different analysis methods, it is impossible to comprehensively consider multi-dimensional parameters such as the melt bead diameter, wire diameter, and grain morphology in the same image, and it is difficult to achieve cross-verification between different methods, which is not conducive to the high-precision identification of melt marks. Summary of the Invention

[0008] To solve the deficiencies of the prior art, the present invention provides a method and device for collaborative acquisition and analysis of melt mark characteristics at a fire scene. By collecting and preprocessing the surface image of the melt mark that simultaneously reveals the appearance characteristics of the melt mark and the metallographic structure characteristics such as the surface grains of the melt mark, the melt bead characteristic parameters and the grain boundary characteristic parameters are extracted and calculated, and the macroscopic method and the metallographic analysis method are used collaboratively to analyze the type of melt mark, reducing the difficulty of image acquisition while improving the analysis accuracy.

[0009] To achieve the above object, the present invention is realized by the following technical solutions:

[0010] In the first aspect, the present invention provides a method for collaborative acquisition and analysis of melt mark characteristics at a fire scene, including the following steps:

[0011] Collect images of the surface of the preprocessed melt mark to obtain a surface image of the melt mark containing the appearance characteristics and metallographic structure characteristics of the melt mark;

[0012] Extract the outer contour line, transition boundary line, and grain boundary contour line in the surface image of the melt mark;

[0013] Assign values to the lengths and included areas of the outer contour line, transition boundary line, and grain boundary contour line, and calculate the melt bead characteristic parameters and grain boundary characteristic parameters;

[0014] Based on the melt bead characteristic parameters and grain boundary characteristic parameters, determine the type of melt mark corresponding to the surface image of the melt mark.

[0015] Further, the preprocessing includes using a surface corrosion agent to treat the surface of the melt mark to remove the combustion residues on the surface, so that the appearance characteristics of the melt mark and the metallographic structure characteristics are revealed on the surface of the melt mark.

[0016] Further, a collaborative acquisition and classification model for melt mark characteristics is established based on the MobileViT neural network, and the outer contour line, transition boundary line, and grain boundary contour line in the surface image of the melt mark are extracted.

[0017] Further, before extracting the outer contour line, transition boundary line, and grain boundary contour line from the surface image of the fusion mark, the method further includes training and iterating the fusion mark feature collaborative acquisition and classification model using a set of fusion mark sample images marked with the outer contour line, transition boundary line, and grain boundary contour line of the fusion mark.

[0018] Still further, after extracting the outer contour line, transition boundary line, and grain boundary contour line from the surface image of the fusion mark, the method further includes adding the extracted surface image of the fusion mark to the set of fusion mark sample images.

[0019] Further, the assignment includes scale marking, pixel counting, chain code, or model calculation.

[0020] Further, the fusion bead feature parameters include the projected perimeter of the fusion bead, the projected area of the fusion bead, and the diameter of the fusion bead, and the grain boundary feature parameters include the projected area of the grain boundary, the projected perimeter of the grain boundary, and the aspect ratio of the grain boundary.

[0021] Still further, based on the fusion bead feature parameters and the grain boundary feature parameters, determining the type of fusion mark corresponding to the surface image of the fusion mark specifically includes:

[0022] Calculating the diameter of the fusion bead from the projected perimeter and projected area of the fusion bead, and obtaining the first determination result of the fusion mark type according to the corresponding relationship between the ratio of the fusion bead diameter to the wire diameter and the fusion mark type;

[0023] Judging the grain type according to the projected area of the grain boundary, the projected perimeter of the grain boundary, and the aspect ratio of the grain boundary, and obtaining the second determination result of the fusion mark type according to the corresponding relationship between the grain type and the fusion mark type;

[0024] Calculating the proportion of grains with different projected areas of the grain boundary, and obtaining the third determination result of the fusion mark type according to the distribution of the projected areas of the grain boundary of different fusion mark types;

[0025] Determining the fusion mark type as the repeated result among the first determination result, the second determination result, and the third determination result of the fusion mark type.

