Fire disaster area measurement method, system and equipment based on thermal imaging fusion

Abstract

This application discloses a method, system, and device for measuring fire-affected area based on thermal imaging fusion. The method includes: in response to a received area to be measured, obtaining an original image group, a thermal imaging image group, and a current image group of the area to be measured; performing image preprocessing based on the original image group, thermal imaging image group, and current image group to obtain an original panoramic image, a thermal imaging panoramic image, and a current panoramic image corresponding to the area to be measured; obtaining a temperature feature vector corresponding to the thermal imaging panoramic image; obtaining disaster distribution data based on the original panoramic image, the current panoramic image, and the temperature feature vector, using a pre-set disaster assessment model; and obtaining the fire-affected area based on the disaster distribution data. This method at least solves the problem in existing technologies where measurements based solely on optical images have low accuracy, making it difficult to accurately assess the degree of disaster in many cases.

Description

Technical Field

[0001] This application relates to the field of disaster monitoring technology, and in particular to a method, system and equipment for measuring the fire-affected area based on thermal imaging fusion. Background Technology

[0002] Measuring the area affected by a fire is a crucial part of post-fire assessment, playing a vital role in developing rescue measures, post-disaster recovery, and reconstruction. With the development of remote sensing technology, optical imaging techniques are widely used for measuring and assessing the area affected by fires. However, despite the wide coverage provided by optical imaging, there are still limitations to measuring the area affected by fires using optical images, especially in terms of accuracy.

[0003] Optical imaging technology performs significantly differently under varying lighting and weather conditions. In cloudy, foggy, or nighttime conditions, the acquisition and quality of optical images can be affected, leading to a loss of visual information about the disaster area and consequently impacting measurement accuracy. For example, at night after a fire or when smoke is heavy, optical images may not effectively penetrate smoke or darkness, making accurate measurement of the affected area difficult. Furthermore, the presence of smoke and ash after a fire severely affects image clarity, reducing measurement reliability. Optical imaging technology also has limitations in assessing the severity of fires. The damage caused by a fire may not be simply reflected in area; the severity includes the depth of burns, structural damage to buildings, and changes in the surrounding environment, all of which optical images cannot fully capture. Therefore, relying solely on optical imaging for measuring the affected area cannot provide accurate post-disaster assessments, especially regarding the long-term impacts of fires on the ecological environment and infrastructure.

[0004] In summary, existing optical image measurement methods have certain limitations in terms of accuracy and application scope, especially in situations involving complex terrain, severe weather, or significant differences in the affected areas after a fire, making it difficult to accurately assess the area and severity of the fire. Therefore, it is necessary to seek more effective technical means that combine multiple data sources and measurement techniques to improve the accuracy and reliability of fire-affected area measurement. Summary of the Invention

[0005] This invention provides a method, system, and device for measuring the fire-affected area based on thermal imaging fusion, and provides a high-precision fire-affected area measurement scheme, which at least solves the problem that the measurement accuracy based solely on optical images in the prior art is low, and it is often difficult to accurately assess the degree of damage.

[0006] This application provides a method for measuring the fire-affected area based on thermal imaging fusion, including:

[0007] In response to the received area to be measured, the original image group, thermal imaging image group, and current image group of the area to be measured are obtained;

[0008] Image preprocessing is performed based on the original image group, the thermal imaging image group, and the current image group to obtain the original panoramic image, the thermal imaging panoramic image, and the current panoramic image corresponding to the area to be measured.

[0009] Based on the thermal imaging panoramic image, a temperature feature vector corresponding to the thermal imaging panoramic image is obtained. The temperature feature vector is configured to be obtained based on the temperature of each pixel in the thermal imaging panoramic image at different times.

[0010] Based on the original panoramic image, the current panoramic image, and the temperature feature vector, disaster distribution data is obtained according to a pre-set disaster assessment model.

[0011] Based on the disaster distribution data, the area affected by the fire was obtained.

[0012] Optionally, in response to the received region to be measured, obtaining the original image group, thermal imaging image group, and current image group of the region to be measured includes:

[0013] In response to the received coordinates of the area to be measured, an image containing at least a portion of the area to be measured is obtained from the image before the fire as the original image set;

[0014] In response to the received coordinates of the area to be measured, an infrared image of at least part of the area to be measured is obtained as a thermal imaging image group in the image of the fire process;

[0015] In response to the received coordinates of the area to be measured, an image containing at least a portion of the area to be measured is obtained as the current image group in the post-fire extinguishing image.

