Forest fire area identification method based on deep learning, electronic equipment and readable storage medium

Abstract

The invention provides a forest fire area identification method based on deep learning, and the method comprises the following steps: S1, obtaining a satellite remote sensing image data set of a forest, and carrying out the preprocessing of the satellite remote sensing image data set, and obtaining a sample data set; s2, an improved Mask2form model is constructed; s3, inputting the sample data set into the improved Mask2form model to carry out training; s4, judging whether the improved Mask2former model is trained or not, if yes, entering the step S5, and if not, entering the step S5; if not, adjusting the model parameters, and returning to the step S3; s5, an image to be recognized is input into the improved Mask2form model which is trained completely, and a segmentation result is obtained; through the method, the calculation complexity can be reduced, and the recognition accuracy of the forest fire area and the forest non-fire area is improved.

Description

Technical Field

[0001] The present invention relates to the field of image segmentation, and in particular to a forest burnt area recognition method based on deep learning, an electronic device and a readable storage medium. Background Art

[0002] Forest fires are a major factor threatening forest ecology, and have adverse effects on both the ecosystem and human society. Understanding the recovery of forests after disasters is conducive to formulating strategies for species diversity protection and ecological restoration, and also helps prevent secondary damage.

[0003] In the existing technology, machine learning models and deep learning models are often used to identify forest burn areas, and then observe the recovery of forests after disasters. However, the existing models have high computational complexity and low recognition accuracy, and cannot accurately identify burnt areas.

[0004] Therefore, in order to solve the above technical problems, it is urgent to propose a new technical means. Summary of the invention

[0005] In view of this, the present invention proposes a method capable of improving the recognition accuracy of forest burnt areas.

[0006] The present invention provides a method for identifying forest burnt areas based on deep learning, comprising the following steps:

[0007] S1. Obtain a satellite remote sensing image dataset of a forest, and preprocess the satellite remote sensing image dataset to obtain a sample dataset;

[0008] S2. Build an improved Mask2former model;

[0009] The improved Mask2former model includes an EASwin-Transformer network, a pixel decoder and a Transformer decoder, wherein the image is input into the EASwin-Transformer network and the Transformer decoder respectively, the output end of the EASwin-Transformer network is connected to the input end of the pixel decoder, and the output end of the pixel decoder is connected to the input end of the Transformer decoder;

[0010] The EASwin-Transformer network includes a Swin-Transformer network and an EfficientlyAdaptive module; the output end of the Swin-Transformer network is connected to the input end of the Efficiently Adaptive module;

[0011] The Efficiently Adaptive module includes a feature grouping module, four average pooling modules, three 1×1 convolution modules, a 3×3 convolution module, two splicing modules, three activation function layers, a group normalization module and two Sigmoid function layers;

[0012] Among them, the output end of the feature grouping module is connected to the input end of the first average pooling module, the second average pooling module and the 3×3 convolution module; the output ends of the first average pooling module and the second average pooling module are both connected to the input end of the first splicing module, the output end of the first splicing module is connected to the input end of the first Sigmoid function layer, the output end of the first Sigmoid function layer is connected to the input end of the group normalization module, the output end of the group normalization module is connected to the input end of the third average pooling module, and the output end of the third average pooling module is connected to the input end of the first activation function layer; the output features of the first 3×3 convolution module are multiplied element by element with the output features of the first activation function layer, and the features after element-by-element multiplication are input to the second Sigmoid function layer; the output end of the first 3×3 convolution module is also connected to the The input ends of the four average pooling modules, the output end of the fourth average pooling module is connected to the input end of the second activation function layer, the output features of the second activation function layer are multiplied element-by-element with the output features of the group normalization module, and the features obtained by the element-by-element multiplication are input into the second Sigmoid function layer, the output end of the second Sigmoid function layer is respectively connected to the input ends of the second 1×1 convolution module, the third 1×1 convolution module and the second splicing module, the output end of the second 1×1 convolution module is connected to the input end of the second splicing module, the output end of the second splicing module is connected to the third activation function layer, the output features of the third activation function layer are multiplied element-by-element with the output features of the third 1×1 convolution module, and the features after the element-by-element multiplication are fused with the features output by the second 1×1 convolution module to obtain the output features of the Efficiently Adaptive module;

[0013] S3. Input the sample data set into the improved Mask2former model for training;

[0014] S4. Determine whether the improved Mask2former model is trained. If so, proceed to step S5; if not, adjust the model parameters and return to step S3;

[0015] S5. Input the image to be recognized into the trained improved Mask2former model to obtain the segmentation result.