[0026] Even further, the corresponding relationship between the ratio of the fusion bead diameter to the wire diameter and the fusion mark type, the corresponding relationship between the grain type and the fusion mark type, and the distribution of the projected areas of the grain boundary of different fusion mark types are obtained by analyzing using a set of fusion mark samples marked with the ratio of the fusion bead diameter to the wire diameter, the grain type, the distribution of the projected areas of the grain boundary, and the fusion mark type.

[0027] Further, after determining the type of fusion mark corresponding to the surface image of the fusion mark, the method further includes:

[0028] Send the type of the molten mark corresponding to the molten mark surface image to the mobile terminal of the fire scene staff;

[0029] Or, display the type of the molten mark corresponding to the molten mark surface image in text form.

[0030] In a second aspect, the present invention provides a collaborative acquisition and analysis device for molten mark characteristics at a fire scene, and the device includes:

[0031] An acquisition module, configured to perform image acquisition on the preprocessed molten mark surface to obtain a molten mark surface image containing the appearance characteristics and metallographic structure characteristics of the molten mark;

[0032] An extraction module, configured to extract the outer contour line, the transition boundary line, and the grain boundary contour line in the molten mark surface image;

[0033] A calculation module, configured to assign values to the lengths and the included areas of the outer contour line, the transition boundary line, and the grain boundary contour line, and calculate to obtain the molten bead characteristic parameters and the grain boundary characteristic parameters;

[0034] A determination module, based on the molten bead characteristic parameters and the grain boundary characteristic parameters, determines the type of the molten mark corresponding to the molten mark surface image.

[0035] The beneficial effects obtained by one or more of the above technical solutions of the present invention are as follows:

[0036] The collaborative acquisition and analysis method for molten mark characteristics at a fire scene of the present invention extracts multi-dimensional characteristics and calculates parameters for the molten mark surface image, no longer simply relying on macroscopic morphology characteristics or microscopic metallographic characteristics. Multi-dimensional parameters such as the molten bead diameter, wire diameter, and grain morphology can be obtained and comprehensively considered on the same molten mark surface image. Based on the extracted multiple characteristic parameters, the type of the molten mark is determined from different angles, realizing the collaboration and cross-validation between different determination methods, and further ensuring the reliability of the molten mark qualitative result.

[0037] The collaborative acquisition and analysis method for molten mark characteristics at a fire scene of the present invention uses the molten mark surface image containing the appearance characteristics and metallographic structure characteristics of the molten mark as an analysis sample, without the need to prepare a specific molten mark cross-section metallographic image like the traditional metallographic method, simplifies the sample preparation process, facilitates on-site sample preparation and acquisition, and improves the analysis efficiency.

[0038] The collaborative acquisition and analysis device for molten mark characteristics at a fire scene of the present invention can quickly and accurately perform collaborative acquisition and analysis of the characteristics of copper wire molten marks at the fire scene through the acquisition module, the extraction module, the calculation, and the determination module. The degree of integration is high, which is convenient for on-site use, reduces the time for molten mark identification, and reduces the difficulty of molten mark identification. Description of the Drawings

[0039] The accompanying drawings of the specification, which form a part of the present invention, are used to provide a further understanding of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention.

[0040] Figure 1 It is a flowchart of a method for collaborative acquisition and analysis of the characteristics of molten marks at the fire scene provided by an embodiment of the present invention;

[0041] Figure 2 It is a distribution diagram of the grain boundary projection area in an embodiment of the present invention;

[0042] Figure 3 It is a schematic internal structure diagram of a device for collaborative acquisition and analysis of the characteristics of molten marks at the fire scene provided by an embodiment of the present invention. Detailed implementation manners

[0043] To make the objectives, technical solutions, and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below in conjunction with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0044] In actual fire investigation work, the molten marks of copper wires are the most numerous and typical trace evidence. Accurately determining the molten marks of copper wires at the fire scene is the key to scientifically and accurately analyzing and determining the cause of the fire.

