Detection method for boundary enhancement and small target perception of problem map

Abstract

The invention relates to the technical field of target detection, and particularly provides a detection method for boundary enhancement and small target perception of a problem map. The method comprises the steps that a double-branch attention convolution module fusing convolution and an attention mechanism is constructed, and the boundary sensing ability is enhanced through a global-local feature collaborative enhancement mechanism; designing a multi-path feature aggregation mechanism, and dynamically reconstructing multi-scale feature representation through bidirectional path interaction and adaptive weighted fusion; constructing a global context fusion module to balance global information and local information; according to the method, the target query is refined through the prediction head, and the category label and the bounding box are generated, so that the overall boundary perception capability is enhanced, the sufficiency and effectiveness of feature aggregation are ensured, and the positioning precision of the target and the accuracy of national boundary region identification are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of target detection, and particularly relates to a detection method for boundary enhancement and small target perception of a problem map. BACKGROUND

[0002] In recent years, target detection technology has been applied to the detection of problem maps. However, due to the special nature of map data, detection still faces many challenges and it is difficult to achieve ideal detection results. Specifically, scale changes and complex background interference can cause discontinuity of boundary features (such as national boundary lines), thereby reducing recognition accuracy. In addition, small targets such as islands are prone to be ignored or confused with the background due to the small number of pixels, local texture blur, and unclear edge details, resulting in missed detection or false detection. Therefore, it is necessary to design a detection model for the characteristics of map data to effectively extract and enhance edge information, thereby improving the detection accuracy of complex boundaries and small targets.

[0003] Attention mechanisms play a key role in enhancing edge representations, but traditional methods are difficult to adapt to complex boundary shapes and suppress background noise, often leading to incomplete or unstable edge extraction. In addition, single-scale feature extraction cannot handle targets of different sizes and shapes simultaneously, which limits the performance of the model in target recognition tasks. Furthermore, single-scale methods also have shortcomings in capturing the overall structure of large targets, leading to decreased positioning accuracy. Multi-scale feature fusion is one of the key technologies to address target detection challenges such as insufficient feature representation and low model positioning accuracy. In existing technologies, feature pyramid networks are used to integrate features of different levels layer by layer through upsampling to achieve multi-scale fusion. However, a single top-down path may ignore the feedback effect of low-level detail features on high-level semantic features. In addition, high-resolution networks proposed in existing technologies achieve multi-resolution feature fusion through feature interaction, but in the fusion process, low-resolution feature maps may introduce redundant information, affecting fusion performance.

[0004] Methods combining scale-oriented modeling and attention mechanisms also show certain advantages in enhancing small target features. For example, existing methods propose adaptive feature fusion, which dynamically adjusts features between different scales through learnable weights, thereby enhancing the representation ability of small targets. Meanwhile, methods that apply dilated convolution to expand the receptive field while maintaining high resolution effectively preserve the fine detail information of small targets. However, these methods still face challenges in practical applications, such as alignment errors in feature maps and the grid effect caused by dilated convolution, which can cause holes and breaks in feature maps, thereby affecting the complete detection and feature extraction of small targets. SUMMARY

[0005] Therefore, the application provides a detection method for boundary enhancement and small target perception of a problem map, so as to enhance the overall boundary perception ability, ensure the sufficiency and effectiveness of feature aggregation, improve the positioning accuracy of the target and the accuracy of the identification of the national border region.

[0006] In a first aspect, the application provides a detection method for boundary enhancement and small target perception of a problem map, comprising: Step 1, constructing a double-branch attention convolution module fusing convolution and attention mechanism, and enhancing the boundary perception ability through a global-local feature cooperative enhancement mechanism; Step 2, according to step 1, designing a multi-path feature aggregation mechanism, dynamically reconstructing multi-scale feature representation through bidirectional path interaction and adaptive weighted fusion; Step 3, according to step 2, constructing a global context fusion module to balance the global information and the local information; Step 4, according to step 3, refining the target query through a prediction head and generating a category label and a bounding box.