[0016] Furthermore, in step S3, the following loss function Loss is used for training:

[0017]

[0018] Among them, i represents the serial number of the category, n represents the total number of categories, j represents the serial number of the sample, b represents the total number of samples, and y represents the total number of samples. ji represents the true label of the jth sample belonging to category i, It represents the predicted probability that the jth sample belongs to category i.

[0019] Furthermore, in step S1, the preprocessing method at least includes image enhancement, noise addition, flipping and noise removal.

[0020] Further, in step S4, when the improved Mask2former model training reaches a preset goal, the improved Mask2former model training is completed.

[0021] Accordingly, the present invention also provides an electronic device, comprising:

[0022] A memory and a processor, wherein the memory is used to store a computer program, and when the computer program is executed by the processor, the above-mentioned forest fire area identification method based on deep learning is implemented.

[0023] Correspondingly, the present invention also provides a readable storage medium, in which computer instructions are stored. When the computer instructions are executed by a processor, the above-mentioned forest fire area identification method based on deep learning is implemented.

[0024] Beneficial effects of the present invention: By improving the Mask2former model, the present invention can reduce the computational complexity while efficiently learning the high-level features of the object of interest, thereby improving the segmentation accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The present invention will be further described below in conjunction with the accompanying drawings and embodiments:

[0026] Figure 1 It is a flow chart of the present invention.

[0027] Figure 2 Schematic diagram of the improved Mask2former model structure of the present invention.

[0028] Figure 3 It is a schematic diagram of the structure of the Efficiently Adaptive module of the present invention. DETAILED DESCRIPTION

[0029] The present invention is further described below in conjunction with the accompanying drawings:

[0030] The present invention provides a method for identifying forest burnt areas based on deep learning, comprising the following steps:

[0031] S1. Obtain a satellite remote sensing image dataset of a forest, and preprocess the satellite remote sensing image dataset to obtain a sample dataset;

[0032] S2. Build an improved Mask2former model;

[0033] The improved Mask2former model includes an EASwin-Transformer network, a pixel decoder and a Transformer decoder, wherein the image is input into the EASwin-Transformer network and the Transformer decoder respectively, the output end of the EASwin-Transformer network is connected to the input end of the pixel decoder, and the output end of the pixel decoder is connected to the input end of the Transformer decoder; the output features of the pixel decoder and the features of the Transformer decoder are multiplied element by element and then output;

[0034] The EASwin-Transformer network includes a Swin-Transformer network and an EfficientlyAdaptive module; the output end of the Swin-Transformer network is connected to the input end of the Efficiently Adaptive module;

[0035] The Efficiently Adaptive module includes a feature grouping module, four average pooling modules, three 1×1 convolution modules, a 3×3 convolution module, two splicing modules, three activation function layers, a group normalization module and two Sigmoid function layers;

[0036] Among them, the output end of the feature grouping module is connected to the input end of the first average pooling module, the second average pooling module and the 3×3 convolution module; the output ends of the first average pooling module and the second average pooling module are both connected to the input end of the first splicing module, the output end of the first splicing module is connected to the input end of the first Sigmoid function layer, the output end of the first Sigmoid function layer is connected to the input end of the group normalization module, the output end of the group normalization module is connected to the input end of the third average pooling module, and the output end of the third average pooling module is connected to the input end of the first activation function layer; the output features of the first 3×3 convolution module are multiplied element by element with the output features of the first activation function layer, and the features after element-by-element multiplication are input to the second Sigmoid function layer; the output end of the first 3×3 convolution module is also connected to the The input ends of the four average pooling modules, the output end of the fourth average pooling module is connected to the input end of the second activation function layer, the output features of the second activation function layer are multiplied element-by-element with the output features of the group normalization module, and the features obtained by the element-by-element multiplication are input into the second Sigmoid function layer, the output end of the second Sigmoid function layer is respectively connected to the input ends of the second 1×1 convolution module, the third 1×1 convolution module and the second splicing module, the output end of the second 1×1 convolution module is connected to the input end of the second splicing module, the output end of the second splicing module is connected to the third activation function layer, the output features of the third activation function layer are multiplied element-by-element with the output features of the third 1×1 convolution module, and the features after the element-by-element multiplication are fused with the features output by the second 1×1 convolution module to obtain the output features of the Efficiently Adaptive module;

