A method for constructing a scene-to-image cross-domain mapping sample set driven by attribute features

Abstract

This specification discloses a method for constructing a scene-to-image cross-domain mapping sample set driven by attribute features, which belongs to the field of deep model compression technology. The method includes augmenting a basic sample set with an image feature transformation method to obtain a material library for sample synthesis; the basic sample set includes simulated target materials and real-shot environment materials; spatially aligning the actual target and the actual environment in the actual application scene to obtain the position information of the actual target in the environment coordinate system; selecting corresponding simulated target materials and real-shot environment materials from the material library based on the actual application scene; based on the position information of the actual target in the environment coordinate system, performing threshold segmentation on the selected simulated target materials and fusing them with the real-shot environment materials to obtain high-confidence synthetic samples, so as to solve the problem of obvious pixel block fragmentation and sample distortion in the synthetic sample area of the existing sample synthesis method, resulting in the inability to effectively synthesize the high-confidence sample set required for intelligent algorithm training.

Description

Technical Field

[0001] The present invention relates to the field of deep model compression technology, and in particular to a method for constructing a scene-to-image cross-domain mapping sample set driven by attribute features. Background Art

[0002] Currently, the main sources of sample sets required for intelligent perception algorithm training include real-life acquisition, simulation modeling, and sample synthesis. Limited by the diversity and complexity of application scenarios, obtaining large-scale real-life samples is costly. Simulation modeling can generate a large number of simulated samples, but there are often significant cross-domain differences between simulated and real-life samples, necessitating the use of sample synthesis and other methods to mitigate cross-domain effects. Current mainstream methods typically employ generative adversarial networks for sample synthesis. By learning target and environment characteristics from simulated and real-life samples and designing an adversarial loss function to constrain the sample generation process, they generate samples with similar distributions to the original data but distinct characteristics, achieving a certain degree of sample confidence improvement through style transfer. However, the training process of these generative adversarial network-based synthesis methods suffers from poor convergence and difficulty avoiding pattern collapse. Furthermore, the synthesized samples suffer from significant regional pixel fragmentation and sample distortion, making it difficult to synthesize the high-confidence sample sets required for intelligent algorithm training. Summary of the Invention

[0003] The purpose of the present invention is to provide a method for constructing a scene-to-image cross-domain mapping sample set driven by attribute features, so as to solve the problem that the existing sample synthesis method has obvious pixel block fragmentation and sample distortion in the synthesized sample area, resulting in the inability to effectively synthesize the high-confidence sample set required for intelligent algorithm training.

[0004] To achieve the above object, the present invention adopts the following technical solutions:

[0005] In one aspect, this specification provides a method for constructing a scene-to-image cross-domain mapping sample set driven by attribute features, including:

[0006] Step 102: augmenting the basic sample set using an image feature transformation method to obtain a material library for sample synthesis; the basic sample set includes simulated target materials and real-shot environment materials;

[0007] Step 104: perform spatial position registration on the actual target and the actual environment in the actual application scenario to obtain position information of the actual target in the environment coordinate system;

[0008] Step 106: Select corresponding simulation target materials and real-shot environment materials from the material library based on the actual application scenario;

[0009] Step 108 : Based on the position information of the actual target in the environment coordinate system, the selected simulated target material is threshold segmented and fused with the real-shot environment material to obtain a high-confidence synthetic sample.

[0010] On the other hand, this specification provides an attribute feature-driven scene-to-image cross-domain mapping sample set construction device, comprising:

[0011] A sample augmentation module is used to augment the basic sample set using an image feature transformation method to obtain a material library for sample synthesis; the basic sample set includes simulated target materials and real-shot environment materials;

[0012] The spatial registration module is used to perform spatial registration of the actual target and the actual environment in the actual application scenario to obtain the position information of the actual target in the environmental coordinate system;

[0013] The actual material acquisition module is used to select corresponding simulation target materials and real-shot environment materials from the material library based on the actual application scenario;

[0014] The material fusion module is used to perform threshold segmentation on the selected simulated target material based on the position information of the actual target in the environmental coordinate system and fuse it with the real-shot environmental material to obtain a high-confidence synthetic sample.