[0045] The series of standards of "Technical Appraisal Methods for Electrical Fire Trace Evidence" give the currently common methods for appraising molten marks in the laboratory, namely the macroscopic method, the metallographic analysis method, and the microscopic morphology analysis method. Among them, the macroscopic method is used to identify through the appearance characteristics of the molten marks, the metallographic analysis method is used to identify through the metallographic tissue characteristics of the cross-section of the molten marks, and the microscopic morphology analysis method is used to identify using the microscopic morphology of the cross-section of the molten marks.

[0046] In actual applications, the most widely used method for appraising molten marks in the physical evidence appraisal experiment is to comprehensively use the macroscopic method and the metallographic analysis method to appraise the melting properties of the molten marks. However, both of these methods have the defect of being subject to the subjective judgment of fire investigators, and misjudgment or missed judgment often occur. In the prior art, the automatic recognition methods of molten marks based on image recognition are mostly single-feature recognition methods established based on the macroscopic method or the metallographic analysis method. Although such methods reduce the influence of the subjective judgment of fire investigators, they are still subject to the singularity and strict requirements of the images, and cannot realize the collaborative analysis of multiple characteristic criteria.

[0047] Figure 1The figure is a flowchart of a collaborative acquisition and analysis method for the characteristics of molten marks at a fire scene provided by an embodiment of the present invention. As Figure 1 shown, the collaborative acquisition and analysis method for the characteristics of molten marks at a fire scene provided by an embodiment of the present invention includes the following steps:

[0048] Step 101: Perform image acquisition on the surface of the preprocessed molten mark to obtain a molten mark surface image containing the appearance characteristics and metallographic structure characteristics of the molten mark;

[0049] Step 102: Extract the outer contour line, transition boundary line, and grain boundary contour line from the molten mark surface image;

[0050] Step 103: Assign values to the lengths and enclosed areas of the outer contour line, transition boundary line, and grain boundary contour line, and calculate the molten bead characteristic parameters and grain boundary characteristic parameters;

[0051] Step 104: Determine the type of molten mark corresponding to the molten mark surface image based on the molten bead characteristic parameters and grain boundary characteristic parameters.

[0052] Research has confirmed that the grain boundary characteristics on the surface of copper wire molten marks in building fires are consistent with the grain boundary characteristics of the molten mark cross-section. Therefore, in the embodiments of the present application, the surface of the molten mark can be preprocessed to simultaneously reveal the appearance characteristics and metallographic structure characteristics of the molten mark, and the molten mark surface image can be collected as the analysis object. Further extract the outer contour line, transition boundary line, and grain boundary contour line, assign values to the lengths and enclosed areas of the above lines, and calculate the molten bead characteristic parameters and grain boundary characteristic parameters. Macroscopic method determination is carried out through the molten bead characteristic parameters, and metallographic method determination is carried out through the grain boundary characteristic parameters. The determination results of the two methods are comprehensively combined to determine the type of molten mark corresponding to the molten mark surface image.

[0053] In one or more embodiments of the present invention, the preprocessing includes treating the surface of the molten mark with a surface etching agent to remove the combustion residues on the surface, so that the appearance characteristics and metallographic structure characteristics of the molten mark are revealed on the surface of the molten mark.

[0054] The processing method of the prior art is to clean with alcohol, which can only remove the combustion residues on the surface of the molten mark, and only one characteristic, the appearance characteristic, can be revealed after processing. When performing intelligent analysis through images, there is only the result of the macroscopic method, and the accuracy is not high. In the implementation of the present invention, the surface is treated with a surface etching agent, which can not only remove the combustion residues on the surface, but also reveal the appearance characteristics and metallographic structure characteristics of the molten mark. Moreover, when analyzing the image, values can be assigned to the characteristic parameters, and the determination results of both the macroscopic method and the metallographic method can be obtained through image analysis, which can improve the determination accuracy.