[0037] S3. Input the sample data set into the improved Mask2former model for training;

[0038] S4. Determine whether the improved Mask2former model is trained. If so, proceed to step S5; if not, adjust the model parameters and return to step S3;

[0039] S5. Input the image to be identified into the trained improved Mask2former model to obtain the segmentation result. Through the above method, the forest burnt area can be accurately identified and the accuracy of identification can be improved.

[0040] A forest burnt area is an area in a forest that has been burned by fire.

[0041] In this embodiment, in step S1, a satellite remote sensing image dataset of a forest is obtained, and the satellite remote sensing image dataset is preprocessed to obtain a sample dataset;

[0042] Specifically, this embodiment uses a DJI MAVIC 3 drone to collect images, with an effective pixel of 20 million, a sensitivity range of 100 to 6400, an image size of 5280×3956, and a storage format of JPEG. The data collection area should meet sufficient natural lighting conditions (>15lux), and the diffuse reflectivity of the material in the scene should be >20%;

[0043] The preprocessing method includes at least image enhancement, noise addition, flipping and noise removal; it may also include image cropping to obtain more sample data; among which image cropping, image enhancement, noise addition, flipping and noise removal are all existing technologies, and the specific preprocessing methods are not described in detail here.

[0044] Since satellite remote sensing images usually contain multispectral information, more detailed data can be extracted from the images. In addition, the upper limit of the display range of satellite remote sensing images is extremely high, which helps to ignore local interference and conduct global analysis.

[0045] In this embodiment, in step S2, an improved Mask2former model is constructed;

[0046] The improved Mask2former model includes an EASwin-Transformer network, a pixel decoder and a Transformer decoder, wherein the image is input into the EASwin-Transformer network and the Transformer decoder respectively, the output end of the EASwin-Transformer network is connected to the input end of the pixel decoder, and the output end of the pixel decoder is connected to the input end of the Transformer decoder (Efficiently Adaptive Swin-Transformer network), such as Figure 2 As shown, it includes an EASwin-Transformer network, a pixel decoder Pixel Decoder and a Transformer Decoder (Transformer decoder), the output end of the EASwin-Transformer network is connected to the input end of the pixel decoder Pixel Decoder, and the output end of the pixel decoder Pixel Decoder is connected to the input end of the Transformer decoder; the output feature of the pixel decoder is multiplied element by element with the output feature of the Transformer decoder and output.

[0047] Mask2former is an efficient and flexible segmentation model. Its multi-scale features greatly improve the accuracy of segmentation. It is a segmentation method suitable for specific objects. The structure of the Mask2former model, as well as the pixel decoder Pixel Decoder and Transformer decoder are all existing structures and will not be repeated here.

[0048] The EASwin-Transformer network (Efficiently Adaptive Swin-Transformer network) includes a Swin-Transformer network and an Efficiently Adaptive module; the output end of the Swin-Transformer network is connected to the input end of the Efficiently Adaptive module; the output end of the Efficiently Adaptive module is connected to the input end of the pixel decoder Pixel Decoder;

[0049] Swin-Transformer uses hierarchical feature representation based on the excellent attention mechanism of Transformer, which can not only better preserve detailed information, but also better obtain global context and adapt to image features of various scales. At the same time, the sliding window mechanism in Swin-Transformer applies local window attention on the feature map to reduce computational complexity and improve the model's ability to capture long-distance dependencies. This improves the computational efficiency of the model while enhancing the performance when processing high-resolution images. The Swin-Transformer network structure is an existing structure and will not be described here.

