Object-oriented change target detection method and system based on improved YOLO

Abstract

The invention discloses an object-oriented change target detection method and system based on improved YOLO. The method comprises the steps of collecting image data of a target detection area at different moments, registering the image data at two different moments, generating an image pair of the target detection area, preprocessing the image pair, inputting the preprocessed image pair into an improved YOLOV8 model, respectively performing interested feature extraction on an input image by using two input branches of a shared backbone, and obtaining a feature extraction result of the target detection area; using a DCAM attention module in an improved YOLOV8 model to perform enhanced fusion on the feature maps of interest extracted by the two branches to obtain a difference feature map of fusion features and original features; performing multi-scale fusion processing on the obtained difference feature map by using the check in the improved YOLOV8 model; identifying and positioning different targets by using a detection head in the improved YOLOV8 model, and outputting an image which marks interested difference targets between the image pairs in a bounding box form; according to the invention, the speed and robustness of change detection can be improved while high-precision detection of object changes can be realized.

Description

Technical Field

[0002] The present application relates to the technical field of target detection, and specifically to an object-oriented variable target detection method and system based on improved YOLO. Background Art

[0003] Change detection technology has been widely used in the field of remote sensing image analysis, especially in construction progress monitoring, urban planning and development. Traditional change detection methods rely on manual feature extraction and complex image processing algorithms. In recent years, with the development of deep learning technology, especially the maturity of target detection models, change detection technology has gradually developed towards automation and intelligence. These new methods not only improve detection accuracy, but also greatly reduce the need for manual intervention, thereby improving work efficiency and accuracy.

[0004] Among the existing change detection technologies, commonly used methods include pixel-level change detection, object-level change detection, and scene-level change detection. Pixel-level change detection generates a difference map by comparing each pixel in each pair of images, and is suitable for applications that require detailed change information. Object-level change detection focuses on changes in specific semantic objects, such as the addition or removal of buildings, and usually uses bounding boxes or masks to mark the changed targets. Scene-level change detection pays more attention to changes in the overall environment, such as urban expansion or land use changes. In order to improve detection accuracy and efficiency, researchers usually adopt a combination of multiple technical means, such as image registration, feature extraction, attention mechanism, etc.

[0005] However, existing change detection methods still have some shortcomings in practical applications. For example, traditional pixel-based methods are easily affected by factors such as lighting and shadows, resulting in high false detection and missed detection rates. Although object-level methods can better capture specific changing targets, in complex backgrounds, especially in changing natural environments, object-level methods still need to be improved in terms of feature extraction and target recognition accuracy. In addition, existing methods consume a lot of computing resources when processing large-scale data sets, making it difficult to achieve real-time or near-real-time detection requirements. Therefore, how to achieve high-precision detection of object changes while improving the speed and robustness of change detection has become a key issue that needs to be solved urgently. Summary of the invention

[0006] In order to achieve high-precision detection of object changes while improving the speed and robustness of change detection, the present application provides an object-oriented change target detection method and system based on improved YOLO.

[0007] In the first aspect, an object-oriented change target detection method based on improved YOLO includes: Collect image data of the target detection area at different times, align the image data at two different times, and generate an image pair of the target detection area; Preprocessing the image pairs of the target detection area; The preprocessed image pair of the target detection area is input into the improved YOLOV8 model, and the two input branches sharing the backbone in the improved YOLOV8 model are used to extract the features of interest from one image in the input image pair respectively. The DCAM attention module in the improved YOLOV8 model is used to enhance and fuse the feature maps of interest extracted by the two branches to obtain the difference feature map between the fused features and the original features; the neck in the improved YOLOV8 model is used to perform multi-scale fusion processing on the obtained difference feature map; the detection head in the improved YOLOV8 model is used to identify and locate the targets with differences, and the images with the difference targets of interest between the image pairs are output in the form of bounding boxes; the structural improvements of the improved YOLO model include: the output of the model is designed as two branches, each branch shares the backbone, and the DCAM attention module is introduced in the neck part of the YOLO V8 model.

[0008] By adopting the above scheme, on the basis of the traditional YOLOV8 model, a dual-branch input is designed to extract features from the registered images. Through the design of a shared backbone, redundant calculations are reduced and the model efficiency is improved. The DCAM attention module is introduced to enhance the expressiveness of the feature map, so that the model can better capture the key features of target changes. Through multi-scale fusion processing, the model's detection ability for targets of different scales is further improved, effectively improving the accuracy and robustness of object change detection, and adapting to the change detection needs in various complex scenarios.