[0007] Optionally, the step 1 comprises: Global correlation modeling path: first, 1×1 and 3×3 convolution operations are performed on the input feature to generate query Q, key K and value V tensors; then, an attention map is calculated through a weighted filtering strategy to realize the interaction between local features; then, weighted product operation is performed on the attention map and the value V to obtain the final output feature map , combined with dynamic convolution, to optimize the modeling effect of the edge; wherein, The expression of is as follows: Wherein, X∈ represents an input feature map, ∈ are 3×3 depth separable convolution kernels of the query Q, the key K and the value V respectively; is a scaling factor, and = C ; wherein, H represents the height of the feature map, W represents the width of the feature map, and C represents the channel number of the feature map; Local channel interaction path: first, the input feature is compressed and reconstructed through 1×1 convolution operation; then, the input feature is divided into N subgroups along the channel dimension, and each subgroup extracts fine-grained local information through depth separable convolution; then, channel rearrangement is introduced to rearrange the channel index, and dynamic convolution and random dropout are used in combination; Finally, the results of the global correlation modeling path and the local channel interaction path are fused after element-wise addition and summation to obtain the output feature.

[0008] Optionally, the step 2 comprises: The multi-path feature aggregation mechanism passes deep semantic information to shallow features through expression (2) to enhance semantic perception ability, and expression (2) is in the form of: (2); wherein, represents the output feature map after fusion of the i-th layer; represents the feature of the i-th layer; and represents the weight, used to adjust the contribution ratio of the up-sampling feature and the current layer feature respectively; function represents up-sampling the feature of the i+1-th layer to match the resolution of the i-th layer feature; Meanwhile, the feature information is backward propagated through the bottom-up path to feed back the fine-grained information in the shallow feature to the deep feature, and the process is expressed as: (3); wherein, function represents down-sampling the feature of the i-1-th layer to match the resolution of the i-th layer feature; In the part of bidirectional path interaction, the multi-path feature aggregation mechanism introduces adaptive weighted fusion; through expression (4), the weights from two different scale features are dynamically adjusted to realize feature fusion, and finally the fusion output O is obtained, and expression (4) is in the form of: (4); wherein, represents the feature map of the first scale path; represents the feature map of the second scale path; represents a constant, taking the value of 1x10 -4 .

[0009] Optionally, the step 3 comprises: The global context fusion module models the features of different levels through a multi-branch structure. First, the global context fusion module combines the global average pooling GAP and the global maximum pooling GMP to extract the global information of the input feature through expression (5), and expression (5) is in the form of: (5); wherein, , ; H represents the height of the feature map, W represents the width of the feature map, represents the feature value at the spatial position (i, j); and respectively represent the weights of linear transformation on the features extracted by global average pooling and global maximum pooling respectively; represent the global distribution features extracted by global average pooling, represent the salient region features extracted by global maximum pooling; both are weighted and summed after being weighted by the attention weights generated by the activation function Softmax to obtain the global feature output . Secondly, the global context fusion module introduces a self-attention mechanism, generates query Q and key K through 1x1 convolution, and performs nonlinear mapping through an activation function to improve the feature expression capability, and at the same time, the value V is directly obtained from the input feature; then, the query Q, the key K and the value V are multiplied element by element to generate the enhanced global feature representation, and the expression of the process is: (6); wherein, represent the global enhanced feature output generated by the self-attention mechanism; , are 1x1 convolution kernels of the query Q and the key K respectively; Finally, the global feature processed by 1x1 convolution is fused with for prediction.

[0010] Secondly, the global context fusion module introduces a self-attention mechanism, generates query Q and key K through 1x1 convolution, and performs nonlinear mapping through an activation function to improve the feature expression capability, and at the same time, the value V is directly obtained from the input feature; then, the query Q, the key K and the value V are multiplied element by element to generate the enhanced global feature representation, and the expression of the process is:

[0011] Thirdly, the embodiments of the present application provide an electronic device, comprising: one or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs comprise instructions, when the instructions are executed by the device, the device executes the detection method for boundary enhancement and small target perception of the problem map in the first aspect or any possible implementation manner of the first aspect.