[0050] In the process of secondary succession, forests gradually recovering from wildfires face fierce competition among different species, and dominant species are constantly alternating. At the same time, due to the different degrees of fire damage in different regions, they are in different stages of succession, and the situation is complex and changeable. In order to achieve better segmentation effects in this complex environment, this application introduces the ContextualTransformer module (CoT module). The CoT module integrates contextual information mining and self-attention mechanism, which can better explore contextual information in complex environments and help distinguish different adjacent objects; in order to further enhance the feature extraction ability of the network in classification tasks, this application introduces the idea of ​​Efficient Multi-Scale Attention (MSA) in the CoT module, and finally forms an Efficiently Adaptive module; MSA reshapes some channels into batch dimensions and divides the channel dimension into multiple sub-features, so that spatial semantic features are well distributed in each feature group. At the same time, MSA recalibrates the channel weights of each parallel branch by encoding global information, so that the channel content can be learned more effectively without reducing the channel dimension, and produces better pixel-level attention in high-level feature mapping.

[0051] Specifically, the Efficiently Adaptive module includes a feature grouping module, four average pooling modules, three 1×1 convolution modules, a 3×3 convolution module, two concatenation modules, three activation function layers, a group normalization module and two Sigmoid function layers; Figure 3 As shown;

[0052] Among them, the output end of the feature grouping module is connected to the input end of the first average pooling module, the second average pooling module and the 3×3 convolution module; the output ends of the first average pooling module and the second average pooling module are both connected to the input end of the first splicing module, the output end of the first splicing module is connected to the input end of the first Sigmoid function layer, the output end of the first Sigmoid function layer is connected to the input end of the group normalization module, the output end of the group normalization module is connected to the input end of the third average pooling module, and the output end of the third average pooling module is connected to the input end of the first activation function layer; the output features of the first 3×3 convolution module are multiplied element by element with the output features of the first activation function layer, and the features after element-by-element multiplication are input to the second Sigmoid function layer; the output end of the first 3×3 convolution module is also connected to the The input ends of the four average pooling modules, the output end of the fourth average pooling module is connected to the input end of the second activation function layer, the output features of the second activation function layer are multiplied element-by-element with the output features of the group normalization module, and the features obtained by the element-by-element multiplication are input into the second Sigmoid function layer, the output end of the second Sigmoid function layer is respectively connected to the input ends of the second 1×1 convolution module, the third 1×1 convolution module and the second splicing module, the output end of the second 1×1 convolution module is connected to the input end of the second splicing module, the output end of the second splicing module is connected to the third activation function layer, the output features of the third activation function layer are multiplied element-by-element with the output features of the third 1×1 convolution module, and the features after the element-by-element multiplication are fused with the features output by the second 1×1 convolution module to obtain the output features of the Efficiently Adaptive module;

[0053] The feature grouping module is used to divide the input feature into g sub-features in the channel dimension; dividing the feature into multiple sub-features in the channel dimension is an existing technology, and the average pooling module, the convolution module, the splicing module, the activation function layer (with an activation function set therein), the group normalization module (Group norm) and the Sigmoid function layer are all existing technologies and will not be repeated here;

[0054] The Efficiently Adaptive module divides the input feature map into g sub - features in the channel dimension for learning different semantics. Usually, g << c (channels), and the learned attention weight descriptors are used to enhance the feature representation of the regions of interest in each sub - feature. The Efficiently Adaptive module extracts the attention weight descriptors of the grouped feature maps through three parallel routes. Two of the parallel paths are on the 1×1 branches, and the third parallel path is on the 3×3 branch. In the 3×3 branch, only one 3×3 convolutional kernel is used to capture multi - scale feature representation, reducing the computational requirements and enlarging the feature space. The features output from the convolution pass through the average pooling module and the activation function layer in sequence. In the 1×1 branches, global average pooling operations are adopted along two spatial directions respectively. The features after global average pooling are concatenated along the height direction of the image and input into the 1×1 convolution module. After decomposing the output of the 1×1 convolution into two vectors, the two - dimensional binomial distribution after linear convolution is fitted using the non - linear Sigmoid function. Cross - channel feature interaction is achieved by multiplying two channels within each group (the 3×3 branch and the 1×1 branch). The output of the 1×1 branch is encoded using two - dimensional global average pooling and converted into the corresponding dimensional shape. To improve computational efficiency, the non - linear function Softmax is used at the output of the two - dimensional global average pooling to fit the above - mentioned linear transformation. By multiplying the output of the above parallel processing element - by - element with the matrix dot - product operation, we obtain the first spatial attention map containing spatial position information. The same method is used on the 3×3 branch to obtain the second spatial attention map, and then the two sets of generated spatial attention weight sets are passed through the Sigmoid function to obtain the pixel - level attention map;