[0016] Optionally, the step of performing image preprocessing based on the original image group, the thermal imaging image group, and the current image group to obtain the original panoramic image, the thermal imaging panoramic image, and the current panoramic image corresponding to the area to be measured includes:

[0017] Based on the original image group, after image preprocessing based on the parameters of each image in the original image group, an original panoramic image matching the area to be measured is obtained;

[0018] Based on the thermal imaging image group, image preprocessing is performed on the parameters of each image in the thermal imaging image group to obtain a thermal imaging panoramic image that matches the original panoramic image. The thermal imaging panoramic image includes multiple images from different times.

[0019] Based on the current image group, image preprocessing is performed on the parameters of each image in the current image group to obtain a current panoramic image that matches the original panoramic image;

[0020] The image preprocessing includes at least one of image coordinate transformation, image cropping, and image stitching.

[0021] Optionally, obtaining the temperature feature vector corresponding to the thermal imaging panoramic image based on the thermal imaging panoramic image includes:

[0022] Based on the thermal imaging panoramic image, obtain the first temperature time series data corresponding to the thermal imaging panoramic image;

[0023] Based on the first temperature time series data, second temperature time series data with a temperature higher than a preset temperature threshold is obtained;

[0024] Based on the second temperature time series data, the temperature feature vector corresponding to the thermal imaging panoramic image is obtained.

[0025] Optionally, obtaining disaster distribution data based on the original panoramic image, the current panoramic image, and the temperature feature vector, according to a pre-set disaster assessment model, includes:

[0026] Based on the original panoramic image, target recognition is performed on the original image to obtain target data to be evaluated. The target data to be evaluated includes at least one target to be evaluated and target distribution data to be evaluated.

[0027] Based on the original panoramic image, the current panoramic image, the temperature feature vector, and the target data to be evaluated, disaster distribution data is obtained according to a pre-set disaster assessment model.

[0028] Optionally, obtaining disaster distribution data based on the original panoramic image, the current panoramic image, the temperature feature vector, and the target data to be evaluated, according to a pre-set disaster assessment model, includes:

[0029] Based on the original panoramic image and the current panoramic image, image feature vectors are obtained through image feature extraction using dual image coding.

[0030] Based on the target to be evaluated, the attribute feature code corresponding to the target to be evaluated is obtained, and the attribute feature code is configured to characterize the performance of the target to be evaluated at different temperatures.

[0031] Based on the distribution data of the target to be evaluated and the attribute feature codes corresponding to the at least one target to be evaluated, an attribute feature vector is obtained;

[0032] The image feature vector, the temperature feature vector, and the attribute feature vector are input into a pre-set disaster assessment model to obtain disaster situation distribution data corresponding to the original panoramic image or the current panoramic image.

[0033] Optionally, obtaining the fire-affected area based on the disaster distribution data includes:

[0034] Edge detection and / or isolated point detection are performed on the disaster distribution data;

[0035] When the disaster distribution data passes the detection, the fire-affected area is obtained based on the disaster distribution data;

[0036] When the disaster distribution data fails the detection, the disaster distribution data is processed to obtain the fire-affected area.

[0037] On the other hand, a fire-affected area measurement system based on thermal imaging fusion includes an image processing platform and a fire analysis platform;

[0038] The image processing platform is configured as follows:

[0039] In response to the received area to be measured, the original image group, thermal imaging image group, and current image group of the area to be measured are obtained;

[0040] Image preprocessing is performed based on the original image group, the thermal imaging image group, and the current image group to obtain the original panoramic image, the thermal imaging panoramic image, and the current panoramic image corresponding to the area to be measured.

[0041] The fire analysis platform is configured as follows:

[0042] Based on the thermal imaging panoramic image, a temperature feature vector corresponding to the thermal imaging panoramic image is obtained. The temperature feature vector is configured to be obtained based on the temperature of each pixel in the thermal imaging panoramic image at different times.

[0043] Based on the original panoramic image, the current panoramic image, and the temperature feature vector, disaster distribution data is obtained according to a pre-set disaster assessment model.

[0044] Based on the disaster distribution data, the area affected by the fire was obtained.

[0045] Optionally, obtaining disaster distribution data based on the original panoramic image, the current panoramic image, and the temperature feature vector, according to a pre-set disaster assessment model, includes:

[0046] Based on the original panoramic image and the current panoramic image, image feature vectors are obtained through image feature extraction using dual image coding.