[0015] Based on the above technical solution, this specification can achieve the following technical effects:

[0016] This method constructs a synthetic feature library based on simulation modeling data and real-shot data, and performs sample augmentation based on image features to improve the diversity of the feature library. Then, through the spatial position alignment of the target and the environment, the rationality of the spatial position relationship between the target and the environment in the synthetic samples is improved. The target threshold segmentation and background adaptive fusion technology are used for sample synthesis, which effectively solves the problems of obvious regional pixel block segmentation and sample authenticity, and improves the confidence of the synthetic samples. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 The figure is a flow chart of a method for constructing a scene-to-image cross-domain mapping sample set driven by attribute features in one embodiment of the present invention.

[0018] Figure 2 The figure is a schematic structural diagram of an attribute feature driven scene-to-image cross-domain mapping sample set construction device according to an embodiment of the present invention.

[0019] Figure 3 The figure is a schematic diagram of an electronic device according to the present invention. DETAILED DESCRIPTION

[0020] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. The advantages and features of the present invention will become more apparent from the following description and claims. It should be noted that the drawings are all in a very simplified form and are not to exact scale. They are only used for the purpose of conveniently and clearly illustrating the embodiments of the present invention.

[0021] It should be noted that, in order to clearly illustrate the contents of the present invention, the present invention specifically provides multiple embodiments to further illustrate different implementations of the present invention. These multiple embodiments are provided in an enumerated manner rather than an exhaustive manner. Furthermore, for the sake of brevity, the contents mentioned in the previous embodiments are often omitted in the subsequent embodiments. Therefore, for the contents not mentioned in the subsequent embodiments, reference may be made to the previous embodiments accordingly. Example 1

[0022] Please refer to Figure 1 , Figure 1 The following is a method for constructing a scene-to-image cross-domain mapping sample set driven by attribute features provided in this embodiment. In this embodiment, the method includes:

[0023] Step 102: augmenting the basic sample set using an image feature transformation method to obtain a material library for sample synthesis; the basic sample set includes simulated target materials and real-shot environment materials;

[0024] In this embodiment, before step 102, the following steps are further included:

[0025] Step 1011: Using a simulation modeling method, establish a target model and generate a number of simulation target materials; the simulation target materials include target type, target scale, and target direction;

[0026] Step 1012: Acquire real-time environment materials using a real-time acquisition method; the real-time environment materials include scene information, time of day information, lighting information, and weather information;

[0027] In this embodiment, one implementation of step 102 is:

[0028] Step 202: Analyze the mapping relationship between scene conditions and image features on the basic sample set to obtain augmented image features; the augmented image features are image features that are strongly coupled with the intelligent detection and recognition algorithm;

[0029] Step 204 : performing image preprocessing and image feature transformation on the basic sample set based on the augmented image features to obtain a material library for sample synthesis.

[0030] Step 104: perform spatial position registration on the actual target and the actual environment in the actual application scenario to obtain position information of the actual target in the environment coordinate system;

[0031] In this embodiment, one implementation of step 104 is:

[0032] Step 302: Determine the actual target and actual environment based on the actual application scenario;

[0033] Step 304: extract features from the actual target and the actual environment to obtain key features;

[0034] Step 306: perform feature point registration on the actual target and the actual environment based on the key features to obtain a transformation matrix from the target coordinate system to the environment coordinate system;

[0035] In this embodiment, one implementation of step 306 is:

[0036] Step 3061: Based on the position information of the actual target in the target coordinate system and the rotation angle of the actual target relative to the actual environment, obtain a rotation matrix for converting from the target coordinate system to the environment coordinate system;

[0037] Step 3062: Obtain a transformation matrix from the target coordinate system to the environment coordinate system based on the translation direction, scaling ratio, and rotation matrix.

[0038] Step 308 : Based on the transformation matrix, the coordinates of the actual target are transformed into the environment coordinate system to obtain the position information of the actual target in the environment coordinate system after spatial registration.

[0039] In this embodiment, the key features include a rotation angle, a translation vector, and a scaling ratio of the actual target relative to the actual environment.