[0055] The pixel - level attention map is respectively input into two 1×1 convolution modules to obtain the input static context representation K1 and the input value V. Then, K1 is merged with the Query of the input pixel - level attention map, and then through the non - linear function Softmax, the attention matrix A is obtained. The attention matrix A is multiplied element - by - element with the input value V to achieve the input dynamic context representation K2. The static context representation K1 and the dynamic context representation K2 are added (fused) to output the extracted features.

[0056] In the CoT module, the MAS mechanism is applied. While enhancing the capture of context information, the context information is used to better focus on higher - level and deeper features, which enables the network to efficiently learn the high - level features of the objects of interest while adapting to tasks in complex environments.

[0057] The use of the improved Mask2former model can not only improve the computational efficiency of the model, but also enhance the performance when processing high-resolution images; it can also enhance the ability to capture contextual information and learn key features, thereby improving segmentation accuracy.

[0058] In this embodiment, in step S3, the sample data set is input into the improved Mask2former model for training;

[0059] The learning rate is set to 0.0001, the batch size is 2, and a total of 250 epochs are trained with the following loss function Loss:

[0060]

[0061] Among them, i represents the serial number of the category, n represents the total number of categories, j represents the serial number of the sample, b represents the total number of samples, and y represents the total number of samples. ji represents the true label of the jth sample belonging to category i, It represents the predicted probability that the jth sample belongs to category i.

[0062] By setting the above loss function, the difference between the model's predicted distribution and the true distribution can be effectively measured. By minimizing the cross entropy loss function, the model's predicted probability distribution can be made as close as possible to the probability distribution of the true label.

[0063] In this embodiment, in step S4, it is determined whether the improved Mask2former model is trained. If so, the process proceeds to step S5; if not, the model parameters are adjusted and the process returns to step S3;

[0064] When the improved Mask2former model training reaches the preset target, the improved Mask2former model training is completed; the preset target can be a preset number of training times or a preset convergence degree, which is not limited here and can be set according to needs. Through the above method, a more accurate prediction model can be obtained.

[0065] In this embodiment, in step S5, the image to be identified is input into the trained improved Mask2former model, which can realize the identification of forests, burned areas and non-forest areas, such as roads, buildings, ponds and construction sites.

[0066] In order to evaluate the performance of the improved Mask2former model, four commonly used evaluation indicators are used for evaluation, namely mAcc (mean of Acc), mIou (mean of Iou), mDice (mean of Dice) and mPrecision (mean of Precision). Their values ​​are all in the range of 0-1. The closer to 1, the better the prediction of the model. For TP (the true value belongs to a certain class and the predicted result after segmentation is also that class), TN (the true value does not belong to a certain class and the predicted result after segmentation is not that class), FP (the true value does not belong to a certain class but the predicted result after segmentation is that class), and FN (the true value belongs to a certain class but the predicted result after segmentation is not that class), Acc, Iou, Dice and Precision are calculated by the following formulas:

[0067]

[0068]

[0069]

[0070]

[0071] Among them, n TP 、n TN 、n FP and n FN They represent the number of TP, TN, FP and FN respectively;