[0055] In one or more embodiments of the present invention, a collaborative acquisition and classification model for weld mark features is established based on the MobileViT neural network, and the outer contour line, transition boundary line, and grain boundary contour line in the weld mark surface image are extracted.

[0056] The collaborative acquisition and classification model for weld mark features is mainly composed of a convolutional layer (Conv), MobileNetV2 (MV2), a mobile vision block (MobileViT Block), a global pooling layer (Global Pooling), and a fully connected layer (Linear Layer).

[0057] The weld mark image enters the convolutional layer (Conv) for initial feature extraction. In this convolutional layer (Conv), the weld mark image is transformed into an initial weld mark feature map, and the size changes from 256×256 to 128×128.

[0058] The initial weld mark feature map first enters the MobileNetV2 layer for image feature information extraction, and the image size changes from 128×128 to 64×64 to improve the feature learning ability of the model.

[0059] The initial weld mark feature map then enters the mobile vision block (MobileViT block) to extract various qualitative features of the image in a collaborative manner. The initial weld mark feature map input to this mobile vision block (MobileViT block) undergoes local feature modeling through a 3×3 convolutional layer (Conv) and a 1×1 convolutional layer (Conv); subsequently, the feature map is divided into 2×2 pixel windows in each channel, and the pixels at relative positions in each window are unfolded and then processed by a Transformer; in the Transformer layer, different positions in each channel are weighted through a series of attention mechanisms to emphasize important feature regions and suppress unimportant regions; the feature map processed by the Transformer is adjusted to 256×256 through a 1×1 convolutional block (Conv) and undergoes feature fusion through a 3×3 convolutional layer (Conv) to capture local and global information of qualitative features and form a final weld mark feature map.

[0060] The final molten mark feature map is then deformed from 256×256 to 8×8 through a 1×1 convolutional layer (Conv), and then enters the global pooling layer, changing from 8×8 to 1×C (C is the number of channels). Calculate the average value of the feature information contained in each channel of the final molten mark feature map, convert the high-dimensional final molten mark feature map into a feature vector of a fixed length, and then input this feature vector into the fully connected layer (Linear Layer), changing from 1×C to 1×N (N = 2, for 2-class classification). The transformed 1×N feature vector is converted into classification probabilities through the activation function, representing the possibility that the final molten mark feature map belongs to different classes. For example, the output result of the identification of the fire-induced molten mark is (0.9, 0.1), indicating that the identification probability of the fire-induced molten mark is 90%.

[0061] In one or more embodiments of the present invention, before extracting the outer contour line, transition dividing line, and grain boundary contour line from the molten mark surface image, the method further includes training and iterating the molten mark feature collaborative acquisition and classification model using a molten mark sample image set annotated with the outer contour line, transition dividing line, and grain boundary contour line of the molten mark.

[0062] The molten mark sample image data and the corresponding annotation data are sent into the molten mark feature collaborative acquisition and classification model in batches. In each training iteration, the network performs forward propagation based on the input data to obtain the prediction result, calculates the loss value through the loss function, and then updates the network parameters through backpropagation using the optimizer according to the loss value. After multiple rounds of training until the network converges, that is, the loss value no longer decreases significantly or reaches the pre-set training stop condition. By using the molten mark sample image set to train and iterate the molten mark feature collaborative acquisition and classification model, the segmentation efficiency and accuracy of the molten mark feature collaborative acquisition and classification model are improved. It should be noted that the method for obtaining the molten mark sample image set in the embodiments of the present application can be obtained on the Internet or downloaded from a specific fire protection website, and the embodiments of the present application do not limit this.

[0063] In one or more embodiments of the present invention, after extracting the outer contour line, transition dividing line, and grain boundary contour line from the molten mark surface image, the method further includes adding the extracted molten mark surface image to the molten mark sample image set.