[0012] The technical scheme provided by the application comprises the following steps: a double-branch attention convolution module of fusion of convolution and attention mechanism is constructed, and a global-local feature cooperative enhancement mechanism is used to enhance the boundary perception capability; a multi-path feature aggregation mechanism is designed, and bidirectional path interaction and adaptive weighted fusion are used to dynamically reconstruct multi-scale feature representation; a global context fusion module is constructed to balance global information and local information; a prediction head is used to refine the target query and generate a category label and a bounding box, the method enhances the overall boundary perception capability, ensures the sufficiency and effectiveness of feature aggregation, and improves the positioning accuracy of the target and the accuracy of the boundary region identification. BRIEF DESCRIPTION OF DRAWINGS

[0013] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0014] Figure 1 The flowchart of the detection method for boundary enhancement and small target perception of the problem map provided by the embodiment of the present application is shown in the figure. Figure 2 The architecture diagram of the detection method for boundary enhancement and small target perception of the problem map provided by the embodiment of the present application is shown in the figure. Figure 3 The architecture diagram of the double-branch attention convolution module provided by the embodiment of the present application is shown in the figure. Figure 4 The architecture diagram of the global context fusion module provided by the embodiment of the present application is shown in the figure. Figure 5 The schematic diagram of an electronic device provided by the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0015] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0016] It should be clear that the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0017] The terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the description of the application and the appended claims, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

[0018] It should be understood that, the term "and / or" used herein is merely an association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the following three cases: A exists alone, A and B exist together, and B exists alone. In addition, the character " / " in this paper generally represents that the front and rear associated objects are a "or" relationship.

[0019] Depending on the context, the word "if" as used herein can be interpreted as meaning "when" or "upon" or "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if determined" or "if detecting (a stated condition or event)" can be interpreted as meaning "when determined" or "in response to determining" or "when detecting (a stated condition or event)" or "in response to detecting (a stated condition or event)".

[0020] The application provides a detection method for boundary enhancement and small target perception of a problem map, as shown in Figure 1 and Figure 2 The method comprises the following steps: The method of the present application first extracts features through a three-stage backbone network, obtains multiple different scale features, and transmits these different scale features to the neck for further processing. In the backbone network, the input picture is processed by a convolutional block with batch normalization and Swish activation function (CBS), a plurality of cross-stage partial block (CSP) stacking structures and a spatial pyramid pooling-fast (SPPF) module in turn, and a plurality of feature maps with different resolutions are gradually generated. These modules work together to not only realize multi-level feature extraction of the image, but also retain rich spatial information and semantic information. In the neck, the dual-branch attention convolution module (DACM) enhances the boundary perception ability by modeling global and local features. Subsequently, the multi-path feature aggregation (MPFA) mechanism uses a weighting strategy to perform bidirectional cross-scale fusion to maximize the retention of key information. The fused features are processed by the global context fusion module (GCFM) to improve the small target detection capability in complex backgrounds. Finally, the prediction head refines the target query and generates accurate class labels and bounding boxes.

[0021] Step 1, construct a dual-branch attention convolution module that integrates convolution and attention mechanism, and through a global-local feature collaborative enhancement mechanism to enhance the boundary perception ability.

[0022] Due to the discontinuity and complexity of edge features in map data, it has become a core challenge in target detection to accurately extract boundary features while ensuring the integrity of the boundary. To this end, the present application proposes a feature enhancement module that integrates convolution and attention mechanism, namely the dual-branch attention convolution module, as shown in Figure 3 By constructing a local-global feature collaborative enhancement mechanism, this module aims to model the fine expression of complex map edge patterns, thereby improving the integrity and robustness of boundary features. Specifically, after channel compression, the input features will be sent to independent branches for modeling and fusion.