[0009] Preferably, the structural improvement of the improved YOLO V8 model further includes: introducing a pre-processing module ShuffleNet into the YOLO V8 model structure, using ShuffleNet to perform scene classification on the input image of the target detection area, and obtaining a scene classification label; the scene classification includes office scenes and outdoor scenes; The process of enhancing and fusing the feature maps of interest extracted by the two branches using the DCAM attention module in the improved YOLOV8 model also includes: querying the matching attention weight modulation parameters from the first scene prior knowledge base according to the acquired scene classification label, modulating the attention weights of the DCAM according to the queried attention weight modulation parameters, and enhancing and fusing the feature maps of interest extracted by the two branches according to the modulated attention weights; the first scene prior knowledge base stores the preset attention weight adjustment parameters corresponding to each scene, and the preset attention weight adjustment parameters are determined according to the attention adjustment parameters corresponding to the optimal target detection feedback results under the conditions of different preset attention weight adjustment parameters for different scenes.

[0010] By adopting the above scheme, a lightweight network is set as the front module to obtain image scene classification, and the DCAM attention weight is modulated according to the scene classification label, so that the model can better adapt to the change detection requirements in specific scenes when processing different scenes, thereby improving the detection performance.

[0011] Preferably, the multi-scale fusion processing of the acquired difference feature map using the neck in the improved YOLOV8 model also includes: According to the acquired scene classification label, the matching multi-scale fusion weight modulation parameters are queried from the second scene prior knowledge base, the multi-scale fusion weight parameters in the neck are adjusted according to the queried multi-scale fusion weight modulation parameters, and the difference feature map is multi-scale fused according to the modulated multi-scale fusion weights; the second scene prior knowledge base stores the preset multi-scale fusion parameters corresponding to each scene, and the preset multi-scale fusion parameters are determined according to the multi-scale fusion parameters corresponding to the optimal target detection feedback results under the conditions of different preset multi-scale fusion parameters for different scenes.

[0012] By adopting the above scheme, the weight parameters of multi-scale fusion are matched according to different scenes and applied to the adjustment of the weight parameters of multi-scale fusion in the neck, which can better capture and fuse the features of different scales, reduce the detection errors caused by scene changes, and improve the overall performance of target detection.

[0013] Preferably, the step of using the detection head in the improved YOLOV8 model to identify and locate targets with differences, and outputting images with bounding boxes marking the targets of interest between the image pairs also includes: According to the acquired scene classification label, the modulation parameter is adjusted by querying the matching confidence threshold from the third scene prior knowledge base, the confidence threshold in the detection head is adjusted according to the queried confidence modulation parameter, and the difference feature map is subjected to difference target detection according to the modulated confidence threshold; the third scene prior knowledge base stores the preset confidence threshold corresponding to each scene match, and the preset confidence threshold is determined according to the confidence threshold corresponding to the optimal target detection feedback result under different confidence threshold conditions in different historical scenes.

[0014] By adopting the above solution, the parameters are adjusted according to the confidence threshold of the scene classification label query match, the confidence threshold of the detection head is dynamically adjusted, the performance of the detection head is optimized, false detections and missed detections are reduced, and the detection effect is improved.

[0015] Preferably, the preprocessing includes: analyzing the light intensity and distribution of the images of the target detection area at different times, using image processing technology to perform light normalization processing on the images at two times, and making the light intensity and distribution of the images of the target detection area at different times after the light normalization processing consistent.

[0016] By adopting the above scheme, the image is subjected to light normalization processing, so that the light intensity and distribution of the processed image are consistent, the pseudo changes caused by light changes are eliminated, and the accuracy and robustness of change detection are improved.

[0017] Preferably, it also includes: Before outputting an image with the difference target of interest between the image pair marked in the form of a bounding box, for the image with the difference target of interest between the image pair marked in the form of a bounding box, image light information is determined, and original light information is queried from a light mapping table, and light of the image with the difference target of interest between the image pair marked in the form of a bounding box is restored according to the queried original light information; the light mapping table stores the original light information before the original image is subjected to light normalization processing and the pre-processed light information associated with the mapping, and the light information includes: light intensity and distribution.

[0018] By adopting the above scheme, the image that has been subjected to light normalization processing is restored in the output stage to ensure that the output image retains the true visual effect under the original lighting conditions, thereby improving the accuracy and reliability of the change detection results.

