A method and apparatus for detecting camouflaged targets based on dual-frequency branching

Abstract

This disclosure relates to a method, apparatus, electronic device, and storage medium for detecting camouflaged targets based on dual-frequency branching. The method includes: performing frequency feature extraction processing on an input image to obtain a high-frequency feature group and a low-frequency feature group, wherein the high-frequency feature group includes at least two high-frequency feature maps, and the low-frequency feature group includes at least two low-frequency feature maps; performing a first fusion processing on the high-frequency feature group to obtain a first fused feature; and performing a second fusion processing on the low-frequency feature group to obtain a second fused feature; obtaining a third fused feature based on the first fused feature and the second fused feature; and using the third fused feature to detect camouflaged target objects in the input image. This disclosure can effectively improve target detection accuracy.

Description

Technical Field

[0001] This disclosure relates to image processing technology, and in particular to a method and apparatus for detecting camouflaged targets, electronic equipment, and storage medium. Background Technology

[0002] Camouflaged object detection (COD) is an important research area in computer vision, aiming to automatically identify and locate target objects in complex natural scenes that are highly similar to the background in terms of color, texture, or structural features. These targets typically possess significant concealment and are widely used in applications such as natural ecological monitoring, military reconnaissance, medical image analysis, and industrial inspection, placing high demands on the feature representation and discrimination capabilities of detection algorithms. Most existing COD methods are based on deep learning frameworks, using structures such as convolutional neural networks or visual Transformers to extract multi-layer features from the input image and employing multi-scale feature fusion, contextual modeling, or attention mechanisms to enhance the perception of target regions. However, because camouflaged targets and backgrounds exhibit high similarity in the spatial domain, relying solely on spatial domain features is often insufficient to effectively distinguish between targets and backgrounds, easily leading to missed or false detections. Summary of the Invention

[0003] This disclosure proposes a method, apparatus, electronic device, and storage medium for detecting camouflaged targets based on dual-frequency branching, which addresses the problem of low detection rate of camouflaged targets in the prior art.

[0004] According to a first aspect of this disclosure, a method for detecting camouflaged targets based on dual-frequency branching is provided, comprising: performing frequency feature extraction processing on an input image to obtain a high-frequency feature group and a low-frequency feature group, wherein the high-frequency feature group includes at least two high-frequency feature maps and the low-frequency feature group includes at least two low-frequency feature maps; performing a first fusion processing on the high-frequency feature group to obtain a first fusion feature, and performing a second fusion processing on the low-frequency feature group to obtain a second fusion feature; obtaining a third fusion feature based on the first fusion feature and the second fusion feature; and using the third fusion feature to detect camouflaged target objects in the input image.

[0005] In some possible implementations, performing frequency feature extraction processing on the input image to obtain a high-frequency feature group and a low-frequency feature group includes: performing Fourier transform or wavelet transform on the input image to obtain the high-frequency feature group and the low-frequency feature group.

[0006] In some possible implementations, a second fusion process is performed on the low-frequency feature group to obtain a second fused feature, including: performing connection processing in the height and width directions on the low-frequency feature maps in the low-frequency feature group to obtain a first low-frequency connection feature and a second low-frequency connection feature; performing feature encoding processing on the first low-frequency connection feature and the second low-frequency connection feature to obtain a first encoded feature and a second encoded feature; and fusing the first encoded feature and the second encoded feature to obtain the second fused feature.

[0007] In some possible implementations, the feature encoding process includes: performing a two-branch process on the input connection features; wherein the first branch process includes: performing a linear transformation and activation process on the connection features; the second branch process includes: performing a linear transformation, feature dimensionality reduction, activation process, and state space transformation process on the connection features; and performing a product process and a linear transformation on the two features obtained from the two-branch process to obtain the encoded features corresponding to the connection features.

[0008] In some possible implementations, performing a first fusion process on the high-frequency feature group to obtain a first fused feature includes: performing connection fusion processing on the high-frequency feature map of the high-frequency feature group in the height direction, width direction, and diagonal direction respectively to obtain high-frequency connection features; performing attention processing on the high-frequency connection features to obtain high-frequency attention features; and performing feature transformation processing on the high-frequency attention features to obtain the first fused feature.

[0009] In some possible implementations, connection fusion processing is performed on the high-frequency feature maps of the high-frequency feature group in the height direction, width direction, and diagonal direction to obtain high-frequency connection features. This includes: performing connection processing on the high-frequency feature maps of the high-frequency feature group in the height direction, width direction, and diagonal direction to obtain a first high-frequency connection feature, a second high-frequency connection feature, and a third high-frequency connection feature; and performing channel direction connection processing on the first high-frequency connection feature, the second high-frequency connection feature, and the third high-frequency connection feature to obtain high-frequency connection features.