[0047] Based on the original panoramic image, target recognition is performed on the original image to obtain target data to be evaluated. The target data to be evaluated includes at least one target to be evaluated and target distribution data to be evaluated.

[0048] Based on the target to be evaluated, the attribute feature code corresponding to the target to be evaluated is obtained, and the attribute feature code is configured to characterize the performance of the target to be evaluated at different temperatures.

[0049] Based on the distribution data of the target to be evaluated and the attribute feature codes corresponding to the at least one target to be evaluated, an attribute feature vector is obtained;

[0050] The image feature vector, the temperature feature vector, and the attribute feature vector are input into a pre-set disaster assessment model to obtain disaster situation distribution data corresponding to the original panoramic image or the current panoramic image.

[0051] In another aspect, embodiments of this application also provide an apparatus including a memory and a processor, wherein the memory stores a computer program and the processor executes the computer program to implement the above-described method.

[0052] In another aspect, embodiments of this application also provide a computer-readable storage medium storing a computer program, wherein a processor executes the computer program to implement the above-described method.

[0053] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0054] This invention discloses a method, system, and device for measuring fire-affected area based on thermal imaging fusion. The method includes: in response to a received area to be measured, obtaining an original image group, a thermal imaging image group, and a current image group of the area to be measured; performing image preprocessing based on the original image group, thermal imaging image group, and current image group to obtain an original panoramic image, a thermal imaging panoramic image, and a current panoramic image corresponding to the area to be measured; obtaining a temperature feature vector corresponding to the thermal imaging panoramic image, the temperature feature vector being configured to be obtained based on the temperature of each pixel in the thermal imaging panoramic image at different times; obtaining disaster distribution data based on the original panoramic image, the current panoramic image, and the temperature feature vector, according to a pre-set disaster assessment model; and obtaining the fire-affected area based on the disaster distribution data. This invention at least solves the problem that existing technologies using only optical images have low measurement accuracy, often making it difficult to accurately assess the degree of disaster. Attached Figure Description

[0055] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0056] Figure 1 This is a flowchart illustrating a method for measuring the fire-affected area based on thermal imaging fusion, as described in this application.

[0057] Figure 2 This is a schematic diagram of the structure of one of the devices in this application;

[0058] The diagram is labeled as follows: 101-Processor, 102-Communication bus, 103-Network interface, 104-User interface, 105-Memory.

[0059] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0060] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present application.

[0061] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0062] Example 1

[0063] like Figure 1 As shown, a method for measuring the fire-affected area based on thermal imaging fusion includes:

[0064] S1. In response to the received area to be measured, obtain the original image group, thermal imaging image group and current image group of the area to be measured.

[0065] In this embodiment, the main purpose of this step is to collect image data from the designated area to be measured. This area may be buildings, forests, industrial areas, etc. The original image set is typically captured by a high-resolution optical camera, providing visual information about the area to be measured; the thermal imaging image set is obtained through an infrared thermal imaging camera, capable of detecting heat sources within the area, such as the temperature distribution of a fire source; the current image set can be the latest scene images. The original and current images can be obtained from dynamic video or still images.

[0066] Specifically, after a forest fire occurs, the area to be measured may be the area where the fire has already occurred. Using drones, satellite equipment, or other monitoring devices, the system acquires a set of original images, a set of thermal images, and a set of current images of the area to be measured.

[0067] S2. Perform image preprocessing based on the original image group, thermal imaging image group, and current image group to obtain the original panoramic image, thermal imaging panoramic image, and current panoramic image corresponding to the area to be measured.

[0068] In this embodiment, the main purpose of this step is to align and optimize images from different sources and types, enabling them to be effectively fused into a unified panoramic image. The synthesized panoramic image can more clearly display the fire situation in the entire area to be measured. Specifically, the original panoramic image is composed of multiple original images stitched together, showing the overall visual situation of the area; the thermal imaging panoramic image is composed of thermal imaging images stitched together, used to analyze the temperature distribution in different areas, especially high-temperature areas, i.e., the areas where the fire started; and the current panoramic image is composed of current images stitched together, reflecting the consequences of the fire and helping to identify the affected area.

[0069] Specifically, before a forest fire, multiple images taken from different angles and time periods are stitched together to obtain a panoramic image covering the entire fire area, which serves as the original panoramic image. Thermal imaging images are also stitched together during this process to form a panoramic image with comprehensive thermal information, helping to analyze the fire intensity and temperature changes in different areas. After a forest fire, multiple images taken from different angles and time periods are stitched together to obtain a panoramic image covering the entire fire area, which serves as the current panoramic image.