[0019] Preferably, the shared backbone structure includes: 5 convolutional layers and 4 pooling layers.

[0020] By adopting the above solution, the shared backbone is simplified and the model's efficiency in detecting target changes is improved.

[0021] In a second aspect, the present application provides an object-oriented change target detection system based on improved YOLO, including: an image pair acquisition module, used to collect image data of a target detection area at different times, align the image data at two different times, and generate an image pair of the target detection area; An image pair preprocessing module, used for preprocessing the image pair of the target detection area; The image-to-object change detection module is used to input the preprocessed image pair into the improved YOLOV8 model, and use the two input branches sharing the backbone in the improved YOLOV8 model to extract the features of interest from one image in the input image pair respectively, and use the DCAM attention module in the improved YOLOV8 model to enhance and fuse the feature maps of interest extracted by the two branches to obtain the difference feature map between the fused features and the original features; use the neck in the improved YOLOV8 model to perform multi-scale fusion processing on the obtained difference feature map; use the detection head in the improved YOLOV8 model to identify and locate the target with differences, and output the image with the target of interest difference between the image pairs marked in the form of a bounding box; wherein, the structural improvement of the improved YOLO model includes: the output of the model is designed as two branches, each branch shares the backbone, and the DCAM attention module is introduced in the neck part of the YOLOV8 model.

[0022] By adopting the above scheme, a dual-branch structure is designed to extract features from image pairs. The shared backbone and DCAM attention modules in the improved YOLOV8 model are used to enhance the capabilities of feature extraction and fusion, improve the accuracy and robustness of detection, and output the difference targets of interest between image pairs annotated in the form of bounding boxes through the detection head, thus achieving efficient object-oriented change target detection.

[0023] In a third aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the method as described above.

[0024] In a fourth aspect, the present application provides a computer device, comprising a memory, a processor, and a program stored and executable on the memory, wherein the program implements the steps of the above method when executed by the processor.

[0025] In summary, this application has the following beneficial effects: 1. Based on the YOLOV8 model, a dual-branch structure is designed and the backbone is shared to extract features from the input image pair. Combined with the introduced DCAM attention module, the features of the two images can be effectively extracted and fused, significantly improving the accuracy and robustness of target change detection. 2. The pre-processing module ShuffleNet is introduced to perform scene classification, and the attention weight, multi-scale fusion weight and confidence threshold are dynamically adjusted in combination with multiple scene prior knowledge bases, achieving adaptive optimization in different scenarios and further improving the accuracy and reliability of detection; 3. Through light normalization processing and light restoration operations, the problems of false detection and missed detection caused by light changes are eliminated, the consistency and stability of the detection results are ensured, and the practicality and reliability of the entire system are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a flowchart of the object-oriented change target detection method based on improved YOLO described in a specific embodiment; Figure 2 It is a schematic diagram of a 6-channel input model structure in the object-oriented changing target detection method based on improved YOLO described in a specific embodiment; Figure 3 It is a schematic diagram of introducing a DCMA module in the object-oriented change target detection method based on improved YOLO described in a specific embodiment; Figure 4 A schematic diagram of the results obtained by using the object-oriented changing target detection method based on the improved YOLO described in the specific embodiment; Figure 4 (a) A schematic diagram of indoor results obtained by using the object-oriented variable target detection method based on improved YOLO described in a specific embodiment; Figure 4 (b) A schematic diagram of outdoor results obtained by using the object-oriented changing target detection method based on the improved YOLO described in the specific embodiment; Figure 5 It is a structural diagram of the object-oriented changing target detection system based on improved YOLO described in a specific embodiment. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0028] like Figure 1 As shown, the embodiment of the present application discloses an object-oriented change target detection method based on improved YOLO, including: S1. Collect image data of the target detection area at different times to generate image pairs of the target detection area.

[0029] Specifically, the image data of the target detection area is collected by using a camera device, and the collected image data of the target area can be framed, and the image data of every two consecutive frames can be aligned in real time according to the time sequence to generate several image pairs of the target monitoring area; or according to user needs, the image data frames of the target detection area at any two moments of pre-detection of the target detection area can be used to generate an image pair of the target monitoring area.