[0010] In some possible implementations, attention processing is performed on the high-frequency connectivity features to obtain high-frequency attention features, including: performing recombination processing on the high-frequency connectivity features to obtain recombination features; performing three branch processing on the recombination features to obtain a first branch feature, a second branch feature, and a third branch feature; using the product of the second branch feature and the third branch feature to obtain a first branch product feature; and using the product of the first branch feature and the first branch product feature to obtain high-frequency attention features.

[0011] According to a second aspect of this disclosure, a disguised target detection apparatus is provided, comprising: a frequency processing module for performing frequency feature extraction processing on an input image to obtain a high-frequency feature group and a low-frequency feature group; a first fusion module for performing a first fusion processing on the high-frequency feature group to obtain a first fusion feature, and performing a second fusion processing on the low-frequency feature group to obtain a second fusion feature; a second fusion module for obtaining a third fusion feature based on the first fusion feature and the second fusion feature; and a detection module for detecting a disguised target object in the input image using the third fusion feature.

[0012] According to a third aspect of this disclosure, an electronic device is provided, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the instructions stored in the memory to perform the method according to any one of the first aspects.

[0013] According to a fourth aspect of this disclosure, a computer-readable storage medium is provided that stores computer program instructions thereon, which, when executed by a processor, implement the method described in any one of the first aspects.

[0014] This disclosure provides a dual-frequency branch-based camouflage target detection method, which constructs an overall detection process based on the ideas of frequency feature decomposition and differential feature fusion. First, frequency feature extraction processing is performed on the input camouflage target image, dividing the image features into a high-frequency feature group and a low-frequency feature group to represent the detailed texture information and overall structural semantic information of the image, respectively. Then, different feature processing branches are set for the high-frequency and low-frequency feature groups. For the high-frequency feature group, high-frequency features are connected and fused in different spatial directions, and high-frequency detail features are selectively enhanced using an attention mechanism to obtain a first fused feature used to characterize the edges and subtle differences of the camouflage target. For the low-frequency feature group, low-frequency features are connected in the height and width directions, and low-frequency structural features are deeply modeled using feature encoding and state space transformation modeling to obtain a second fused feature reflecting the overall contour and semantic information of the target. Based on this, the first and second fused features are further fused, fully utilizing the complementary relationship between high-frequency and low-frequency features to generate a third fused feature containing both detailed and structural information. Finally, based on the third fusion feature, camouflaged target object detection is performed, and the localization and prediction results of the camouflaged target object in the input image are output. Through the above method, this embodiment of the disclosure achieves effective decomposition and differential modeling of frequency domain features, enhancing the model's ability to perceive subtle differences between camouflaged targets and complex backgrounds, thereby improving the accuracy and robustness of camouflaged target object detection.

[0015] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure.

[0016] Other features and aspects of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the specification, serve to illustrate the technical solutions of this disclosure.

[0018] Figure 1 This is a flowchart of the camouflage target detection method in the embodiments of this disclosure; Figure 2 This is a schematic diagram of the model structure of the camouflage target detection method in the embodiments of this disclosure. Detailed Implementation

[0019] Various exemplary embodiments, features, and aspects of this disclosure will now be described in detail with reference to the accompanying drawings. The same reference numerals in the drawings denote elements that have the same or similar functions. Although various aspects of the embodiments are shown in the drawings, they are not necessarily drawn to scale unless specifically indicated otherwise.

[0020] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.

[0021] In this document, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0022] Furthermore, to better illustrate this disclosure, numerous specific details are set forth in the following detailed description. Those skilled in the art will understand that this disclosure can be practiced without certain specific details. In some instances, methods, means, components, and circuits well known to those skilled in the art have not been described in detail in order to highlight the main points of this disclosure.

[0023] The method disclosed herein can be executed by an image processing device, such as a terminal device, a server, or other processing device. The terminal device can be a user equipment (UE), mobile device, user terminal, terminal, cellular phone, cordless phone, personal digital assistant (PDA), handheld device, computing device, in-vehicle device, wearable device, etc. In some possible implementations, the method can be implemented by a processor calling computer-readable instructions stored in memory.

[0024] It is understood that the various method embodiments mentioned above in this disclosure can be combined with each other to form combined embodiments without violating the principle and logic. Due to space limitations, this disclosure will not elaborate further.

[0025] Figure 1 This is a flowchart of the camouflaged target object detection method in the embodiments of this disclosure; as follows: Figure 1 As shown, the method for detecting camouflaged target objects includes: S10: Perform frequency feature extraction processing on the input image to obtain high-frequency feature groups and low-frequency feature groups; In some possible implementations, a color image of the camouflaged object can be obtained using an image acquisition device, which is the image in the example of this disclosure. Specifically, the input image in the embodiment of this disclosure includes the camouflaged object to be detected by this disclosure. The camouflaged object can be any species, object, or medical detection target, for example, it can be a rabbit, but this is not a specific limitation of the embodiment of this disclosure.