[0023] In the embodiment of the present application, step 1 includes: The global correlation modeling path: firstly, 1x1 and 3x3 convolution operations are adopted on the input features to generate query Q, key K and value V tensors; subsequently, an attention map is calculated through a weighted filtering strategy to realize the interaction between local features and enhance the selectivity and position sensitivity of the features; then, weighted multiplication is performed on the attention map and the value V to obtain the final output feature map , combined with dynamic convolution, to optimize the modeling effect of the edge; this process not only strengthens the edge features of the target, but also establishes potential connections between the broken edges, thereby improving the continuity of the boundary. Among them, The expression is: (1); Wherein, X represents the input feature map, Q, K and V are 3x3 depth separable convolution kernels respectively; is a scaling factor, and =C; wherein H represents the height of the feature map, W represents the width of the feature map, and C represents the number of channels of the feature map; the final output feature map contains local texture information and cross-region feature correlation information. Local channel interaction path: firstly, the input features are compressed and reconstructed through 1x1 convolution operation to enhance the compactness of the feature representation; subsequently, the input features are divided into N subgroups along the channel dimension, and each subgroup extracts fine-grained local information through depth separable convolution, thereby strengthening the modeling ability of local feature patterns; then, in order to enhance the information interaction between channels, channel rearrangement is introduced to rearrange the channel index, and dynamic convolution and random dropout are combined; Finally, the results of the global correlation modeling path and the local channel interaction path are fused after element-wise addition and summation to obtain the output feature.

[0024] The attention mechanism plays a key role in enhancing edge representation, but traditional methods are difficult to adapt to complex boundary shapes and suppress background noise, often leading to incomplete or unstable edge extraction. The invention constructs a dual-branch parallel module that integrates convolution and attention mechanism, also known as a dual-branch attention convolution module. This module can enhance boundary perception ability through global-local feature collaborative enhancement mechanism, where the global branch is used to model long-distance dependencies to enhance overall boundary perception ability; the local branch optimizes local features through channel rearrangement, dynamic convolution and random dropout to improve detail representation ability and model robustness. The synergistic effect of global-local dual branches enables the model to stably extract complete edge features in complex boundary and high noise scenes, ensuring accurate identification of boundary regions.

[0025] The attention mechanism plays a key role in enhancing edge representation, but traditional methods are difficult to adapt to complex boundary shapes and suppress background noise, often leading to incomplete or unstable edge extraction. The invention constructs a dual-branch parallel module that integrates convolution and attention mechanism, also known as a dual-branch attention convolution module. This module can enhance boundary perception ability through global-local feature collaborative enhancement mechanism, where the global branch is used to model long-distance dependencies to enhance overall boundary perception ability; the local branch optimizes local features through channel rearrangement, dynamic convolution and random dropout to improve detail representation ability and model robustness. The synergistic effect of global-local dual branches enables the model to stably extract complete edge features in complex boundary and high noise scenes, ensuring accurate identification of boundary regions. ​

[0026] Step 2, according to step 1, a multi-path feature aggregation mechanism is designed, and multi-scale feature representation is dynamically reconstructed through bidirectional path interaction and adaptive weighted fusion.

[0027] The map data usually has multiple resolutions, resulting in complex and diverse feature distribution at different scales. The existing feature fusion method has certain limitations in dealing with complex background and scale changes in the map, thereby affecting the positioning accuracy of the model. Therefore, the present application proposes a multi-path feature aggregation mechanism, as shown in Figure 2 The module dynamically reconstructs multi-scale feature representation through bidirectional path interaction and adaptive weighted fusion (AWF), realizes more in-depth and accurate cross-scale information integration, thereby effectively improving the expression ability of the model to different scale features and retaining detailed information.