[0070] S3. Based on the thermal imaging panoramic image, obtain the temperature feature vector corresponding to the thermal imaging panoramic image.

[0071] Specifically, the temperature feature vector is configured to be obtained based on the temperature of each pixel in the thermal imaging panoramic image at different times.

[0072] In this embodiment, the main purpose of this step is to extract temperature features from the thermal imaging image. Each pixel represents the temperature value at a specific location. Through time-series data analysis, temperature changes over different time periods in the thermal imaging image can be obtained, thereby deriving a temperature feature vector. These feature vectors not only reflect the temperature distribution in the fire area but also reveal the fire's spread trend and severity.

[0073] Specifically, a thermal imaging panoramic image is a set of images including time-series labels. The method to obtain the temperature feature vector corresponding to the thermal imaging panoramic image can be based on the highest temperature, average temperature, and duration of exceeding a preset temperature threshold for each pixel.

[0074] S4. Based on the original panoramic image, the current panoramic image, and the temperature feature vector, obtain disaster distribution data according to the pre-set disaster assessment model.

[0075] In this embodiment, the main purpose of this step is to use the previously processed image data and temperature features to assess the disaster situation through a disaster assessment model. The model combines visual information from the original image and the current image with temperature information from the thermal imaging image to determine the degree of fire damage in each area. This step typically involves machine learning or deep learning models, which learn the relationship between fire areas and the degree of damage through training data, thereby making an accurate assessment.

[0076] Specifically, in forest fire cases, disaster assessment models may determine the degree of damage to each area based on the temperature distribution in panoramic thermal imaging images, combined with the original and current images. For example, the model may identify "severely affected areas," "moderately affected areas," or "lightly affected areas."

[0077] S5. Based on the disaster distribution data, obtain the fire-affected area.

[0078] In this embodiment, the main purpose of this step is to calculate the specific affected area by combining disaster distribution data with GIS data. Different affected areas are assigned different area values ​​based on their degree of damage, thus yielding the total area affected by the fire. This step can use GIS technology to accurately calculate the area and further assess the resources and time required for post-disaster recovery through numerical models.

[0079] Specifically, in forest fire assessment, the model marks the specific areas of severely affected, moderately affected, and lightly affected areas based on the disaster distribution data. Then, GIS tools are used to calculate the area of ​​these areas, ultimately yielding the total area affected by the fire and the area of ​​areas with different disaster conditions.

[0080] By combining the optical images with the thermal images of the fire, the disaster situation can be identified more accurately. This solves the problem that the measurement accuracy based solely on optical images is low and it is often difficult to accurately assess the degree of damage in existing technologies.

[0081] Example 2

[0082] This embodiment, based on Embodiment 1, provides a method for measuring the fire-affected area using thermal imaging fusion, including:

[0083] S1. In response to the received area to be measured, obtain the original image group, thermal imaging image group and current image group of the area to be measured.

[0084] Optionally, in response to the received area to be measured, the original image group, thermal imaging image group, and current image group of the area to be measured are obtained, including:

[0085] In response to the received coordinates of the area to be measured, an image containing at least a portion of the area to be measured is obtained from the image before the fire as the original image set;

[0086] In response to the received coordinates of the area to be measured, an infrared image of at least part of the area to be measured is obtained as a thermal imaging image group in the image of the fire process;

[0087] In response to the received coordinates of the area to be measured, an image containing at least a portion of the area to be measured is obtained as the current image group in the post-fire extinguishing image.

[0088] Optionally, the coordinates of the area to be measured can be entered manually or obtained from data sent by satellite imagery or other monitoring equipment.

[0089] S2. Perform image preprocessing based on the original image group, thermal imaging image group, and current image group to obtain the original panoramic image, thermal imaging panoramic image, and current panoramic image corresponding to the area to be measured.

[0090] Optionally, image preprocessing is performed based on the original image group, the thermal imaging image group, and the current image group to obtain the original panoramic image, the thermal imaging panoramic image, and the current panoramic image corresponding to the area to be measured, including:

[0091] Based on the original image set, image preprocessing is performed on the parameters of each image in the original image set to obtain the original panoramic image that matches the area to be measured.

[0092] Based on the thermal imaging image group, image preprocessing is performed on the parameters of each image in the thermal imaging image group to obtain a thermal imaging panoramic image that matches the original panoramic image. The thermal imaging panoramic image includes multiple images from different times.