[0026] In this embodiment, frequency feature extraction processing can be performed on the input image. By performing frequency domain analysis on the image, the image features are divided into a high-frequency feature group and a low-frequency feature group. The high-frequency feature group includes at least two high-frequency feature maps, and the low-frequency feature group includes at least two low-frequency feature maps. The high-frequency feature group is used to characterize high-frequency information related to edge variations and texture details in the image, while the low-frequency feature group is used to characterize the overall structure, regional distribution, and global semantic information in the image. By separating the frequency features of the input image, different frequency components can be modeled and utilized separately in subsequent processing, thereby providing basic feature input for subsequent differentiated fusion processing of high-frequency and low-frequency features.

[0027] S20: Perform a first fusion process on the high-frequency feature group to obtain a first fused feature, and perform a second fusion process on the low-frequency feature group to obtain a second fused feature; In this embodiment, a first fusion process can be performed on the high-frequency feature group to integrate and enhance the detailed information contained in the high-frequency features, thereby obtaining a first fused feature. Simultaneously, a second fusion process can be performed on the low-frequency feature group to model and fuse the overall structural and semantic information contained in the low-frequency features, thereby obtaining a second fused feature. By performing targeted fusion processes on the high-frequency and low-frequency feature groups respectively, different frequency features can be effectively expressed according to their information attributes, and complementary feature representations are provided for subsequent further fusion of high-frequency and low-frequency features.

[0028] S30: A third fusion feature is obtained based on the first fusion feature and the second fusion feature; In this embodiment, feature fusion processing can be performed based on the first fusion feature and the second fusion feature to comprehensively utilize the detailed information contained in the high-frequency features and the structural semantic information contained in the low-frequency features to obtain the third fusion feature. By further integrating the fusion features of different frequencies, the complementary information between the high-frequency features and the low-frequency features can be synergistically expressed, thereby forming a comprehensive feature representation that takes into account both local details and overall structure, providing a more discriminative feature basis for the subsequent detection of disguised target objects.

[0029] S40: Detect the disguised target object in the input image using the third fusion feature.

[0030] In this embodiment, camouflaged target object detection processing can be performed based on the third fusion feature. By performing target discrimination and localization analysis on the third fusion feature, detection results indicating the location of camouflaged target objects in the input image are generated. Since the third fusion feature simultaneously contains high-frequency detail information and low-frequency structural semantic information, it can effectively enhance the representation ability of subtle differences between camouflaged targets and the background, thereby improving the accuracy and stability of camouflaged target object detection.

[0031] Based on the above configuration, this embodiment integrates the high-frequency and low-frequency feature groups of the input image into the same camouflage target detection framework for processing. By fusing and modeling the high-frequency features, the edge details and local differences of the camouflage target in the image can be effectively represented. By fusing and modeling the low-frequency features, the overall structure and semantic information of the camouflage target can be stably depicted. Furthermore, by further fusing the high-frequency and low-frequency fusion features, the synergistic expression of detail and structural information is achieved, ultimately used for the detection of camouflage targets in the input image. Through this method, the ability to perceive subtle differences between camouflage targets and complex backgrounds can be effectively enhanced, thereby improving the detection accuracy and robustness of camouflage targets.

[0032] The embodiments of this disclosure will now be described in detail with reference to the accompanying drawings. First, an input image can be obtained in the embodiments of this disclosure. The input image is a color image including a disguised target object. In the embodiments of this disclosure, the method of obtaining the input image may include at least one of the following methods: A) Directly use an image acquisition device to acquire color images including camouflaged target objects; wherein, the image acquisition device can be a color camera, video recording device or other device with image acquisition capabilities, and the specific type of image acquisition device is not limited in this disclosure embodiment.

[0033] B) Transmitting and receiving color images including camouflaged target objects via electronic devices; in this embodiment of the disclosure, color images transmitted by other electronic devices can be received via wired and / or wireless communication, and the communication method is not a specific limitation of this disclosure.

[0034] C) Reading a color image including a disguised target object from a storage medium or database; in this embodiment of the disclosure, a pre-stored color image can be read from a local storage device or server according to a received read instruction, and this disclosure does not specifically limit this.

[0035] It should be noted that the input images in the embodiments of this disclosure may come from the same scene or different scenes, and the type, shape and background environment of the disguised target object in the image can be set according to the actual application requirements. Those skilled in the art can select the corresponding image source according to the specific application scenario, and no specific limitation is made here.