[0028] In the embodiment of the present application, step 2 includes: The multi-path feature aggregation mechanism transmits deep semantic information to shallow features through expression (2) to enhance semantic perception ability, and the form of expression (2) is: (2); Wherein, represents the output feature map after fusion of the i-th layer; represents the feature of the i-th layer; and represent weights for adjusting the contribution proportion of up-sampling features and current layer features respectively; function represents up-sampling the feature of the i+1-th layer to match the resolution of the i-th layer feature; At the same time, the feature information is propagated back through the bottom-up path to feed back the fine-grained information in the shallow feature to the deep feature, thereby enhancing the expression ability of the deep feature to the detailed information, and the expression of the process is: (3); Wherein, function represents down-sampling the feature of the i-1-th layer to match the resolution of the i-th layer feature; In the part of bidirectional path interaction, the multi-path feature aggregation mechanism introduces adaptive weighted fusion; through expression (4), the weights from two different scale features are dynamically adjusted to realize feature fusion, and finally the fusion output O is obtained, and the form of expression (4) is: (4); Wherein, represents the feature map of the first scale path; represents the feature map of the second scale path; denotes a constant, and takes a value of 1x10 -4 ; In the embodiment of the present application, the three-stage backbone network is used to extract features to obtain multiple different scale features, and the expression (4) is used to dynamically adjust the weights of two different scale features from the multiple different scale features each time.

[0029] In the embodiment of the present application, to prevent information loss, the multi-path feature aggregation mechanism adopts a cross-scale feature connection strategy, so that the features at the same level can be directly transmitted to the final output layer. This design not only ensures the semantic integrity in the multi-scale feature fusion process, but also retains the fine local details, especially when dealing with complex boundaries (such as broken national boundary lines).

[0030] The multi-path feature aggregation mechanism proposed in the present application not only breaks through the limitations of traditional methods in multi-scale target detection, but also effectively suppresses the information loss and redundancy problems in complex scenes, significantly enhancing the model's understanding ability and positioning accuracy for targets of different scales.

[0031] Single-scale feature extraction is difficult to handle targets of different sizes and shapes at the same time, which limits the performance of the model in the target recognition task. In addition, the single-scale method also has shortcomings in capturing the overall structure of large targets, resulting in a decrease in positioning accuracy. The present application designs a multi-path feature aggregation mechanism to enhance the recursive connection of cross-scale features through bidirectional path interaction and adaptive weighted fusion. This module uses bidirectional path interaction to achieve more efficient feature fusion, and introduces a cascade interaction design combining adaptive weighted fusion and Cross Stage Partial Block (CSP) to ensure the sufficiency and effectiveness of feature aggregation. With this design, the multi-path feature aggregation mechanism not only effectively improves the model's perception ability for targets of different scales, but also significantly improves the positioning accuracy of the targets.

[0032] Step 3, according to step 2, a global context fusion module is constructed to balance global information and local information.

[0033] The existing model still has shortcomings in small target feature extraction, and it is difficult to effectively distinguish islands from background textures in low-contrast sea scenes. At the same time, the model lacks the ability to model the overall outline of the island, resulting in incomplete representation of its shape and boundary. In order to solve the above problems, the present application proposes a global context fusion module, as shown in Figure 4 which models features at different levels through a multi-branch structure to achieve comprehensive extraction and fusion of global information and local details.

[0034] In the embodiment of the present application, step 3 includes: The global context fusion module models features of different levels through a multi-branch structure. First, the global context fusion module combines global average pooling GAP and global maximum pooling GMP to extract global information of input features through expression (5), which is in the form of expression (5): (5); wherein, , ; H represents the height of the feature map, W represents the width of the feature map, represents the feature value at the spatial position (i, j); and respectively represent the weights of linear transformation of the features extracted by global average pooling and global maximum pooling; represents the global distribution feature extracted by global average pooling, represents the significant region feature extracted by global maximum pooling; after weighted summation of the two through the attention weight generated by the activation function Softmax, the global feature output is obtained; Secondly, the global context fusion module introduces a self-attention mechanism, generates query Q and key K through 1×1 convolution, and performs nonlinear mapping through an activation function to improve the feature expression capability, and at the same time, the value V is directly obtained from the input feature; then, the query Q, the key K and the value V are multiplied element by element to generate the enhanced global feature representation, and the process is expressed as expression (6): (6); wherein, represents the global enhanced feature output generated by the self-attention mechanism; , are 1×1 convolution kernels of the query Q and the key K, respectively; Finally, the processed by 1×1 convolution is fused with for prediction.

[0035] Through feature complementation and dynamic focusing of the self-attention mechanism, this module effectively enhances the recognition and representation ability of small targets, thereby improving the detection accuracy of the model in complex scenes.