[0064] Adding the molten mark surface image from which the outer contour line, transition dividing line, and grain boundary contour line have been extracted to the molten mark sample image set, and performing repeated training and iteration on the semantic segmentation algorithm to further improve the segmentation efficiency and accuracy of the semantic segmentation algorithm.

[0065] In one or more embodiments of the present invention, the assignment includes scale annotation, pixel counting, chain code, or model calculation.

[0066] In one or more embodiments of the present invention, the bead feature parameters include the bead projection perimeter, the bead projection area, and the bead diameter, and the grain boundary feature parameters include the grain boundary projection area, the grain boundary projection perimeter, and the grain boundary aspect ratio.

[0067] In one or more embodiments of the present invention, it is characterized in that, based on the bead feature parameters and the grain boundary feature parameters, the type of the fusion mark corresponding to the fusion mark surface image is determined, specifically including:

[0068] The bead diameter is calculated through the bead projection perimeter and the bead projection area, and the first determination result of the fusion mark type is obtained according to the corresponding relationship between the ratio of the bead diameter to the wire diameter and the fusion mark type;

[0069] The grain types are judged according to the grain boundary projection area, the grain boundary projection perimeter, and the grain boundary aspect ratio, and the second determination result of the fusion mark type is obtained according to the corresponding relationship between the grain types and the fusion mark type;

[0070] The proportion of grains with different grain boundary projection areas is calculated, and the third determination result of the fusion mark type is obtained according to the grain boundary projection area distribution of different fusion mark types;

[0071] The fusion mark type is determined as the repeated result among the first determination result, the second determination result, and the third determination result of the fusion mark type.

[0072] In the existing macroscopic method, the type of the fusion mark is determined by the ratio of the bead diameter to the wire diameter. In the existing metallographic method, the type of the fusion mark is determined by the grain area and type. There is an overlap in the ratio ranges of different types in the former, and there are also repetitions in the grain types in the latter, and the description of the grain boundary area is the vague attributives of "fine" and "coarse". Therefore, it is difficult to accurately obtain the type of the fusion mark based on a single determination result. The macroscopic method is used for determination through the bead feature parameters, the metallographic method is used for determination through the grain boundary feature parameters, the grain type and the grain boundary area are split, and the three determination results of the two methods are comprehensively determined, which is beneficial to improving the accuracy of the fusion mark type.

[0073] In one or more embodiments of the present invention, the corresponding relationship between the ratio of the bead diameter to the wire diameter and the fusion mark type, the corresponding relationship between the grain types and the fusion mark type, and the grain boundary projection area distribution of different fusion mark types are obtained through analysis using a fusion mark sample set that marks the ratio of the bead diameter to the wire diameter, the grain types, the grain boundary projection area distribution, and the fusion mark type.

[0074] The above corresponding relationships and the distribution of the grain boundary projection area can be obtained through data grouping, statistics, and correlation analysis, or can be obtained through model construction and training. Accurately obtaining the corresponding relationship between the ratio of the bead diameter to the wire diameter and the type of fusion mark, the corresponding relationship between the type of crystal grain and the type of fusion mark, and the distribution of the grain boundary projection area of different types of fusion marks can avoid the ambiguity and overlap of the judgment basis in the existing standards and improve the feasibility of the judgment result of the type of fusion mark. The distribution of the grain boundary projection area obtained in an embodiment of the present invention is as Figure 2 shown. Through the distribution of the grain boundary projection area, it can be intuitively obtained that the primary short circuit is mainly composed of fine cellular crystals, the secondary short circuit is composed of thick columnar crystals, and the fire fusion mark is composed of thick equiaxed crystals, and specific numerical values of fine and thick are given. Such numerical values are the key parameters for improving the classification accuracy.