[0036] After obtaining a color image including a disguised target object, disguised target object detection processing can be performed on the color image. Specifically, in this embodiment of the disclosure, the color image can be used as input and fed into a pre-built disguised target object detection model for processing, so as to realize the identification and location of the disguised target object in the image; The camouflaged target detection model in this embodiment is constructed based on frequency feature analysis and includes multiple feature processing paths targeting different frequency features. The detection model first performs frequency feature extraction processing on the input color image, dividing the image features into high-frequency feature groups and low-frequency feature groups; then, it performs targeted feature fusion and modeling processing on the high-frequency and low-frequency feature groups respectively, thereby obtaining a fused feature representation for camouflaged target detection. Through the above method, this embodiment can effectively detect camouflaged target objects by simultaneously utilizing the detailed texture information and overall structural semantic information in the image, given an input image. Those skilled in the art can adjust the number, resolution, or source of the input image according to actual application needs, but this is not intended as a specific limitation of this disclosure.

[0037] In some possible implementations, Fourier transform or wavelet transform can be performed on the input image to obtain the high-frequency feature group and the low-frequency feature group.

[0038] This disclosure allows for the execution of wavelet transform or Fourier transform on the input image to obtain high-frequency feature groups and low-frequency feature groups. The high-frequency feature groups contain detailed information about the image, while the low-frequency feature groups contain global information. It's important to note that in related technologies, backbone networks using multi-scale feature extraction processes obtain features at different scales. The high and low-frequency characteristics corresponding to these multi-scale features are implicit frequency representations derived from changes in spatial resolution and receptive field expansion, rather than strict signal frequency decomposition. Wavelet transform and Fourier transform, on the other hand, achieve explicit frequency decoupling of features through predefined filters, clearly separating low-frequency structural components from high-frequency detailed components at the signal level. In other words, unlike the high and low-frequency features extracted by multi-scale feature extraction networks, the frequency domain feature method used in this disclosure obtains true frequency domain information, while the high and low-frequency features extracted by the backbone network are feature information obtained based on spatial resolution.

[0039] Figure 2 This is a schematic diagram of the model structure of the camouflaged target detection method in this embodiment. This embodiment performs a first fusion process on the high-frequency feature group, including connecting and fusing the high-frequency feature maps along the height, width, and diagonal directions, and then applying an attention mechanism to obtain high-frequency fused features. For the low-frequency feature group, a second fusion process is performed, first connecting the low-frequency feature maps along the height and width directions, and then encoding the connected features through a two-branch process to finally obtain low-frequency fused features. Then, based on the high-frequency and low-frequency fused features, a third fusion feature is obtained, which combines image details and global information. Finally, the third fusion feature is used to detect camouflaged target objects in the input image. This invention, through the fusion processing of multi-band features, can significantly improve the accuracy and robustness of camouflaged target object detection.

[0040] Performing a second fusion process on the low-frequency feature group to obtain a second fused feature includes: performing connection processing in the height and width directions on the low-frequency feature maps in the low-frequency feature group to obtain a first low-frequency connection feature and a second low-frequency connection feature; performing feature encoding processing on the first low-frequency connection feature and the second low-frequency connection feature to obtain a first encoded feature and a second encoded feature; and fusing the first encoded feature and the second encoded feature to obtain the second fused feature.

[0041] This disclosure embodiment can first perform connection processing on the low-frequency feature map within the low-frequency features, respectively, in the height and width directions. Specifically, the low-frequency features... It contains at least two low-frequency feature maps. To effectively fuse low-frequency feature information, these feature maps are concatenated. In the height direction, the rows of each low-frequency feature map are first concatenated to form the first low-frequency concatenation feature. In the width direction, the columns of each low-frequency feature map are further concatenated to obtain the second low-frequency connectivity feature. This connection processing allows the low-frequency feature map to be expanded in spatial dimensions, thereby preserving more image information and enhancing the effect of subsequent processing.

[0042] Subsequently, feature encoding processing can be performed on the first low-frequency connection feature and the second low-frequency connection feature respectively to obtain the first encoded feature and the second encoded feature. The feature encoding processing includes: performing a two-branch process on the input connection feature; wherein the first branch process includes: performing a linear transformation and activation processing on the connection feature; the second branch process includes: performing a linear transformation, feature dimensionality reduction, activation processing, and state space transformation processing on the connection feature; performing a product process and a linear transformation on the two features obtained from the two-branch process to obtain the encoded feature corresponding to the connection feature. The input connection feature is the first low-frequency connection feature and the second low-frequency connection feature. For ease of description, the following explanation uses the input connection feature as an example and will not elaborate further.

[0043] In this embodiment, after completing the connection processing of the low-frequency feature map, the obtained connection features are flattened to convert the feature map into one-dimensional data (B, H×W×C) for subsequent linear transformation and feature encoding. Next, feature encoding processing is performed on the first and second low-frequency connection features. Feature encoding includes performing a two-branch process on each connection feature. In the first branch, a linear transformation is first performed on the first low-frequency connection feature to obtain feature F, and then a nonlinear activation function is applied to this feature. For example, with Sigmoid, the activated feature A is the first encoded feature:

[0044] Where W and b are the weights and biases, respectively, and are learnable parameters.