[0036] The existing target detection model usually uses multiple downsampling operations in the backbone network to expand the receptive field. However, this way may compress or lose the position and detail information of small targets in the low layer feature map, especially when the small target only occupies a few pixels, which is prone to miss detection. To solve this problem, the present application constructs a global context fusion module to enhance the feature representation of small targets and reduce the miss detection rate. The global context fusion module adopts a multi-branch attention mechanism, combines global average pooling and global maximum pooling, and extracts global and local statistical information to improve the integrity of the features. In addition, the global context fusion module introduces a self-attention mechanism to optimize the spatial distribution of the features, guide the model to focus on the key areas around the small target, improve the discriminability of the target, and effectively suppress the background interference. By fusing the outputs of different branches, the global context fusion module balances the global and local information, preserves the details and textures of small targets in complex backgrounds, thereby improving the recognition accuracy and reducing the detection error.

[0037] Step 4, according to step 3, refining the target query through the prediction head, and generating the category label and the bounding box.

[0038] The technical scheme provided by the present application includes constructing a double-branch attention convolution module that fuses convolution and attention mechanism, and enhancing the boundary perception ability through global-local feature cooperative enhancement mechanism; designing a multi-path feature aggregation mechanism to dynamically reconstruct multi-scale feature representation through bidirectional path interaction and adaptive weighted fusion; constructing a global context fusion module to balance global information and local information; refining the target query through the prediction head, and generating the category label and the bounding box. The method enhances the overall boundary perception ability, ensures the sufficiency and effectiveness of feature aggregation, improves the positioning accuracy of the target and the accuracy of the border area recognition.

[0039] The steps of the embodiment of the present application can be executed by an electronic device. The electronic device includes but is not limited to a tablet computer, a portable PC, a desktop computer, etc.

[0040] The embodiment of the present application provides a computer readable storage medium, which includes a stored program, wherein when the program runs, the computer readable storage medium controls the electronic device where the computer readable storage medium is located to execute the embodiment of the above-mentioned detection method for problem map boundary enhancement and small target perception.

[0041] Figure 5 A schematic diagram of an electronic device provided by the embodiment of the present application is shown in Figure 5As shown, the electronic device 21 includes a processor 211, a memory 212, and a computer program 213 stored in the memory 212 and executable on the processor 211, which, when executed by the processor 211, implements the method for boundary enhancement and small target perception detection of problem map in the embodiments. For the sake of brevity and conciseness, the detailed working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be described herein.

[0042] The electronic device 21 includes, but is not limited to, the processor 211 and the memory 212. Those skilled in the art can understand that the electronic device 21 can further include other components, such as an input / output device, a network access device, a bus, etc. Figure 5 The electronic device 21 is only an example and does not constitute a limitation on the electronic device 21, and can include more or fewer components than the illustration, or combine certain components, or different components, for example, the electronic device can also include an input / output device, a network access device, a bus, etc.

[0043] The processor 211 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0044] The memory 212 can be an internal storage unit of the electronic device 21, such as a hard disk or a memory of the electronic device 21. The memory 212 can also be an external storage device of the electronic device 21, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 21. Further, the memory 212 can include both the internal storage unit and the external storage device of the electronic device 21. The memory 212 is used to store computer programs and other programs and data required by the network device. The memory 212 can also be used to temporarily store data that has been output or will be output.

[0045] Those skilled in the art can clearly understand that, for the sake of brevity and conciseness, the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be described herein.

[0046] The above merely provides the preferred embodiment of the present application, and is not used to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of protection of the present application.

Claims

1. A detection method for boundary enhancement and small target perception of problem map, characterized in that, The method comprises: Step 1, constructing a double-branch attention convolution module fusing convolution and attention mechanism, and enhancing boundary perception ability through global-local feature collaborative enhancement mechanism; Step 2, according to step 1, designing a multi-path feature aggregation mechanism, dynamically reconstructing multi-scale feature representation through bidirectional path interaction and adaptive weighted fusion; Step 3, according to step 2, constructing a global context fusion module to balance global information and local information; Step 4, according to step 3, refining the target query through the prediction head, and generating class label and bounding box.