[0075] In one or more embodiments of the present invention, after determining the type of fusion mark corresponding to the surface image of the fusion mark, the method further includes:

[0076] Sending the type of fusion mark corresponding to the surface image of the fusion mark to the mobile terminal corresponding to the fire scene staff;

[0077] Or, displaying the type of fusion mark corresponding to the surface image of the fusion mark in text form.

[0078] Compared with the existing fusion mark discrimination methods, the method for collaborative acquisition and analysis of fusion mark characteristics at the fire scene provided in the embodiments of the present invention has the following advantages:

[0079] By preprocessing to obtain the surface image of the fusion mark containing the appearance characteristics and metallographic structure characteristics of the fusion mark as an analysis sample, sample preparation, acquisition, and analysis can be carried out on-site, effectively improving the efficiency of acquisition and analysis of the type of fusion mark, shortening the time and steps required for analysis, and reducing the operation burden of on-site personnel;

[0080] Multi-dimensional feature extraction and parameter calculation are performed on the surface image of the fusion mark, no longer simply relying on macroscopic morphology features or microscopic metallographic features, and the parameter values required for judgment are refined, realizing the collaboration and cross-validation between different judgment methods, and further ensuring the reliability of the fusion mark qualitative result.

[0081] The above is the method embodiment provided in the embodiments of the present application. Based on the same inventive concept, the embodiments of the present application also provide a device for collaborative acquisition and analysis of fusion mark characteristics at the fire scene.

[0082] Figure 3 It is a schematic internal structure diagram of a device for collaborative acquisition and analysis of fusion mark characteristics at the fire scene provided in an embodiment of the present invention. As Figure 3 shown, the device for collaborative acquisition and analysis of fusion mark characteristics at the fire scene provided in an embodiment of the present invention includes:

[0083] The acquisition module 201 is used to acquire images of the surface of the melted mark after preprocessing, and obtain the surface images of the melted mark containing the appearance features and metallographic structure features of the melted mark;

[0084] The extraction module 202 is used to extract the outer contour line, the transition division line and the grain boundary contour line in the surface image of the melted mark;

[0085] The calculation module 203 is used to assign values to the lengths and included areas of the outer contour line, the transition division line and the grain boundary contour line, and calculate the bead feature parameters and the grain boundary feature parameters;

[0086] The determination module 204 is used to determine the type of the melted mark corresponding to the surface image of the melted mark based on the bead feature parameters and the grain boundary feature parameters.

[0087] The device for collaborative acquisition and analysis of the characteristics of the melted mark at the fire scene provided by the embodiment of the present invention can quickly and accurately perform collaborative acquisition and analysis of the characteristics of the copper wire melted mark at the fire scene, has a high degree of integration and is convenient to use on site, and reduces the time and difficulty of melted mark identification.

[0088] The above are only the preferred embodiments of the present invention, and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for collaborative collection and analysis of melt mark characteristics at a fire scene, characterized in that: The following steps are involved: Capturing images of the pre-treated melt mark surface to obtain a melt mark surface image containing melt mark appearance features and metallographic structure features; Extracting outer contour lines, transition zone boundary lines and grain boundary contour lines in the melt mark surface image; Assigning values ​​to the lengths and included areas of the outer contour line, transition zone boundary line and grain boundary contour line, and calculating and obtaining the characteristic parameters of the molten bead and the characteristic parameters of the grain boundary; Based on the melt bead characteristic parameters and the grain boundary characteristic parameters, the melt mark type corresponding to the melt mark surface image is determined.

2. The method for collaborative collection and analysis of melt mark characteristics at a fire scene according to claim 1, characterized in that: The pretreatment includes using a surface corrosive agent to treat the surface of the melt mark, removing combustion residues on the surface, and making the melt mark surface show the melt mark appearance characteristics and metallographic structure characteristics.