[0072] In order to verify the partial effectiveness and versatility of the improved Mask2former model, this application performs segmentation on a total of 19 types of objects, including "highway", "sidewalk", "building", "high wall", "fence", "pole", "traffic light", "traffic sign", "plant", "terrain", "sky", "pedestrian", "cyclist", "car", "truck", "bus", "train", "motorcycle" and "bicycle" on the image segmentation open source dataset Cityscapes. The segmentation models include: Deeplabv3+ segmentation model with Resnet101 as the main network, Segformer segmentation model with MixViT as the main network, Mask2former segmentation model with Resnet50 as the main network, Mask2former segmentation model with Swin-Transformer as the main network, and Mask2former segmentation model with EAswin-Transformer as the main network (i.e., the improved Mask2former model in this application), etc., and the above segmentation models are compared with each other using the same dataset and training method, and the experimental results are shown in Table 1:

[0073] Segmentation Model Backbone network mAcc mIou mDice mPrecision DeepLabV3+ Resnet101 0.7209 0.6361 0.7260 0.7817 Segformer MixViT 0.7689 0.6806 0.7968 0.8433 Mask2former Resnet50 0.7753 0.6732 0.7910 0.8184 Mask2former Swin-Transformer 0.8191 0.7068 0.8213 0.8303 Mask2former EAswin-Transformer 0.8365 0.7281 0.8352 0.8396

[0074] Table 1 Comparative experimental results of open source dataset Cityscapes

[0075] The sample data set of this application is used to evaluate the above segmentation model, and the experimental results are shown in Table 2:

[0076] Segmentation Model Backbone network mAcc mIou mDice mPrecision DeepLabV3+ Resnet101 0.8299 0.7231 0.8373 0.8455 Segformer MixViT 0.8481 0.7460 0.8528 0.8580 Mask2former Resnet50 0.8545 0.7309 0.8421 0.8310 Mask2former Swin-Transformer 0.8576 0.7577 0.8602 0.8633 Mask2former EAswin-Transformer 0.8623 0.7635 0.8642 0.8668

[0077] Table 2 Comparative experimental results of sample data sets

[0078] It can be concluded from Tables 1 and 2 that the improved Mask2former model in this application has the best performance in all key indicators, with a high average intersection over union (mIou). mIou is particularly important in segmentation tasks. A high mIou can indicate the high accuracy of the segmentation result on the one hand, and the low misjudgment rate of the image parts of different categories in the segmentation result on the other hand. It is a key indicator for evaluating the performance of the segmentation model, especially for evaluating the consistency between the predicted results and the observed values. The above results show that the model in this application can more effectively extract information from burned areas and forest images, thereby improving the accuracy of prediction.

[0079] To further verify the effectiveness of the Efficiently Adaptive module (EA module), it is necessary to conduct ablation experiments on the EA module, CoT module and MAS module respectively. The ablation experiment results are shown in Table 3:

[0080] Segmentation Model CoT MAS mAcc mIou mDice mPrecision Mask2former × × 0.8576 0.7577 0.8602 0.8633 Mask2former √ × 0.8528 0.7599 0.8618 0.8715 Mask2former × √ 0.8607 0.7609 0.8625 0.8659 Mask2former √ √ 0.8623 0.7635 0.8642 0.8668

[0081] Table 3 Ablation experiment results

[0082] Among them, the Mask2former model that includes both the CoT module and the MAS module is the improved Mask2former model in this application; from the ablation experiment results, it can be seen that in order to improve the ability of contextual information to guide dynamic learning and strengthen the ability of visual representation, this application adds the CoT module. The results show that there is indeed an improvement in mIou, but although the average precision (mPrecision) is the highest among all the improved methods, the average intersection-over-union ratio (mIou) is the lowest, which shows that the improvement of the CoT module sometimes leads to misjudgment, which may be due to insufficient learning of some key and deep features such as texture. The improvement using the MAS module avoids this problem very well. The MAS module improves the ability of information extraction by reshaping some channels to the batch dimension and grouping the channel dimension into multiple sub-features. At the same time, it is more efficient and can avoid boundary blur. The EA module combines the advantages of both, not only improving the ability of information extraction, but also having a stronger learning ability for long-distance data, and effectively avoiding the problem of boundary blur.

[0083] Accordingly, the present invention also provides an electronic device, comprising:

[0084] A memory and a processor, wherein the memory is used to store a computer program, and when the computer program is executed by the processor, the above-mentioned forest fire area identification method based on deep learning is implemented.