[0093] Based on the parameters of each image in the current image group, perform image preprocessing to obtain a current panoramic image that matches the original panoramic image.

[0094] Image preprocessing includes at least one of image coordinate transformation, image cropping, and image stitching.

[0095] Specifically, a common method for generating panoramic images by stitching together multiple images with overlapping areas is to find the transformation relationships between the images, such as translation, rotation, and scaling, and then combine the multiple images into a larger image. This mainly includes the following image processing methods: feature point extraction, feature matching, transformation matrix estimation, and image stitching.

[0096] S3. Based on the thermal imaging panoramic image, obtain the temperature feature vector corresponding to the thermal imaging panoramic image.

[0097] Specifically, the temperature feature vector is configured to be obtained based on the temperature of each pixel in the thermal imaging panoramic image at different times.

[0098] Optionally, based on the thermal imaging panoramic image, the temperature feature vector corresponding to the thermal imaging panoramic image is obtained, including:

[0099] Based on the thermal imaging panoramic image, obtain the first temperature time series data corresponding to the thermal imaging panoramic image;

[0100] Based on the first temperature time series data, obtain the second temperature time series data where the temperature is higher than the preset temperature threshold.

[0101] Based on the second temperature time series data, the temperature feature vector corresponding to the thermal imaging panoramic image is obtained.

[0102] Optionally, the preset temperature threshold can be between 50 degrees Celsius and 80 degrees Celsius. By setting the temperature threshold and filtering the temperature time series data, the impact of the temperature before ignition on the final prediction result can be reduced, and the amount of data processing can also be reduced.

[0103] S4. Based on the original panoramic image, the current panoramic image, and the temperature feature vector, obtain disaster distribution data according to the pre-set disaster assessment model.

[0104] Optionally, based on the original panoramic image, the current panoramic image, and the temperature feature vector, and using a pre-set disaster assessment model, disaster distribution data is obtained, including:

[0105] Based on the original panoramic image, target recognition is performed on the original image to obtain target data to be evaluated. The target data to be evaluated includes at least one target to be evaluated and target distribution data to be evaluated.

[0106] Based on the original panoramic image, the current panoramic image, temperature feature vector, and the data of the target to be assessed, the disaster distribution data is obtained according to the pre-set disaster assessment model.

[0107] Optionally, based on the original panoramic image, the current panoramic image, temperature feature vector, and the target data to be assessed, and using a pre-set disaster assessment model, disaster distribution data is obtained, including:

[0108] Based on the original panoramic image and the current panoramic image, image feature vectors are obtained through image feature extraction using dual image coding.

[0109] Based on the target to be evaluated, the attribute feature code corresponding to the target to be evaluated is obtained. The attribute feature code is configured to characterize the performance of the target to be evaluated at different temperatures.

[0110] Based on the distribution data of the target to be evaluated and the attribute feature encoding corresponding to at least one target to be evaluated, an attribute feature vector is obtained;

[0111] Input the image feature vector, temperature feature vector, and attribute feature vector into the pre-set disaster assessment model to obtain the disaster situation distribution data corresponding to the original panoramic image or the current panoramic image.

[0112] Specifically, based on the original panoramic image and the current panoramic image, image feature extraction is performed using dual-image coding to obtain image feature vectors. This includes using deep learning models such as convolutional neural networks (CNNs) and a trained dual-image coding model to extract feature vectors from the original panoramic image and the current panoramic image respectively. The dual-image coding method allows us to capture different features between the two images and simultaneously analyze the differences between the original image and the current image. By comparing the feature vectors of the two images, we can identify the areas of change in the post-disaster image compared to the pre-disaster image, such as collapsed trees.

[0113] Specifically, based on the target to be evaluated, the attribute feature code corresponding to the target to be evaluated is obtained. The attribute feature code is configured to characterize the performance of the target to be evaluated at different temperatures, including: determining the type of target to be evaluated, such as buildings, roads, different types of trees, etc., and collecting related attribute information for each target, such as ignition point, fire resistance index, etc.; and obtaining the attribute feature code based on the target's attribute information and a preset coding rule.

[0114] Based on the distribution data of the targets to be evaluated and the attribute feature codes corresponding to at least one target to be evaluated, an attribute feature vector is obtained, including: obtaining the attribute feature vector based on the attribute feature codes of all targets to be evaluated and the coordinates or distribution of each target to be evaluated on the original panoramic image.

[0115] Specifically, the data input for the disaster assessment model is configured to include image feature vectors, temperature feature vectors, and attribute feature vectors as input data.