3. The method for collaborative collection and analysis of melt mark characteristics at a fire scene according to claim 1, characterized in that: Based on the MobileViT neural network, a collaborative collection and classification model of melt mark features is established to extract the outer contour line, transition zone boundary line and grain boundary contour line in the melt mark surface image; Before extracting the outer contour line, transition zone boundary line and grain boundary contour line in the melt mark surface image, the method also includes using a melt mark sample image set marked with the melt mark outer contour line, transition zone boundary line and grain boundary contour line to iteratively train the melt mark feature collaborative collection and classification model.

4. The method for collaborative collection and analysis of melt mark characteristics at a fire scene according to claim 3, characterized in that: After extracting the outer contour line, transition zone boundary line and grain boundary contour line in the melt mark surface image, the method further includes adding the extracted melt mark surface image to the melt mark sample image set.

5. The method for collaborative collection and analysis of melt mark characteristics at a fire scene according to claim 1, characterized in that: The assignment includes scale marking, pixel counting, chain code or model calculation.

6. The method for collaborative collection and analysis of melt mark characteristics at a fire scene according to claim 1, characterized in that: The characteristic parameters of the molten bead include the projected circumference of the molten bead, the projected area of ​​the molten bead and the diameter of the molten bead, and the characteristic parameters of the grain boundary include the projected area of ​​the grain boundary, the projected circumference of the grain boundary and the axial ratio of the grain boundary.

7. The method for collaborative collection and analysis of melt mark characteristics at a fire scene according to claim 6, characterized in that: Determining the type of fusion mark corresponding to the fusion mark surface image based on the fusion bead characteristic parameters and the grain boundary characteristic parameters, specifically includes: The diameter of the molten bead is calculated by the projection perimeter and the projection area of ​​the molten bead, and the first molten mark type determination result is obtained according to the corresponding relationship between the ratio of the molten bead diameter to the wire diameter and the molten mark type; The type of grain is determined according to the grain boundary projection area, the grain boundary projection perimeter and the grain boundary axis ratio, and the second melt mark type determination result is obtained according to the corresponding relationship between the grain type and the melt mark type; The proportion of grains with different grain boundary projection areas is calculated, and the third melt mark type determination result is obtained according to the distribution of grain boundary projection areas of different melt mark types; The determination of the melt mark type is a repeated result among the first melt mark type determination result, the second melt mark type determination result and the third melt mark type determination result.

8. The method for collaborative collection and analysis of melt mark characteristics at a fire scene according to claim 7, characterized in that: The correspondence between the ratio of the molten bead diameter to the wire diameter and the melt mark type, the correspondence between the grain type and the melt mark type, and the grain boundary projection area distribution of different melt mark types are obtained by analyzing the melt mark sample set that is labeled with the ratio of the molten bead diameter to the wire diameter, the grain type, the grain boundary projection area distribution, and the melt mark type.

9. The method for collaborative collection and analysis of melt mark characteristics at a fire scene according to claim 1, characterized in that: After determining the type of the melt mark corresponding to the melt mark surface image, the method further includes: Sending the type of the melt mark corresponding to the melt mark surface image to the mobile terminal corresponding to the fire scene staff; Alternatively, the type of melt mark corresponding to the melt mark surface image is displayed in text form.

10. A device for collaborative collection and analysis of melt mark characteristics at a fire scene, characterized in that: The device comprises: An acquisition module is used to acquire images of the pre-processed melt mark surface to obtain a melt mark surface image containing melt mark appearance features and metallographic structure features; An extraction module, used to extract the outer contour line, transition zone boundary line and grain boundary contour line in the melt mark surface image; A calculation module, used for assigning values ​​to the lengths and included areas of the outer contour line, the transition zone boundary line and the grain boundary contour line, and calculating and obtaining the characteristic parameters of the molten bead and the characteristic parameters of the grain boundary; A determination module determines the type of melt mark corresponding to the melt mark surface image based on the melt bead characteristic parameters and the grain boundary characteristic parameters.

Images