[0045] Furthermore, in the second branch, the first low-frequency connection feature L is first linearly transformed to obtain the linearly transformed feature F. Then, a feature dimensionality reduction convolution operation is applied, using a convolution kernel size of 1×1, or alternatively 3×3, which is not specifically limited in this disclosure. Next, a nonlinear activation function is used to obtain nonlinear features, followed by a state space transformation to obtain the second encoded feature. The state space transformation process uses an SSM model, and the state equation and output equation used are set by those skilled in the art according to their needs, and are not specifically limited here. Through state space transformation, accurate representation of features in long-distance dimensions can be achieved, thereby improving model performance. Finally, the final state space transformed feature is obtained, which is the second encoded feature.

[0046] The linear transformations of the first and second branches use different weight parameters, which are learned during training. Further, a linear transformation is performed after multiplying the first and second encoded features to obtain the final first branch output features. Similarly, the second low-frequency connection features undergo the same encoding process to obtain the second branch output features. After feature encoding is complete, especially after multiple transformations (e.g., state-space transformation), the one-dimensional first branch output features and the first branch output features need to be restored to dimensional feature maps with the original input image, and then directly concatenated to obtain the final second fused feature.

[0047] This concatenation method preserves the independent information of each encoded feature and combines them to form a richer feature representation. In some optional implementations, the second fused feature can be further optimized, for example, by performing CBR (convolution, batch normalization, and ReLU activation) processing on the second fused feature. The CBR module extracts local features through convolution operations, improves training stability through batch normalization, and provides non-linear transformation through activation functions. To further enhance feature representation capabilities and avoid the gradient vanishing problem, residual connections are introduced into feature processing. In residual connections, low-frequency features are directly combined... The features are then added to the CBR-processed features to obtain the final optimized second fused features. These steps, through multi-level feature processing, nonlinear transformation, and information fusion, significantly improve the robustness and accuracy of camouflaged target detection.

[0048] In some possible implementations, performing a first fusion process on the high-frequency feature group to obtain a first fused feature includes: performing connection fusion processing on the high-frequency feature map of the high-frequency feature group in the height direction, width direction, and diagonal direction respectively to obtain high-frequency connection features; performing attention processing on the high-frequency connection features to obtain high-frequency attention features; and performing feature transformation processing on the high-frequency attention features to obtain the first fused feature.

[0049] This embodiment of the disclosure targets a high-frequency feature group extracted through frequency domain transformation. First, it performs connection and fusion processing on multiple high-frequency feature maps contained within the high-frequency feature group in the height, width, and diagonal directions, respectively, thereby aggregating multi-directional texture detail information to obtain high-frequency connection features. Since high-frequency features contain more detailed relationships, this embodiment of the disclosure introduces more spatial connection methods in high-frequency feature fusion, further enriching the high-frequency feature information. Specifically, connection processing can be performed on the high-frequency feature maps of the high-frequency feature group in the height, width, and diagonal directions, respectively, to obtain a first high-frequency connection feature, a second high-frequency connection feature, and a third high-frequency connection feature; channel direction connection processing is then performed on the first, second, and third high-frequency connection features to obtain the high-frequency connection features.

[0050] In some possible implementations, after obtaining the high-frequency connection features, the embodiments of this disclosure can further perform fusion optimization on the first fusion feature and the high-frequency connection features to obtain optimized high-frequency connection features. The fusion optimization method includes any of the following: ① performing channel-direction connection processing on the first fusion feature and the high-frequency connection features to obtain optimized high-frequency connection features; ② calculating the distance between the first fusion feature and the high-frequency fusion connection features; if the distance is less than a distance threshold, using the first fusion feature as the optimized high-frequency feature; if the distance is greater than the distance threshold, performing channel-direction connection processing on the first fusion feature and the high-frequency connection features to obtain optimized high-frequency connection features. After obtaining optimized high-frequency connection features, the optimized high-frequency connection features are used as high-frequency connection features for subsequent attention processing. The distance can be Euclidean distance or other requirements set by those skilled in the art.

[0051] Next, attention processing is performed on the high-frequency connectivity features to obtain high-frequency attention features. Specifically, firstly, recombination processing is performed on the high-frequency connectivity features to obtain recombination features; then, three-branch processing is performed on the recombination features to obtain first-branch features, second-branch features, and third-branch features; the product of the second-branch features and the third-branch features is used to obtain the first-branch product features; and the product of the first-branch features and the first-branch product features is used to obtain the high-frequency attention features.