[0040] Step 106: Select corresponding simulation target materials and real-shot environment materials from the material library based on the actual application scenario;

[0041] Step 108 : Based on the position information of the actual target in the environment coordinate system, the selected simulated target material is threshold segmented and fused with the real-shot environment material to obtain a high-confidence synthetic sample.

[0042] In this embodiment, one implementation of step 108 is:

[0043] Step 402 , based on the position information of the actual target in the environment coordinate system, calculate the gradient of the local area in the image of the simulated target material and determine the segmentation threshold;

[0044] Step 404 , segmenting the image of the simulated target material into a target portion and a background portion based on the segmentation threshold;

[0045] Step 406 , determining the edges of the segmented simulation target material based on a Sobel detection operator and performing edge smoothing optimization to obtain a smoothed simulation target material;

[0046] In this embodiment, one implementation of step 406 is:

[0047] Step 4061, using the Sobel detection operator to perform convolution on the simulated target material along the X-axis and the Y-axis respectively, to determine the image edge of the simulated target material;

[0048] Step 4062: Perform edge smoothing optimization on the image edge of the simulation target material through Gaussian kernel filtering to obtain a smoothed simulation target material.

[0049] Step 408: synthesize the smoothed simulation target material with the real-shot environment material to generate a simulation-real-shot synthesized sample;

[0050] Step 410 : performing contrast adjustment on the simulated real-shot synthetic sample to obtain a high-confidence synthetic sample.

[0051] In this embodiment, one implementation of step 410 is:

[0052] Step 4101, performing grayscale histogram statistics on the simulated real-shot synthetic samples;

[0053] Step 4102: Based on the grayscale histogram, the contrast of the simulated real-shot synthetic sample is adjusted using a histogram equalization method to obtain a high-confidence synthetic sample.

[0054] Specifically, a method for constructing a scene-to-image cross-domain mapping sample set driven by attribute features includes the following steps:

[0055] The first step is to build a basic sample set of simulation targets and real-shot environments, establish a material library required for sample synthesis, and build a basic sample set consisting of a small number of real samples and a large number of simulation samples. By analyzing the mapping relationship between scene conditions and image features, the image feature transformation method is used to expand the basic sample set, improve sample diversity, and form a material library required for sample synthesis.

[0056] By adopting simulation modeling to establish the target model, a large number of simulation samples of different types, scales and perspectives are generated.

[0057] A small number of real samples of different scenes, different times of day, different lighting, different weather conditions, etc. are obtained through actual shooting to build a basic sample set.

[0058] Based on a small number of real samples and a large number of simulated samples, the relationship between scene conditions and image feature mapping is analyzed, and different features are used for intelligent detection and recognition test analysis. By comparing the degree of influence of different features on the accuracy of the detection and recognition algorithm, image features that are strongly coupled with the performance of the intelligent detection and recognition algorithm are found as the feature basis for sample augmentation. Through preprocessing such as image rotation, scaling, cropping, denoising, as well as image feature transformation operations such as geometric transformation, color transformation, and texture transformation, the basic sample set is augmented and the sample diversity is improved.

[0059] The augmented target materials and environmental materials are standardized and uniformly stored to form a material library required for sample synthesis.

[0060] The second step is to align the spatial positions of the target and the environment in the sample

[0061] By extracting key features of the target material and environmental information, the feature points of the target and environmental information are aligned, and the transformation matrix between the target and the environment is calculated. The target is transformed into the environmental information coordinate system to achieve spatial position alignment.

[0062] Combined with the actual application scenario, the target type and environmental information are determined, and the key features of the target material and environmental information are extracted respectively.

[0063] Based on the extracted features, the feature points of the target and the environment information are aligned, the corresponding feature point pairs are found, and the transformation matrix between the target and the environment is calculated.

[0064] Apply the change matrix to transform the target into the environmental information coordinate system to achieve spatial position alignment, clarify the position, size, and direction of the target in the environment, and ensure that the relative position of the target and the environment is relevant and reasonable.