[0116] Specifically, the input layer of the disaster assessment model includes image feature vectors, temperature feature vectors, and attribute feature vectors; the hidden layer of the disaster assessment model can be processed by multi-layer neural networks, such as fully connected layers; and the final output layer is the disaster distribution data, which describes the degree of disaster in different areas and targets.

[0117] S5. Based on the disaster distribution data, obtain the fire-affected area.

[0118] Optionally, based on the disaster distribution data, the fire-affected area can be obtained, including:

[0119] Perform edge detection and / or isolated point detection on the disaster distribution data;

[0120] When the disaster distribution data passes the detection, the fire-affected area is obtained based on the disaster distribution data;

[0121] When the disaster distribution data fails the test, the disaster distribution data is processed to obtain the fire-affected area.

[0122] Considering the continuity of fire spread, edge detection and / or isolated point detection are performed on the disaster distribution data. When the disaster distribution data fails the detection, the disaster distribution data is processed to obtain the fire-affected area.

[0123] By combining the optical images with the thermal images of the fire, the disaster situation can be identified more accurately. This solves the problem that the measurement accuracy based solely on optical images is low and it is often difficult to accurately assess the degree of damage in existing technologies.

[0124] Example 3

[0125] A fire-affected area measurement system based on thermal imaging fusion, comprising an image processing platform and a fire analysis platform;

[0126] The image processing platform is configured as follows:

[0127] In response to the received area to be measured, the original image group, thermal imaging image group, and current image group of the area to be measured are obtained;

[0128] Image preprocessing is performed based on the original image group, thermal imaging image group, and current image group to obtain the original panoramic image, thermal imaging panoramic image, and current panoramic image corresponding to the area to be measured.

[0129] The fire analysis platform is configured as follows:

[0130] Based on the thermal imaging panoramic image, the temperature feature vector corresponding to the thermal imaging panoramic image is obtained. The temperature feature vector is configured to be obtained based on the temperature of each pixel in the thermal imaging panoramic image at different times.

[0131] Based on the original panoramic image, the current panoramic image, and the temperature feature vector, and using a pre-set disaster assessment model, the distribution data of the disaster situation is obtained.

[0132] The area affected by the fire was obtained based on the distribution data of the disaster situation.

[0133] Optionally, in response to the received area to be measured, the original image group, thermal imaging image group, and current image group of the area to be measured are obtained, including:

[0134] In response to the received coordinates of the area to be measured, an image containing at least a portion of the area to be measured is obtained from the image before the fire as the original image set;

[0135] In response to the received coordinates of the area to be measured, an infrared image of at least part of the area to be measured is obtained as a thermal imaging image group in the image of the fire process;

[0136] In response to the received coordinates of the area to be measured, an image containing at least a portion of the area to be measured is obtained as the current image group in the post-fire extinguishing image.

[0137] Optionally, image preprocessing is performed based on the original image group, the thermal imaging image group, and the current image group to obtain the original panoramic image, the thermal imaging panoramic image, and the current panoramic image corresponding to the area to be measured, including:

[0138] Based on the original image set, image preprocessing is performed on the parameters of each image in the original image set to obtain the original panoramic image that matches the area to be measured.

[0139] Based on the thermal imaging image group, image preprocessing is performed on the parameters of each image in the thermal imaging image group to obtain a thermal imaging panoramic image that matches the original panoramic image. The thermal imaging panoramic image includes multiple images from different times.

[0140] Based on the parameters of each image in the current image group, perform image preprocessing to obtain a current panoramic image that matches the original panoramic image.

[0141] Image preprocessing includes at least one of image coordinate transformation, image cropping, and image stitching.

[0142] Optionally, based on the thermal imaging panoramic image, the temperature feature vector corresponding to the thermal imaging panoramic image is obtained, including:

[0143] Based on the thermal imaging panoramic image, obtain the first temperature time series data corresponding to the thermal imaging panoramic image;

[0144] Based on the first temperature time series data, obtain the second temperature time series data where the temperature is higher than the preset temperature threshold.

[0145] Based on the second temperature time series data, the temperature feature vector corresponding to the thermal imaging panoramic image is obtained.

[0146] Optionally, based on the original panoramic image, the current panoramic image, and the temperature feature vector, and using a pre-set disaster assessment model, disaster distribution data is obtained, including:

[0147] Based on the original panoramic image and the current panoramic image, image feature vectors are obtained through image feature extraction using dual image coding.