[0030] Among them, the registration of image data at two different moments can adopt a feature-based registration method, a grayscale-based registration method, a transform domain-based registration method, and a deep learning-based registration method. In this embodiment, a feature matching algorithm, such as SIFT, SURF, etc., is used to extract key points in the image and match them, and then the RANSAC algorithm is used to remove the wrong matching points, and finally the affine transformation or homography transformation is used to align the images.

[0031] S2. Preprocess the image of the target detection area.

[0032] Specifically, the preprocessing includes image denoising, image enhancement, and size normalization processing.

[0033] S3. Input the preprocessed image pairs into the improved YOLOV8 model, and output an image with the difference of interest between the image pairs marked in the form of bounding boxes.

[0034] Specifically, the improved YOLOV8 model is based on the YOLOV8 model with partial structural improvements, and the main structural improvements include: The input of the model adopts a 6-channel output structure commonly used in the prior art, such as Figure 2 As shown in the figure, a feature extraction operation is performed on the input image pair to obtain the feature maps corresponding to the two images in the image pair respectively; on this basis, the input structure is designed as a dual-branch structure, and the two branch structures share a backbone. The backbone structure includes 5 convolutional layers and 4 convolutional layers. Batch normalization (Batch Normalization) and activation function (ReLU) are added between each convolutional layer and pooling layer of the backbone to improve the convergence speed and generalization ability of the model. A convolution operation is performed on one image data in the input image pair with a convolutional structure of 1 CNN+BN+relu and 4 (CNN+BN+relu)×2; 4 pooling layers are interspersed in the 5 convolutional layers, and pooling operations are performed on the feature data extracted by each convolutional layer.

[0035] The DCAM attention module is introduced in the neck part of the YOLO V8 model. The DCAM attention module includes a spatial attention mechanism and a channel attention mechanism. The DCAM attention module is used to learn and assign attention weights. By weighting the specific spatial positions in the feature map of each branch, the most critical areas for the task are highlighted to achieve feature enhancement. Then, the features in the feature maps extracted by the two branches are weighted and fused to obtain a fused feature map. The fused feature map is compared with the two original feature maps to determine the difference features whose feature differences are greater than the preset differences, and generate a difference feature map. Among them, the specific attention weight distribution of DCAM is determined through model training.

[0036] The improved YOLOV8 model training can be performed by training historical image pairs annotated with the classification and location of the difference target of interest to the user; the input of the model is an image pair, and the output is an image annotated with the difference target of interest between the image pairs in the form of a bounding box, wherein the bounding box is located in the image that is later in time order.

[0037] like Figure 3 As shown in the figure, the process of obtaining the output annotated interesting difference targets by using the improved YOLOV8 model includes: using the two input branches of the shared backbone to extract the interesting features of one image in the input image pair respectively, using the DCAM attention module in the improved YOLOV8 model to enhance and fuse the interesting feature maps extracted by the two branches, and obtain the difference feature map between the fused features and the original features, specifically, enhancing and fusion the interesting feature maps of the same scale under multiple different scales extracted by the two branches, and then generating difference feature maps of different scales; using the neck in the improved YOLOV8 model to perform multi-scale fusion processing on the obtained difference feature maps; using the detection head in the improved YOLOV8 model to identify and locate the targets with differences, specifically, the detection head can use the anchor box mechanism to preliminarily screen the candidate targets through the pre-set anchor box, and then remove the overlapping candidate boxes through the non-maximum suppression (NMS) algorithm, and output the image with the interesting difference targets between the image pairs annotated in the form of bounding boxes.

[0038] Using the method described in the above embodiment, Figure 4 As shown in Figure 2, the improved YOLOV8 model can be used to detect changes in multiple categories of objects in image pairs. While maintaining high-precision detection, the speed and robustness of object change detection are improved. The test results are shown in Figure 2. Figure 4 (a) with Figure 4 (b).

[0039] In a specific embodiment, in order to further improve the speed and robustness of object change detection and adapt to object change detection in complex and changing scenes, the method further includes: Taking into account the different importance of the same target in different scenarios, in a specific or typical scenario, the importance of some targets needs to be adjusted accordingly. In order to adapt to changing scenarios, the parameters of these targets can be adjusted in advance to improve the detection accuracy and robustness of the model.

[0040] Specifically, a pre-processing module ShuffleNet is introduced into the YOLO V8 model structure, and ShuffleNet is used to perform scene classification on the image of the input target detection area to obtain scene classification labels, thereby providing effective prior information for subsequent feature extraction and target detection. In this embodiment, the scene classification includes office scenes and outdoor scenes.