[0052] The reorganization process for the high-frequency connectivity features includes: performing block processing on the high-frequency connectivity features in the width and height directions to obtain multiple block features; and performing connection processing on the block features in the height direction to obtain the reorganized features. The number of blocks can be set according to requirements, such as 2×2, or other numbers; this disclosure does not specifically limit this. This block processing strategy aims to achieve local attention enhancement: compared to global attention, which easily allows the camouflaged region to be submerged by background information, local attention allows the model to focus more on subtle differences within small regions, amplifying detailed textures and making it easier to detect edge changes of camouflaged objects; at the same time, block operations can reduce the computational complexity of the attention mechanism. Subsequently, the high-frequency connectivity features are input into the attention mechanism module for attention processing; during this process, the feature data undergoes dimensional reorganization, capturing short-distance dependencies and local statistical distribution characteristics between features, ultimately obtaining the first fusion feature for subsequent fusion calculations.

[0053] Upon obtaining the reconstructed features, multi-branch processing is performed on them. Within the attention processing unit, this embodiment improves the classic query, key, and value interaction logic by performing multi-level transformations on the features through statistical branches to enhance discriminability. Specifically, after performing reconstruction processing on the input feature stream, this embodiment generates Query, Key, and Value through three parallel branches. Specifically, Query is the first branch, Key is the second branch, and Value is the third branch.

[0054] The first and second branch processing methods respectively include feature centering, feature squarening, channel normalization, and height*width normalization. The purpose of feature centering is to highlight the "subtle differences" between the camouflage region and the background by eliminating the mean background. In this processing, the third branch is not centered to maintain the integrity of its original expression, while the second branch and its related paths are centered, which amplifies feature fluctuations and compresses flat background areas, thereby making subtle textures and edge changes clearer. In this embodiment, a feature square transformation is performed on the centered features. The square operation can achieve a contrast stretching effect of "larger values ​​are larger, smaller values ​​are smaller," so that the model pays more attention to texture boundaries, detail changes, and the outline of the camouflage, enhancing the response of significant features while suppressing weak background features, resulting in stronger recognition contrast. To further improve the robustness of the model in complex backgrounds, this embodiment performs double normalization processing on the channel dimension (C) and spatial dimension (H×W) after feature squarening. Among them, normalization along the channel dimension is used to constrain the activation amplitude of each semantic channel (such as texture, color, and edge channels), suppressing the contributions of different channels to the same order of magnitude, and preventing certain high-energy channels or noise channels from dominating the correlation calculation; normalization along the spatial dimension balances the energy distribution at each location in the image, making the contribution of each pixel location comparable, and effectively avoiding strong texture backgrounds or large areas from masking small camouflaged targets.

[0055] Furthermore, the product of the second branch features and the third branch features is used to obtain the first branch product features; the product of the first branch features and the first branch product features is used to obtain the high-frequency attention features. Given the high-frequency attention features, feature transformation processing is performed on them to obtain the first fused features. The feature transformation includes transforming the feature dimensions; through block processing in the width and height directions, the features are restored to the dimensions of the high-frequency features within the high-frequency feature group, thus obtaining the first fused features.

[0056] Based on the above configuration, high-frequency features are fused to obtain effective high-frequency features from different perspectives, thereby optimizing the algorithm accuracy.

[0057] Having obtained the first and second fusion features, a third fusion feature is further obtained by connecting the first and second fusion features along the channel direction. For example, the first and second fusion features can be added together to obtain the third fusion feature; or the first and second fusion features can be connected along the channel direction and then convolved to obtain the third fusion feature. The location of the disguised target object can then be obtained through the third fusion feature. Detecting the disguised target object in the input image using the third fusion feature includes: directly performing activation processing on the third fusion feature to obtain the location information of the disguised target object, wherein the location of the disguised target object is where the feature value is greater than 0.5 in the activated feature. Alternatively, the location of the disguised target object can be obtained by performing convolution processing on the third fusion feature followed by activation processing. This disclosure does not specifically limit this.

[0058] In related technologies, different frequency features are often simply superimposed or directly spliced ​​together, failing to fully exploit the differences in expression and information distribution between high-frequency and low-frequency features. Furthermore, high-frequency and low-frequency features differ significantly in spatial structure, information density, and semantic level, requiring different modeling approaches. Some existing methods do not design differentiated feature fusion and modeling strategies for the characteristics of different frequency features, leading to difficulties in effectively coordinating complementary information between frequency features and affecting overall detection performance. Especially in complex backgrounds and low-contrast scenes, noise information in high-frequency features is easily amplified, while key information in low-frequency features may be weakened, further increasing detection difficulty. This disclosure proposes to rationally model and fuse high-frequency and low-frequency features separately, ensuring information complementarity while suppressing redundancy and noise interference, thereby improving the detection accuracy and robustness against camouflaged targets.