[0148] Based on the original panoramic image, target recognition is performed on the original image to obtain target data to be evaluated. The target data to be evaluated includes at least one target to be evaluated and target distribution data to be evaluated.

[0149] Based on the target to be evaluated, the attribute feature code corresponding to the target to be evaluated is obtained. The attribute feature code is configured to characterize the performance of the target to be evaluated at different temperatures.

[0150] Based on the distribution data of the target to be evaluated and the attribute feature encoding corresponding to at least one target to be evaluated, an attribute feature vector is obtained;

[0151] Input the image feature vector, temperature feature vector, and attribute feature vector into the pre-set disaster assessment model to obtain the disaster situation distribution data corresponding to the original panoramic image or the current panoramic image.

[0152] Optionally, based on the disaster distribution data, the fire-affected area can be obtained, including:

[0153] Perform edge detection and / or isolated point detection on the disaster distribution data;

[0154] When the disaster distribution data passes the detection, the fire-affected area is obtained based on the disaster distribution data;

[0155] When the disaster distribution data fails the test, the disaster distribution data is processed to obtain the fire-affected area.

[0156] Example 4

[0157] This embodiment provides a device including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement any of the methods described above.

[0158] Specifically, such as Figure 2 As shown, Figure 2 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of this application. The device is an electronic device and may include: a processor 101, such as a central processing unit (CPU), a communication bus 102, a user interface 104, a network interface 103, and a memory 105. The communication bus 102 is used to realize the connection and communication between these components. The user interface 104 may include a display screen and an input unit such as a keyboard. Optionally, the user interface 104 may also include a standard wired interface and a wireless interface. The network interface 103 may optionally include a standard wired interface and a wireless interface (such as a Wi-Fi interface). The memory 105 may be a storage device independent of the aforementioned processor 101. The memory 105 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as at least one disk storage device. The processor 101 may be a general-purpose processor, including a central processing unit, a network processor, etc., or it may be a digital signal processor, an application-specific integrated circuit, a field-programmable gate array or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component.

[0159] Those skilled in the art will understand that the appendix Figure 2 The structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0160] like Figure 2 As shown, the memory 105, which serves as a storage medium, may include an operating system, a network communication module, a user interface module, and an application program for implementing a method for measuring the fire-affected area based on thermal imaging fusion.

[0161] exist Figure 2 In the electronic device shown, the network interface 103 is mainly used for data communication with the network server; the user interface 104 is mainly used for data interaction with the user; the processor 101 and the memory 105 in this application can be set in the electronic device, and the electronic device can call the application program stored in the memory 105 through the processor 101 to implement a method for measuring the fire-affected area based on thermal imaging fusion to implement the above method.

[0162] Example 5

[0163] This embodiment provides a computer-readable storage medium on which a computer program is stored, and a processor executes the computer program to implement any of the methods described above.

[0164] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or it may be a device including one or any combination of the above-mentioned memories. The computer may be a variety of computing devices, including smart terminals and servers.

[0165] In the above embodiments of this disclosure, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0166] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0167] The units described as separate components may or may not be physically separate. Similarly, the components shown as units may or may not be physical units; they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0168] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0169] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable non-volatile storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a non-volatile storage medium and includes several instructions to cause a device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this disclosure. The aforementioned non-volatile storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0170] The above are merely preferred embodiments of this disclosure. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of this disclosure, and these improvements and modifications should also be considered within the scope of protection of this disclosure.

Claims

1. A method for measuring the fire-affected area based on thermal imaging fusion, characterized in that, include: In response to the received area to be measured, the original image group, thermal imaging image group, and current image group of the area to be measured are obtained; Image preprocessing is performed based on the original image group, the thermal imaging image group, and the current image group to obtain the original panoramic image, the thermal imaging panoramic image, and the current panoramic image corresponding to the area to be measured. Based on the thermal imaging panoramic image, a temperature feature vector corresponding to the thermal imaging panoramic image is obtained. The temperature feature vector is configured to be obtained based on the temperature of each pixel in the thermal imaging panoramic image at different times. Based on the original panoramic image, target recognition is performed on the original image to obtain target data to be evaluated. The target data to be evaluated includes at least one target to be evaluated and target distribution data to be evaluated. Based on the original panoramic image and the current panoramic image, image feature vectors are obtained through image feature extraction using dual image coding. Based on the target to be evaluated, the attribute feature code corresponding to the target to be evaluated is obtained, and the attribute feature code is configured to characterize the performance of the target to be evaluated at different temperatures. Based on the distribution data of the target to be evaluated and the attribute feature codes corresponding to the at least one target to be evaluated, an attribute feature vector is obtained; Input the image feature vector, the temperature feature vector, and the attribute feature vector into a preset disaster assessment model to obtain disaster situation distribution data corresponding to the original panoramic image or the current panoramic image. Edge detection and / or isolated point detection are performed on the disaster distribution data; When the disaster distribution data passes the detection, the fire-affected area is obtained based on the disaster distribution data; When the disaster distribution data fails the detection, the disaster distribution data is processed to obtain the fire-affected area.