2. The method of claim 1, wherein, The step 1 comprises: The global correlation modeling path comprises the following steps: firstly, 1x1 and 3x3 convolution operations are adopted on input features to generate query Q, key K and value V tensors; subsequently, an attention map is calculated through a weighted filtering strategy to realize interaction between local features; and then, weighted product operation is performed on the attention map and the value V to obtain a final output feature map , combined with dynamic convolution, to optimize the modeling effect of edges; wherein, The expression is: （1）； wherein X e represents an input feature map, e are 3x3 depthwise separable convolution kernels for query Q, key K and value V respectively; is a scaling factor, and takes =C; wherein H represents a feature map height, W represents a feature map width, and C represents a feature map channel number; The local channel interaction path: first, the input feature is compressed and reconstructed through 1×1 convolution operation; then, the input feature is divided into N subgroups along the channel dimension, and each subgroup extracts fine-grained local information through depth separable convolution; then, channel rearrangement is introduced to rearrange the channel index, and dynamic convolution and random dropout are used; Finally, the results of the global correlation modeling path and the local channel interaction path are summed element by element and fused to obtain the output feature.

3. The method of claim 1, wherein, The step 2 comprises: The multi-path feature aggregation mechanism transmits deep semantic information to shallow features through expression (2) to enhance semantic perception ability, and the form of expression (2) is: （2）； wherein, denotes the output feature map after fusion of the i-th layer; denotes the feature of the i-th layer; and denotes the weight for adjusting the contribution ratio of the up-sampled feature and the feature of the current layer, respectively; the function denotes up-sampling the feature of the i+1-th layer to match the resolution of the i-th layer feature; At the same time, the feature information is propagated back through the bottom-up path to feed back the fine-grained information in the shallow feature to the deep feature, and the process is expressed as: （3）； where the function denotes down-sampling the features of the i-1th layer to match the resolution of the i-th layer features; In the part of bidirectional path interaction, the multi-path feature aggregation mechanism introduces adaptive weighted fusion; through expression (4), the weights from two different scale features are dynamically adjusted to realize feature fusion, and finally the fusion output O is obtained, and the form of expression (4) is: （4）； wherein, represents a feature map of the first scale path; represents a feature map of the second scale path; represents a constant, taking a value of 1 x 10 -4 .

4. The method of claim 1, wherein, The step 3 comprises: The global context fusion module models different levels of features through a multi-branch structure, first, the global context fusion module combines global average pooling GAP and global maximum pooling GMP to extract global information of the input feature through expression (5), and the form of expression (5) is: （5）； wherein, , ; H represents the feature map height, W represents the feature map width, represents the feature value at the spatial position (i, j); and respectively represent the weights of linear transformation of the features extracted by the global average pooling and the global maximum pooling; represents the global distribution feature extracted by the global average pooling, represents the salient region feature extracted by the global maximum pooling; both are weighted and summed after being weighted by the attention weight generated by the activation function Softmax to obtain the global feature output ; Secondly, the global context fusion module introduces a self-attention mechanism, generates query Q, key K through 1×1 convolution, and performs nonlinear mapping through an activation function to improve feature expression ability, and at the same time, the value V is directly obtained from the input feature; then, the query Q, the key K and the value V are multiplied element by element to generate enhanced global feature representation, and the process is expressed as: （6）； wherein, represents a global enhanced feature output generated by a self-attention mechanism; , are 1x1 convolution kernels for the query Q and the key K, respectively. Finally, the 1x1 convolution processed with fusion for prediction.

5. A computer readable storage medium, characterized in that, The computer readable storage medium comprises a stored program, wherein when the program runs, the computer readable storage medium controls the device where the computer readable storage medium is located to execute the detection method for boundary enhancement and small target perception of problem map in any one of claims 1-4.

6. An electronic device, comprising: Comprise: One or more processors; Memory; And one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs comprise instructions, which when executed by the device, cause the device to execute the detection method for boundary enhancement and small target perception of problem map in any one of claims 1-4.

Images