[0065] Assume that the target position in its own coordinate system is , the rotation angle relative to the environment coordinate is , the rotation matrix from the target system to the environment coordinate system is R,

[0066]

[0067] If the translation vector is , the scaling factor is , then the change matrix T of the target transformation to the environment information coordinate system is:

[0068] ;

[0069] Coordinates after spatial position registration The calculation is as follows:

[0070] ;

[0071] The target position converted to the environment coordinate is , .

[0072] The third step is to perform adaptive synthesis of the target environment through threshold segmentation and background fusion technology

[0073] The edge distribution of the target material is adjusted through threshold segmentation, and background fusion is performed according to the adaptive adjustment of the target and environmental materials to generate simulated real-shot synthetic samples, effectively reducing the problem of large edge gradient changes in the synthetic samples.

[0074] For image-level sample synthesis of targets and environments, based on the target type, lighting, weather, environment and other scene information contained in the desired synthetic samples, target simulation materials and real-shot environment materials related to the scene information are selected from the synthetic material library;

[0075] Using the relative positional relationship between the target and the environment in the sample determined by spatial registration in step 2, a threshold is set by calculating the gradient of a local area in the target material image (usually a 3×3 or 5×5 pixel area is used as the local area). The target part and the background part of the target material are segmented based on this threshold to reduce the interference of background information in the target material.

[0076] Edges are determined by calculating the Sobel detection operator (3×3 pixel size), and the edge distribution of the target material is adjusted through Gaussian kernel filtering to optimize the fusion boundary smoothing. The target and environmental materials are then synthesized to generate simulated real-life synthetic samples. The grayscale histogram of the synthetic samples is calculated, and the contrast is adjusted through histogram equalization to make the grayscale value distribution more uniform, effectively reducing the problem of large gradient changes at the edges of the synthetic samples.

[0077] For example, the edge features of the target material I are calculated using the Sobel operator.

[0078] For the pixel points in the target material image , the Sobel operator performs 3×3 convolution along the X-axis and Y-axis respectively, and its gradient is:

[0079] ,

[0080] in,

[0081] When the 3×3 convolution traverses the entire image, the edge of the image can be obtained.

[0082] After determining the edge of the image, the edge distribution of the target material is adjusted by Gaussian kernel filtering, and a 3×3 Gaussian kernel is used for average rate filtering. The Gaussian smoothing filter formula is:

[0083]

[0084] After Gaussian smoothing filtering, the smooth optimization of the fusion boundary can be achieved.

[0085] After smoothing and optimizing the target material, the target and environment materials are synthesized to generate simulated real-shot synthetic samples. The grayscale histogram of the synthetic samples is calculated, and the contrast is adjusted using histogram equalization to make the grayscale value distribution of the synthetic samples more uniform and reduce the edge distortion problem of the synthetic image.

[0086] This method proposes a sample augmentation method based on the image feature domain. A synthetic feature library is constructed based on simulation modeling data and real-shot data. By analyzing the coupling relationship between scene conditions and image features, the scene domain is mapped to the image feature domain. Image feature transformation is then used for sample augmentation. This method realizes the transition from a qualitative augmentation method based on scene description to a quantitative and controllable augmentation method based on the feature domain, effectively improving sample efficiency and sample diversity.

[0087] This method proposes a target environment adaptive synthesis method based on threshold segmentation and edge gradient adjustment. Based on the sample synthesis element library, spatial position registration is used to determine the relative position relationship between the target and the environment, thereby improving the spatial position rationality of the synthesized samples. By performing threshold segmentation and edge gradient adjustment on the target and environment materials, the adaptive synthesis of the target and the environment is achieved, effectively reducing the regional deformation and sample distortion problems of the synthesized samples.