2. The method for measuring fire-affected area based on thermal imaging fusion according to claim 1, characterized in that, The step of obtaining the original image group, thermal imaging image group, and current image group of the measured region in response to the received region to be measured includes: In response to the received coordinates of the area to be measured, an image containing at least a portion of the area to be measured is obtained from the image before the fire as the original image set; In response to the received coordinates of the area to be measured, an infrared image of at least part of the area to be measured is obtained as a thermal imaging image group in the image of the fire process; In response to the received coordinates of the area to be measured, an image containing at least a portion of the area to be measured is obtained as the current image group in the post-fire extinguishing image.

3. The method for measuring fire-affected area based on thermal imaging fusion according to claim 1, characterized in that, The step of performing image preprocessing based on the original image group, the thermal imaging image group, and the current image group to obtain the original panoramic image, the thermal imaging panoramic image, and the current panoramic image corresponding to the area to be measured includes: Based on the original image group, after image preprocessing based on the parameters of each image in the original image group, an original panoramic image matching the area to be measured is obtained; Based on the thermal imaging image group, image preprocessing is performed on the parameters of each image in the thermal imaging image group to obtain a thermal imaging panoramic image that matches the original panoramic image. The thermal imaging panoramic image includes multiple images from different times. Based on the current image group, image preprocessing is performed on the parameters of each image in the current image group to obtain a current panoramic image that matches the original panoramic image; The image preprocessing includes at least one of image coordinate transformation, image cropping, and image stitching.

4. The method for measuring fire-affected area based on thermal imaging fusion according to claim 1, characterized in that, The step of obtaining the temperature feature vector corresponding to the thermal imaging panoramic image based on the thermal imaging panoramic image includes: Based on the thermal imaging panoramic image, obtain the first temperature time series data corresponding to the thermal imaging panoramic image; Based on the first temperature time series data, second temperature time series data with a temperature higher than a preset temperature threshold is obtained; Based on the second temperature time series data, the temperature feature vector corresponding to the thermal imaging panoramic image is obtained.

5. A fire-affected area measurement system based on thermal imaging fusion, characterized in that, This includes an image processing platform and a fire analysis platform; The image processing platform is configured as follows: In response to the received area to be measured, the original image group, thermal imaging image group, and current image group of the area to be measured are obtained; Image preprocessing is performed based on the original image group, the thermal imaging image group, and the current image group to obtain the original panoramic image, the thermal imaging panoramic image, and the current panoramic image corresponding to the area to be measured. The fire analysis platform is configured as follows: Based on the thermal imaging panoramic image, a temperature feature vector corresponding to the thermal imaging panoramic image is obtained. The temperature feature vector is configured to be obtained based on the temperature of each pixel in the thermal imaging panoramic image at different times. Based on the original panoramic image, target recognition is performed on the original image to obtain target data to be evaluated. The target data to be evaluated includes at least one target to be evaluated and target distribution data to be evaluated. Based on the original panoramic image and the current panoramic image, image feature vectors are obtained through image feature extraction using dual image coding. Based on the target to be evaluated, the attribute feature code corresponding to the target to be evaluated is obtained, and the attribute feature code is configured to characterize the performance of the target to be evaluated at different temperatures. Based on the distribution data of the target to be evaluated and the attribute feature codes corresponding to the at least one target to be evaluated, an attribute feature vector is obtained; Input the image feature vector, the temperature feature vector, and the attribute feature vector into a preset disaster assessment model to obtain disaster situation distribution data corresponding to the original panoramic image or the current panoramic image. Edge detection and / or isolated point detection are performed on the disaster distribution data; When the disaster distribution data passes the detection, the fire-affected area is obtained based on the disaster distribution data; When the disaster distribution data fails the detection, the disaster distribution data is processed to obtain the fire-affected area.

6. A device, characterized in that, The device includes a memory and a processor, wherein the memory stores a computer program and the processor executes the computer program to implement the method according to any one of claims 1-4.

Images