[0041] The process of enhancing and fusing the feature maps of interest extracted by the two branches using the DCAM attention module in the improved YOLOV8 model also includes: According to the acquired scene classification label, the matching attention weight modulation parameter is queried from the first scene prior knowledge base. Wherein, the first scene prior knowledge base stores the preset attention weight adjustment parameters corresponding to each scene, such as: the office scene pays more attention to the changes of indoor objects, while in the outdoor scene, it may pay more attention to the changes of terrain and vegetation, and the optimal attention weight ratio of the more concerned changing target (specific target) is set accordingly, and the preset attention weight ratio is preset as the preset attention weight adjustment parameter, such as: the preset first attention weight adjustment parameter corresponding to the office scene, and the preset second attention weight adjustment parameter corresponding to the outdoor scene; the preset attention weight adjustment parameter is determined according to the attention adjustment parameter corresponding to the optimal target detection feedback result under the conditions of different preset attention weight adjustment parameters in different scenes. Wherein, the optimal target detection feedback result refers to the target detection feedback result with the greatest similarity with the actual result during the target detection process of the user simulation test.

[0042] The attention weight of DCAM is modulated according to the queried attention weight modulation parameter; the feature maps of interest extracted by the two branches are enhanced and fused according to the modulated attention weight; By using the method described in the above embodiment, the attention weight can be dynamically adjusted in different scenarios to improve the detection accuracy and robustness of the model.

[0043] In a specific embodiment, in order to further improve the speed and robustness of object change detection and adapt to the requirements of object change detection in complex and changing scenes, the method further includes: The multi-scale fusion processing of the acquired difference feature map by using the neck in the improved YOLOV8 model also includes: querying the matching multi-scale fusion weight modulation parameters from the second scene prior knowledge base according to the acquired scene classification label. Wherein, the second scene prior knowledge base stores the preset multi-scale fusion parameters corresponding to each scene, such as: more small-scale features may be required, and in outdoor scenes, more large-scale features may be required, and the feature weight ratio of the fusion of different scale features is set accordingly, and the feature weight ratio of the fusion of different scale features is set as the preset multi-scale fusion weight modulation parameter, such as: the preset first multi-scale fusion weight modulation parameter corresponding to the office scene, and the preset second multi-scale fusion weight modulation parameter corresponding to the outdoor scene; the preset multi-scale fusion parameter is determined according to the multi-scale fusion parameter corresponding to the optimal target detection feedback result under the conditions of different preset multi-scale fusion parameters in different scenes.

[0044] The weight parameters of multi-scale fusion in the neck are adjusted according to the queried multi-scale fusion weight modulation parameters, and the multi-scale fusion of the difference feature map is performed according to the modulated multi-scale fusion weights.

[0045] By using the method described in the above embodiment, the multi-scale fusion weights can be dynamically adjusted in different scenarios to improve the detection accuracy and robustness of the model.

[0046] In a specific embodiment, in order to improve the accuracy and reliability of detection, the method further comprises: The method of using the detection head in the improved YOLOV8 model to identify and locate targets with differences, and outputting images with bounding boxes marking the targets of interest between the image pairs, further includes: The modulation parameters are adjusted by querying the matching confidence threshold from the third scene prior knowledge base according to the acquired scene classification label. The third scene prior knowledge base stores the preset confidence thresholds for each scene, such as: outdoor scenes may require a lower threshold due to the complex background, while office scenes may be suitable for higher thresholds due to the relatively stable environment. Correspondingly, a preset first confidence threshold corresponding to the outdoor scene and a preset second confidence threshold corresponding to the office scene are set, and the first confidence threshold is less than the second confidence threshold; specifically, the preset confidence threshold is determined according to the confidence threshold corresponding to the optimal target detection feedback result under different confidence threshold conditions in different historical scenes.

[0047] The confidence threshold in the detection head is adjusted according to the queried confidence modulation parameter, and the difference target detection is performed on the difference feature map according to the modulated confidence threshold.

[0048] By using the method described in the above embodiment, the confidence threshold can be dynamically adjusted in different scenarios to improve the accuracy and reliability of model detection.

[0049] In a specific embodiment, considering the influence of light on image feature extraction and detection, in order to avoid the influence of light and improve the reliability and accuracy of the detection results, the method further includes: The preprocessing includes: analyzing the light intensity and distribution of the image of the target detection area at different times, which can be specifically achieved by calculating the brightness histogram, contrast and other parameters of the image; using image processing techniques, such as: histogram equalization, contrast stretching, etc., to perform light normalization processing on the images at two times, and making the light intensity and distribution of the image of the target detection area at different times after the light normalization processing consistent.