[0088] In summary, this method constructs an element library based on simulation modeling data and real-shot data, constructs a basic sample set of simulation targets and real-shot environments, establishes a material library required for sample synthesis, analyzes the target style, environmental information, and the relative spatial position of the target and the environment in the required samples according to the actual application scenarios, performs target foreground threshold segmentation and adaptive fusion with the background, and generates high-confidence synthetic samples. It solves the problem of synthetic sample distortion in existing methods, achieves the beneficial effects of improving the confidence of synthetic samples and reducing the construction of large-scale training sets, and has outstanding substantive characteristics and significant progress. Example 2

[0089] Please refer to Figure 2 , Figure 2 The following is a device for constructing a scene-to-image cross-domain mapping sample set driven by attribute features provided in this embodiment. In this embodiment, the device includes:

[0090] A sample augmentation module is used to augment the basic sample set using an image feature transformation method to obtain a material library for sample synthesis; the basic sample set includes simulated target materials and real-shot environment materials;

[0091] The spatial registration module is used to perform spatial registration of the actual target and the actual environment in the actual application scenario to obtain the position information of the actual target in the environmental coordinate system;

[0092] The actual material acquisition module is used to select corresponding simulation target materials and real-shot environment materials from the material library based on the actual application scenario;

[0093] The material fusion module is used to perform threshold segmentation on the selected simulated target material based on the position information of the actual target in the environmental coordinate system and fuse it with the real-shot environmental material to obtain a high-confidence synthetic sample.

[0094] Optionally, also include:

[0095] A simulation target material acquisition module is used to establish a target model and generate a number of simulation target materials using a simulation modeling method; the simulation target materials include target type, target scale and target direction;

[0096] The real-shot environment material acquisition module is used to acquire real-shot environment materials using a real-shot acquisition method; the real-shot environment materials include scene information, time of day information, lighting information and weather information.

[0097] Optional sample augmentation modules include:

[0098] An image feature mapping unit is used to analyze the mapping relationship between scene conditions and image features on the basic sample set to obtain augmented image features; the augmented image features are image features that are strongly coupled with the intelligent detection and recognition algorithm;

[0099] The image augmentation unit is used to perform image preprocessing and image feature transformation on the basic sample set based on the augmented image features to obtain a material library for sample synthesis.

[0100] Optional spatial registration modules include:

[0101] An actual scenario determination unit, configured to determine an actual target and an actual environment based on an actual application scenario;

[0102] Feature extraction unit, used to extract features from actual targets and actual environments to obtain key features;

[0103] A transformation matrix calculation unit is used to perform feature point registration on the actual target and the actual environment based on key features, and obtain a transformation matrix for converting from the target coordinate system to the environment coordinate system;

[0104] The spatial registration unit is used to convert the coordinates of the actual target into the environment coordinate system based on the transformation matrix, and obtain the position information of the actual target in the environment coordinate system after spatial registration.

[0105] Optionally, the key features include a rotation angle, a translation vector, and a scaling ratio of the actual target relative to the actual environment.

[0106] Optionally, the transformation matrix calculation unit includes:

[0107] A rotation matrix calculation subunit, configured to obtain a rotation matrix for converting from a target coordinate system to an environment coordinate system based on the position information of the actual target in the target coordinate system and the rotation angle of the actual target relative to the actual environment;

[0108] The coordinate system conversion subunit is used to obtain the transformation matrix from the target coordinate system to the environment coordinate system based on the translation vector, the scaling factor and the rotation matrix.

[0109] Optional material fusion modules include:

[0110] a segmentation threshold determination unit, configured to calculate the gradient of a local area in the image of the simulated target material and determine the segmentation threshold based on the position information of the actual target in the environment coordinate system;

[0111] The target and background segmentation unit is used to segment the image of the simulated target material into a target part and a background part based on a segmentation threshold;

[0112] An edge smoothing optimization unit is used to determine the edge of the segmented simulation target material based on a Sobel detection operator and perform edge smoothing optimization to obtain a smoothed simulation target material;

[0113] A material fusion unit is used to synthesize the smoothed simulation target material with the real-shot environment material to generate a simulation-real-shot synthesis sample;

[0114] The contrast adjustment unit is used to adjust the contrast of the simulated real-shot synthetic sample to obtain a high-confidence synthetic sample.

[0115] Optionally, the edge smoothing optimization unit includes:

[0116] A convolution subunit, configured to perform convolution on the simulation target material along the X-axis and the Y-axis respectively using a Sobel detection operator to determine the image edge of the simulation target material;

[0117] The filtering subunit is used to perform edge smoothing optimization on the image edge of the simulation target material through Gaussian kernel filtering to obtain the smoothed simulation target material.