[0059] Compared with the prior art, the beneficial effects of this disclosure include the following aspects: 1. This invention achieves high-precision camouflage target capture based on frequency domain decoupling, overcoming the limitations of single spatial domain detection. The embodiments disclosed herein decompose the input image into high-frequency and low-frequency feature groups using wavelet transform, enabling parallel processing of the detailed texture and macroscopic semantics of the camouflage target from a frequency domain perspective. This method effectively solves the problem of blurred edges and difficulty in extraction caused by the high integration of color, texture, and background in the field of camouflage object detection, significantly improving the model's feature recognition capability in extreme camouflage environments.

[0060] 2. A State Space Transformation (SSM) architecture is introduced to achieve efficient modeling of long-distance semantic dependencies. In the low-frequency feature processing path, this embodiment employs an encoding module that includes state space transformation processing. Compared to traditional convolutional kernels, this architecture, through linear transformation, feature dimensionality reduction, and state space evolution, can acquire a wider receptive field and deeper semantic context information at a lower computational cost, effectively capturing the macroscopic logical relationship between the overall outline of the camouflaged target and the background environment, and improving the global consistency of the detection results.

[0061] 3. An improved attention mechanism based on local enhancement is proposed, significantly enhancing the sensitivity to detect subtle differences. Addressing the challenge of extremely small local differences in camouflaged targets, which are easily obscured by the background, this disclosure achieves precise magnification of subtle local textures by dividing high-frequency features into local regions and performing enhanced attention processing. Through improved Query-Key-Value interaction logic, combined with feature centering, square transformation, and dual normalization calibration of channels and space, the model can suppress strong background noise and highlight the weak edges of camouflaged areas. While maintaining the accuracy of dense prediction tasks, the computational complexity is significantly reduced through block-based computation.

[0062] 4. A multi-level, multi-dimensional feature fusion mechanism has been established to ensure the robustness and accuracy of the detection results. This disclosure employs a sophisticated fusion strategy to fuse attention-enhanced high-frequency detail features with low-frequency semantic features processed by state space transformation in multiple stages (such as first, second, and third fusion processes). This comprehensive processing flow, from local to global and from micro-texture to macro-semantics, enables the model to output accurate and complete camouflaged target detection results even in challenging scenarios such as varying target sizes, complex background textures, and extremely concealed camouflage areas.

[0063] Based on the above configuration, this embodiment provides a method for detecting camouflaged targets. This method constructs an overall detection process based on the idea of ​​frequency feature decomposition and differential feature fusion. First, frequency feature extraction is performed on the input camouflaged target image, dividing the image features into high-frequency feature groups and low-frequency feature groups to represent the detailed texture information and overall structural semantic information of the image, respectively. Then, different feature processing branches are set for the high-frequency and low-frequency feature groups. For the high-frequency feature group, high-frequency features are connected and fused in different spatial directions, and high-frequency detail features are selectively enhanced using an attention mechanism to obtain a first fused feature used to characterize the edges and subtle differences of the camouflaged target. For the low-frequency feature group, low-frequency features are connected in the height and width directions, and low-frequency structural features are deeply modeled using feature encoding and state space transformation modeling to obtain a second fused feature reflecting the overall contour and semantic information of the target. Based on this, the first and second fused features are further fused, fully utilizing the complementary relationship between high-frequency and low-frequency features to generate a third fused feature containing both detailed and structural information. Finally, based on the third fusion feature, camouflaged target object detection is performed, and the localization and prediction results of the camouflaged target object in the input image are output. Through the above method, this embodiment of the disclosure achieves effective decomposition and differential modeling of frequency domain features, enhancing the model's ability to perceive subtle differences between camouflaged targets and complex backgrounds, thereby improving the accuracy and robustness of camouflaged target object detection.

[0064] Those skilled in the art will understand that, in the above-described method of the specific implementation, the order in which each step is written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0065] In addition, this disclosure also provides a disguised object detection device, electronic device, computer-readable storage medium, and program, all of which can be used to implement any of the disguised object detection methods provided in this disclosure. The corresponding technical solutions and descriptions are described in the corresponding records in the method section and will not be repeated here.

[0066] The disguised object detection device includes: a frequency processing module for performing frequency feature extraction processing on the input image to obtain a high-frequency feature group and a low-frequency feature group; a first fusion module for performing a first fusion processing on the high-frequency feature group to obtain a first fusion feature, and performing a second fusion processing on the low-frequency feature group to obtain a second fusion feature; a second fusion module for obtaining a third fusion feature based on the first fusion feature and the second fusion feature; and a detection module for detecting disguised target objects in the input image using the third fusion feature.

[0067] In some embodiments, the apparatus provided in this disclosure may have functions or include modules that can be used to perform the methods described in the above method embodiments. Specific implementations can be referred to the descriptions in the above method embodiments, and for brevity, will not be repeated here. This disclosure also proposes a computer-readable storage medium storing computer program instructions that, when executed by a processor, implement the above methods. The computer-readable storage medium may be a non-volatile computer-readable storage medium.

[0068] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments.