[0050] And in the process of preprocessing, the original light information before the light normalization processing of the original image and the preprocessed light information associated with the mapping are stored in the light mapping table as a pair of mapping relationships, and the light information includes: light intensity and distribution.

[0051] In addition, in order to make the visual effect of the detection result more natural, the light of the remote sensing image with the difference target of interest between the remote sensing image pair marked in the form of a bounding box is restored using a light mapping table. Specifically, the method further includes: before outputting the image with the difference target of interest between the image pair marked in the form of a bounding box, for the image with the difference target of interest between the image pair marked in the form of a bounding box, using image analysis technology to determine the image light information, and querying the original light information from the light mapping table, and restoring the light of the image with the difference target of interest between the image pair marked in the form of a bounding box according to the queried original light information.

[0052] like Figure 5 As shown, an object-oriented change target detection system based on improved YOLO includes: An image pair acquisition module 101 is used to collect image data of a target detection area at different times, align the image data at two different times, and generate an image pair of the target detection area; An image pair preprocessing module 102, used for preprocessing the image pair of the target detection area; The image-to-object change detection module 103 is used to input the preprocessed image pair of the target detection area into the improved YOLOV8 model, use the two input branches that share the backbone in the improved YOLOV8 model to extract the features of interest from one image in the input image pair respectively, use the DCAM attention module in the improved YOLOV8 model to enhance and fuse the feature maps of interest extracted by the two branches, and obtain the difference feature map between the fused features and the original features; use the neck in the improved YOLOV8 model to perform multi-scale fusion processing on the obtained difference feature map; use the detection head in the improved YOLOV8 model to identify and locate the target with differences, and output an image with the target of interest difference between the image pairs marked in the form of a bounding box; wherein the structural improvement of the improved YOLO model includes: the output of the model is designed as two branches, each branch shares the backbone, and the DCAM attention module is introduced in the neck part of the YOLO V8 model.

[0053] The embodiment of the present application also discloses a computer-readable storage medium.

[0054] Specifically, the computer-readable storage medium stores a computer program that can be loaded by a processor and executes the above-mentioned object-oriented change target detection method based on the improved YOLO. The computer-readable storage medium includes, for example: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0055] The embodiment of the present application also discloses a computer device.

[0056] Specifically, the computer device includes a memory and a processor, and the memory stores a computer program that can be loaded by the processor and execute the above-mentioned object-oriented change target detection method based on improved YOLO.

[0057] The above are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Any feature disclosed in this specification (including the abstract and drawings), unless otherwise stated, can be replaced by other equivalent or alternative features with similar purposes. That is, unless otherwise stated, each feature is only an example of a series of equivalent or similar features.

Claims

1. An object-oriented change target detection method based on improved YOLO, characterized in that: include: Collect image data of the target detection area at different times, align the image data at two different times, and generate an image pair of the target detection area; Preprocessing the image pairs of the target detection area; The preprocessed image pair of the target detection area is input into the improved YOLOV8 model, and the two input branches of the shared backbone in the improved YOLOV8 model are used to extract the features of interest from one image in the input image pair respectively. The DCAM attention module in the improved YOLOV8 model is used to enhance and fuse the feature maps of interest extracted by the two branches to obtain the difference feature map between the fused features and the original features. The neck in the improved YOLOV8 model is used to perform multi-scale fusion processing on the acquired difference feature maps; The detection head in the improved YOLOV8 model is used to identify and locate targets with differences, and images with the different targets of interest between image pairs are output in the form of bounding boxes. The structural improvements of the improved YOLO model include: the output of the model is designed as two branches, each branch shares the backbone, and the DCAM attention module is introduced in the neck part of the YOLO V8 model.

2. According to the object-oriented change target detection method based on improved YOLO according to claim 1, it is characterized in that: The structural improvement of the improved YOLO V8 model also includes: introducing a pre-processing module ShuffleNet into the YOLO V8 model structure, using ShuffleNet to perform scene classification on the input image of the target detection area, and obtaining a scene classification label; the scene classification includes office scenes and outdoor scenes; The process of enhancing and fusing the feature maps of interest extracted by the two branches using the DCAM attention module in the improved YOLOV8 model also includes: querying the matching attention weight modulation parameters from the first scene prior knowledge base according to the acquired scene classification label, modulating the attention weights of the DCAM according to the queried attention weight modulation parameters, and enhancing and fusing the feature maps of interest extracted by the two branches according to the modulated attention weights; the first scene prior knowledge base stores the preset attention weight adjustment parameters corresponding to each scene, and the preset attention weight adjustment parameters are determined according to the attention adjustment parameters corresponding to the optimal target detection feedback results under the conditions of different preset attention weight adjustment parameters for different scenes.