[0118] Optionally, the contrast adjustment unit includes:

[0119] The histogram statistics subunit is used to perform grayscale histogram statistics on the simulated real-shot synthetic samples;

[0120] The contrast adjustment subunit is used to adjust the contrast of the simulated real-shot synthetic sample based on the grayscale histogram and use the histogram equalization method to obtain a high-confidence synthetic sample.

[0121] Based on this, this device constructs an element library based on simulation modeling data and real-shot data, constructs a basic sample set of simulation targets and real-shot environments, establishes a material library required for sample synthesis, and analyzes the target style, environmental information, and the relative spatial position of the target and the environment in the required samples according to the actual application scenarios. It performs target foreground threshold segmentation and adaptive fusion with the background to generate high-confidence synthetic samples, which solves the problem of synthetic sample distortion of existing methods, and achieves the beneficial effects of improving the confidence of synthetic samples and reducing the construction of large-scale training sets. It has outstanding substantive characteristics and significant progress. Example 3

[0122] Please refer to Figure 3 , this embodiment provides an electronic device, which includes a processor, an internal bus, a network interface, a memory and a non-volatile memory, and of course may also include hardware required for other services. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a method for constructing a scene-to-image cross-domain mapping sample set driven by attribute features at the logical level. Of course, in addition to software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0123] The network interface, processor, and memory can be connected to each other through a bus system. The above bus can be divided into address bus, data bus, control bus, etc.

[0124] The memory is used to store programs. Specifically, the program may include program code, which includes computer operating instructions. The memory may include read-only memory and random access memory, and provides instructions and data to the processor.

[0125] The processor is configured to execute the program stored in the memory and specifically perform:

[0126] Step 102: augmenting the basic sample set using an image feature transformation method to obtain a material library for sample synthesis; the basic sample set includes simulated target materials and real-shot environment materials;

[0127] Step 104: perform spatial position registration on the actual target and the actual environment in the actual application scenario to obtain position information of the actual target in the environment coordinate system;

[0128] Step 106: Select corresponding simulation target materials and real-shot environment materials from the material library based on the actual application scenario;

[0129] Step 108 : Based on the position information of the actual target in the environment coordinate system, the selected simulated target material is threshold segmented and fused with the real-shot environment material to obtain a high-confidence synthetic sample.

[0130] The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit of the processor or the instructions in the form of software.

[0131] Based on the same invention, the embodiment of this specification also provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple application programs, the electronic device executes Figure 1 The corresponding embodiment provides a method for constructing a scene-to-image cross-domain mapping sample set driven by attribute features.

[0132] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Thus, this specification may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this specification may take the form of a computer program product embodied on one or more computer-readable storage media containing computer-usable program code.

[0133] In addition, for the above-mentioned specific implementation of the system, since it is basically similar to the method implementation, the description is relatively simple, and the relevant parts can be referred to the partial description of the method implementation. Moreover, it should be noted that in each module of the system of the present application, the components therein are logically divided according to the functions to be implemented, but the present application is not limited thereto, and the components can be re-divided or combined as needed.

[0134] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences between it and other embodiments.

[0135] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the figures do not necessarily require the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0136] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for constructing a scene-to-image cross-domain mapping sample set driven by attribute features, characterized in that: include: The basic sample set is augmented by image feature transformation method to obtain the material library for sample synthesis; The basic sample set includes simulation target materials and real-shot environment materials; Perform spatial registration of the actual target and the actual environment in the actual application scenario to obtain the position information of the actual target in the environmental coordinate system; Select corresponding simulation target materials and real-life environment materials from the material library based on actual application scenarios; Based on the position information of the actual target in the environmental coordinate system, the selected simulated target material is threshold segmented and fused with the real-shot environmental material to obtain a high-confidence synthetic sample.

2. The method according to claim 1, characterized in that Before the basic sample set is augmented by the image feature transformation method to obtain a material library for sample synthesis, the method further includes: A simulation modeling method is used to establish a target model and generate a plurality of simulation target materials; the simulation target materials include target type, target scale and target direction; A real-time acquisition method is used to obtain real-time environment materials; the real-time environment materials include scene information, time of day information, lighting information and weather information.