[0085] Correspondingly, the present invention also provides a readable storage medium, in which computer instructions are stored. When the computer instructions are executed by a processor, the above-mentioned forest fire area identification method based on deep learning is implemented.

[0086] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

Claims

1. A forest burnt area identification method based on deep learning, characterized in that: The following steps are involved: S1. Obtain a satellite remote sensing image dataset of a forest, and preprocess the satellite remote sensing image dataset to obtain a sample dataset; S2. Build an improved Mask2former model; The improved Mask2former model includes an EASwin-Transformer network, a pixel decoder and a Transformer decoder, wherein the image is input into the EASwin-Transformer network and the Transformer decoder respectively, the output end of the EASwin-Transformer network is connected to the input end of the pixel decoder, and the output end of the pixel decoder is connected to the input end of the Transformer decoder; The EASwin-Transformer network includes a Swin-Transformer network and an Efficiently Adaptive module; the output end of the Swin-Transformer network is connected to the input end of the Efficiently Adaptive module; The Efficiently Adaptive module includes a feature grouping module, four average pooling modules, three 1×1 convolution modules, a 3×3 convolution module, two splicing modules, three activation function layers, a group normalization module and two Sigmoid function layers; Among them, the output end of the feature grouping module is connected to the input end of the first average pooling module, the second average pooling module and the 3×3 convolution module; the output ends of the first average pooling module and the second average pooling module are both connected to the input end of the first splicing module, the output end of the first splicing module is connected to the input end of the first Sigmoid function layer, the output end of the first Sigmoid function layer is connected to the input end of the group normalization module, the output end of the group normalization module is connected to the input end of the third average pooling module, and the output end of the third average pooling module is connected to the input end of the first activation function layer; the output features of the first 3×3 convolution module are multiplied element by element with the output features of the first activation function layer, and the features after element-by-element multiplication are input to the second Sigmoid function layer; the output end of the first 3×3 convolution module is also connected to the The input ends of the four average pooling modules, the output end of the fourth average pooling module is connected to the input end of the second activation function layer, the output features of the second activation function layer are multiplied element-by-element with the output features of the group normalization module, and the features obtained by the element-by-element multiplication are input into the second Sigmoid function layer, the output end of the second Sigmoid function layer is respectively connected to the input ends of the second 1×1 convolution module, the third 1×1 convolution module and the second splicing module, the output end of the second 1×1 convolution module is connected to the input end of the second splicing module, the output end of the second splicing module is connected to the third activation function layer, the output features of the third activation function layer are multiplied element-by-element with the output features of the third 1×1 convolution module, and the features after the element-by-element multiplication are fused with the features output by the second 1×1 convolution module to obtain the output features of the Efficiently Adaptive module; S3. Input the sample data set into the improved Mask2former model for training; S4. Determine whether the improved Mask2former model is trained. If so, proceed to step S5; if not, adjust the model parameters and return to step S3; S5. Input the image to be recognized into the trained improved Mask2former model to obtain the segmentation result.

2. The forest burnt area identification method based on deep learning according to claim 1 is characterized in that: In step S3, the following loss function Loss is used for training: Among them, i represents the serial number of the category, n represents the total number of categories, j represents the serial number of the sample, b represents the total number of samples, and y represents the number of samples. ji represents the true label of the jth sample belonging to category i, It represents the predicted probability that the jth sample belongs to category i.

3. The forest burnt area identification method based on deep learning according to claim 1 is characterized in that: In step S1, the preprocessing method at least includes image enhancement, noise addition, flipping and noise removal.

4. The forest burnt area identification method based on deep learning according to claim 1 is characterized in that: In step S4, when the improved Mask2former model training reaches a preset goal, the improved Mask2former model training is completed.

5. An electronic device, characterized in that: include: A memory and a processor, wherein the memory is used to store a computer program, and when the computer program is executed by the processor, the forest burn area identification method based on deep learning as described in any one of claims 1 to 4 is implemented.

6. A readable storage medium, characterized in that: The readable storage medium stores computer instructions, which, when executed by a processor, implement the forest burn area identification method based on deep learning as described in any one of claims 1 to 4.

Images