3. According to claim 2, the object-oriented change target detection method based on improved YOLO is characterized in that: The multi-scale fusion processing of the acquired difference feature map using the neck in the improved YOLOV8 model also includes: According to the acquired scene classification label, the matching multi-scale fusion weight modulation parameters are queried from the second scene prior knowledge base, the multi-scale fusion weight parameters in the neck are adjusted according to the queried multi-scale fusion weight modulation parameters, and the difference feature map is multi-scale fused according to the modulated multi-scale fusion weights; the second scene prior knowledge base stores the preset multi-scale fusion parameters corresponding to each scene, and the preset multi-scale fusion parameters are determined according to the multi-scale fusion parameters corresponding to the optimal target detection feedback results under the conditions of different preset multi-scale fusion parameters for different scenes.

4. According to the object-oriented change target detection method based on improved YOLO according to claim 1, it is characterized in that: The method of using the detection head in the improved YOLOV8 model to identify and locate targets with differences, and outputting images with bounding boxes marking the targets of interest between the image pairs, further includes: According to the acquired scene classification label, the modulation parameter is adjusted by querying the matching confidence threshold from the third scene prior knowledge base, the confidence threshold in the detection head is adjusted according to the queried confidence modulation parameter, and the difference feature map is subjected to difference target detection according to the modulated confidence threshold; the third scene prior knowledge base stores the preset confidence threshold corresponding to each scene match, and the preset confidence threshold is determined according to the confidence threshold corresponding to the optimal target detection feedback result under different confidence threshold conditions in different historical scenes.

5. According to the object-oriented change target detection method based on improved YOLO according to claim 1, it is characterized in that: The preprocessing includes: analyzing the light intensity and distribution of the images of the target detection area at different times, using image processing technology to perform light normalization processing on the images at two times, and making the light intensity and distribution of the images of the target detection area at different times after the light normalization processing consistent.

6. According to claim 5, the object-oriented change target detection method based on improved YOLO is characterized in that: Also includes: Before outputting the image in which the difference target of interest between the image pair is annotated in the form of a bounding box, for the image in which the difference target of interest between the image pair is annotated in the form of a bounding box, image light information is determined, and original light information is queried from a light mapping table, and light of the image in which the difference target of interest between the image pair is annotated in the form of a bounding box is restored according to the queried original light information; The light mapping table stores original light information before light normalization processing of the original image and pre-processed light information associated with the mapping, and the light information includes: light intensity and distribution.

7. According to claim 1, the object-oriented change target detection method based on improved YOLO is characterized in that: The shared backbone structure includes 5 convolutional layers and 4 pooling layers.

8. An object-oriented change target detection system based on improved YOLO, characterized in that: include: An image pair acquisition module is used to collect image data of the target detection area at different times, align the image data at two different times, and generate an image pair of the target detection area; An image pair preprocessing module, used for preprocessing the image pair of the target detection area; The image-to-object change detection module is used to input the preprocessed image pair of the target detection area into the improved YOLOV8 model, and use the two input branches of the shared backbone in the improved YOLOV8 model to extract the features of interest from one image in the input image pair respectively, and use the DCAM attention module in the improved YOLOV8 model to enhance and fuse the feature maps of interest extracted by the two branches to obtain the difference feature map between the fused features and the original features; The neck in the improved YOLOV8 model is used to perform multi-scale fusion processing on the acquired difference feature maps; The detection head in the improved YOLOV8 model is used to identify and locate targets with differences, and images with the different targets of interest between image pairs are output in the form of bounding boxes. The structural improvements of the improved YOLO model include: the output of the model is designed as two branches, each branch shares the backbone, and the DCAM attention module is introduced in the neck part of the YOLO V8 model.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

10. A computer device, characterized in that: The computer device comprises a memory, a processor and a program stored and executable on the memory, and the program implements the steps of the method according to any one of claims 1 to 7 when executed by the processor.

Images