Claims

1. A method for detecting camouflaged targets based on dual-frequency branching, characterized in that, include: Perform a Fourier transform or wavelet transform on the input image to obtain a high-frequency feature group and a low-frequency feature group; wherein the high-frequency feature group includes at least two high-frequency feature maps, and the low-frequency feature group includes at least two low-frequency feature maps; Performing a first fusion process on the high-frequency feature group to obtain a first fused feature includes: performing connection fusion processing on the high-frequency feature map of the high-frequency feature group in the height direction, width direction, and diagonal direction respectively to obtain high-frequency connection features; performing attention processing on the high-frequency connection features to obtain high-frequency attention features; and performing feature transformation processing on the high-frequency attention features to obtain the first fused feature. The second fusion process is performed on the low-frequency feature group to obtain a second fused feature, including: performing connection processing in the height and width directions on the low-frequency feature maps in the low-frequency feature group to obtain a first low-frequency connection feature and a second low-frequency connection feature; performing feature encoding processing on the first low-frequency connection feature and the second low-frequency connection feature to obtain a first encoded feature and a second encoded feature; and fusing the first encoded feature and the second encoded feature to obtain the second fused feature. The feature encoding process includes: performing a two-branch process on the input connection feature; wherein the first branch process includes: performing linear transformation and activation processing on the connection feature; the second branch process includes: performing linear transformation, feature dimensionality reduction, activation processing, and state space transformation processing on the connection feature; and performing product processing and linear transformation on the two features obtained from the two-branch process to obtain the encoded feature corresponding to the connection feature. A third fusion feature is obtained based on the first fusion feature and the second fusion feature; The third fusion feature is used to detect the disguised target object in the input image.

2. The camouflaged target detection method based on dual-frequency branching according to claim 1, characterized in that, Perform connection fusion processing on the high-frequency feature maps of the high-frequency feature group in the height direction, width direction, and diagonal direction respectively to obtain high-frequency connection features, including: The high-frequency feature maps of the high-frequency feature group are connected in the height direction, width direction and diagonal direction respectively to obtain the first high-frequency connection feature, the second high-frequency connection feature and the third high-frequency connection feature. Channel direction connection processing is performed on the first high-frequency connection feature, the second high-frequency connection feature, and the third high-frequency connection feature to obtain the high-frequency connection feature.

3. The camouflaged target detection method based on dual-frequency branching according to claim 2, characterized in that, Attention processing is performed on the high-frequency connectivity features to obtain high-frequency attention features, including: The high-frequency connection features are recombined to obtain recombined features; The recombined features are processed in three branches to obtain the first branch features, the second branch features, and the third branch features. The first branch product feature is obtained by multiplying the features of the second branch and the features of the third branch. The high-frequency attention features are obtained by multiplying the first branch features and the first branch product features.

4. A camouflaged target detection device, characterized in that, include: The frequency processing module is used to perform Fourier transform or wavelet transform on the input image to obtain a high-frequency feature group and a low-frequency feature group; wherein the high-frequency feature group includes at least two high-frequency feature maps, and the low-frequency feature group includes at least two low-frequency feature maps; A first fusion module is configured to perform a first fusion process on the high-frequency feature group to obtain a first fused feature, including: performing connection fusion processing on the high-frequency feature maps of the high-frequency feature group in the height direction, width direction, and diagonal direction respectively to obtain high-frequency connection features; performing attention processing on the high-frequency connection features to obtain high-frequency attention features; and performing feature transformation processing on the high-frequency attention features to obtain the first fused feature. A second fusion process is also configured to perform a second fusion process on the low-frequency feature group to obtain a second fused feature, including: performing connection processing on the low-frequency feature maps in the low-frequency feature group in the height and width directions respectively to obtain a first low-frequency connection feature and a second low-frequency feature. The connection features are processed by performing feature encoding on the first low-frequency connection feature and the second low-frequency connection feature respectively to obtain a first encoded feature and a second encoded feature; the first encoded feature and the second encoded feature are then fused to obtain a second fused feature; the feature encoding process includes performing a two-branch process on the input connection features; wherein the first branch process includes performing a linear transformation and activation process on the connection features; the second branch process includes performing a linear transformation, feature dimensionality reduction, activation process, and state space transformation process on the connection features; and performing a product process and a linear transformation on the two features obtained from the two-branch process to obtain the encoded feature corresponding to the connection features; The second fusion module is used to obtain a third fusion feature based on the first fusion feature and the second fusion feature; The detection module is used to detect disguised target objects in the input image using the third fusion feature.

5. An electronic device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to invoke instructions stored in the memory to execute the dual-frequency branch-based camouflage target detection method according to any one of claims 1 to 3.

6. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When the computer program instructions are executed by the processor, they implement the camouflage target detection method based on dual-frequency branch as described in any one of claims 1 to 3.

Images