3. The method according to claim 1, characterized in that The method of augmenting the basic sample set by using the image feature transformation method to obtain a material library for sample synthesis includes: Analyzing the mapping relationship between scene conditions and image features on the basic sample set to obtain augmented image features; the augmented image features are image features that are strongly coupled with the intelligent detection and recognition algorithm; Based on the augmented image features, image preprocessing and image feature transformation are performed on the basic sample set to obtain a material library for sample synthesis.

4. The method according to claim 1, wherein The spatial registration of the actual target and the actual environment in the actual application scenario to obtain the position information of the actual target in the environment coordinate system includes: Determine the actual goals and actual environment based on the actual application scenario; Extract features from actual targets and actual environments to obtain key features; Based on the key features, the actual target and the actual environment are registered with feature points to obtain the transformation matrix from the target coordinate system to the environment coordinate system; Based on the transformation matrix, the coordinates of the actual target are converted to the environment coordinate system to obtain the position information of the actual target in the environment coordinate system after spatial registration.

5. The method according to claim 4, characterized in that The key features include the rotation angle, translation vector, and scaling ratio of the actual target relative to the actual environment.

6. The method according to claim 5, characterized in that The step of performing feature point registration on the actual target and the actual environment based on the key features to obtain a transformation matrix from the target coordinate system to the environment coordinate system includes: Based on the position information of the actual target in the target coordinate system and the rotation angle of the actual target relative to the actual environment, a rotation matrix for converting from the target coordinate system to the environment coordinate system is obtained; Based on the translation vector, scale factor, and rotation matrix, obtain the transformation matrix from the target coordinate system to the environment coordinate system.

7. The method according to claim 1, characterized in that The method of performing threshold segmentation on the selected simulated target material based on the position information of the actual target in the environmental coordinate system and fusing it with the real-shot environmental material to obtain a high-confidence synthetic sample includes: Based on the position information of the actual target in the environment coordinate system, the gradient of the local area in the image of the simulated target material is calculated and the segmentation threshold is determined; Segmenting the target part and the background part of the image of the simulated target material based on the segmentation threshold; Determine the edge of the segmented simulation target material based on the Sobel detection operator and perform edge smoothing optimization to obtain the smoothed simulation target material; The smoothed simulation target material is synthesized with the real-shot environment material to generate a simulation-real-shot synthesis sample; The contrast of the simulated real-shot synthetic samples is adjusted to obtain high-confidence synthetic samples.

8. The method according to claim 7, characterized in that The step of determining the edge of the segmented simulation target material based on the Sobel detection operator and performing edge smoothing optimization to obtain the smoothed simulation target material includes: Use the Sobel detection operator to perform convolution on the simulation target material along the X-axis and Y-axis respectively to determine the image edge of the simulation target material; The edge of the image of the simulation target material is smoothed and optimized by Gaussian kernel filtering to obtain the smoothed simulation target material.

9. The method according to claim 8, characterized in that The step of adjusting the contrast of the simulated real-shot synthetic sample to obtain a high-confidence synthetic sample includes: Perform grayscale histogram statistics on the simulated real-shot synthetic samples; Based on the grayscale histogram, the contrast of the simulated real-shot synthetic samples is adjusted using the histogram equalization method to obtain high-confidence synthetic samples.

10. A device for constructing a scene-to-image cross-domain mapping sample set driven by attribute features, characterized in that: include: A sample augmentation module is used to augment the basic sample set using an image feature transformation method to obtain a material library for sample synthesis; the basic sample set includes simulated target materials and real-shot environment materials; The spatial registration module is used to perform spatial registration of the actual target and the actual environment in the actual application scenario to obtain the position information of the actual target in the environmental coordinate system; The actual material acquisition module is used to select corresponding simulation target materials and real-shot environment materials from the material library based on the actual application scenario; The material fusion module is used to perform threshold segmentation on the selected simulated target material based on the position information of the actual target in the environmental coordinate system and fuse it with the real-shot environmental material to obtain a high-confidence synthetic sample.

Images