Remote sensing image sensitive target safe distribution method based on zero watermark and block chain

Abstract

The invention discloses a remote sensing image sensitive target safe distribution method based on zero watermarking and a block chain, and relates to the technical field of remote sensing image processing. The method comprises the steps of extracting a sensitive target image from an original remote sensing image according to a mask, and repairing a sensitive area to generate a published image. Normalized published images and effective areas are determined, and robust feature maps are extracted from the effective areas. And respectively scrambling the sensitive target image and the robust feature map, and then carrying out XOR to generate a zero-watermark image. And packaging the zero-watermark image, the effective area coordinates and the repair algorithm parameters into a record file, encrypting the record file, and then uploading the record file, the published image and the zero-watermark image to a distributed storage to obtain an index. And segmenting the secret key of the record file, and writing the index and secret key segmentation information into a block chain storage certificate. And when the sensitive target needs to be recovered, the authorized user acquires data and a secret key according to the block chain record, reproduces a feature extraction process from the to-be-verified image according to the effective region coordinates and the algorithm parameters, and recovers a sensitive target image through inverse operation in combination with the zero-watermark image.

Description

Technical Field

[0001] This invention relates to the field of remote sensing image processing technology, and more specifically, to a method for securely distributing sensitive targets in remote sensing images based on zero watermarking and blockchain. Background Technology

[0002] Remote sensing images often contain sensitive targets that require protection during public sharing, data release, and collaborative applications. To meet the dual requirements of open sharing and security compliance, it is usually necessary to process sensitive areas and release usable versions that do not disclose sensitive information, while retaining the ability to restore sensitive targets in authorized scenarios.

[0003] Existing technologies primarily employ methods for handling sensitive targets, including irreversible sensitive area hiding, embedded or reversible watermarking schemes, and recovery through external credentials. These methods achieve sensitive content hiding through techniques such as blurring, occlusion, patching, or information embedding, but each has its limitations.

[0004] However, the aforementioned existing technical solutions have significant drawbacks. Embedded watermarks introduce additional distortion into published images, affecting the usability and quantitative analysis of remote sensing images. Irreversible concealment fails to meet authorization recovery requirements, while external credential solutions lack verifiable binding and unified recording with published images. Furthermore, these methods lack robustness to common processing such as compression, noise, and scaling, and inconsistent management of coordinates and parameters leads to difficulties in reproduction, making it difficult to achieve full-scenario forensics and audit evidence preservation. Summary of the Invention

[0005] This invention provides a secure distribution method for sensitive targets in remote sensing images based on zero watermarking and blockchain, in order to improve at least one of the aforementioned technical problems.

[0006] The present invention provides a secure distribution method for sensitive targets in remote sensing images based on zero watermarking and blockchain, comprising steps S1 to S6.

[0007] S1. Extract sensitive target images from the original remote sensing images based on the mask, repair sensitive areas, and generate published images.

[0008] S2. Normalize the published image to a uniform size and determine the effective region, from which robust feature maps are extracted.

[0009] S3. After scrambling the sensitive target image and the robust feature map respectively, XOR them to generate a zero-watermark image.

[0010] S4. Package the zero-watermark image, effective region coordinates, and repair algorithm parameters into a record file and encrypt it. Then upload it together with the published image and the zero-watermark image to the distributed storage to obtain an index.

[0011] S5. Segment the key of the record file and write the index and key segmentation information into the blockchain for evidence storage.

[0012] S6. When it is necessary to recover sensitive targets, authorized users obtain data and keys based on blockchain records, reproduce the feature extraction process from the image to be verified based on the valid area coordinates and algorithm parameters, and recover the sensitive target image by inverse operation in combination with the zero-watermark image.

[0013] As a further aspect of the present invention, S1 specifically includes the following steps.

[0014] Acquiring remote sensing images Masks for sensitive areas .

[0015] If the mask is empty, the original remote sensing image is used directly as the published image.

[0016] If sensitive areas exist, use a mask to determine the bounding box of the sensitive areas and crop out the sensitive target image. If there are multiple sensitive areas, each area will be cropped separately.

[0017] Using image inpainting algorithms to fill in the original remote sensing image The sensitive area is made continuous with the background to obtain the published image. The image inpainting algorithm is selected from inpainting based on partial differential equations, inpainting based on sample block matching, or inpainting based on deep generative models.

[0018] As a further aspect of the present invention, S2 specifically includes the following steps.

[0019] Images will be published. Normalized to standard dimensions Image for The width. for The height.

[0020] Reading sensitive target images Size for The width. for The height.

[0021] Calculation satisfies and , Scale factor ,in This is the base size for the singular value decomposition sub-blocks.

[0022] by The rectangular area is calculated based on the center point as the effective region coordinate (Coord), and boundary processing rules are set. Boundary processing rules include truncation and / or mirror fill and / or zero fill.

[0023] Based on the valid area coordinates Coord The effective area is obtained by cropping the middle. .

[0024] As a further aspect of the present invention, S2 also includes the following steps.

[0025] For the effective area Extracting low-frequency subbands by performing two-stage discrete wavelet transform and the low-frequency subband Divided into Individual blocks.

[0026] Perform singular value decomposition on each sub-block and extract the maximum singular value. And use the mean of all the largest singular values ​​as the threshold. Generate binary feature matrix .

[0027] .

[0028] In the formula, and These are the row index and column index of the sub-block, respectively.

[0029] right Perform bit expansion to generate a robust feature map of the same size as the sensitive target image. .

[0030] As a further aspect of the present invention, S3 specifically includes the following steps.

[0031] A scrambled sequence is generated based on chaotic mapping parameters. The chaotic mapping parameters include mapping type, initial value, control parameters, number of iterations, or sequence length.

[0032] Using the generated scrambled sequence, sensitive target images are processed. robust feature map Perform scrambling operations separately to obtain encrypted images. and encryption feature map .

[0033] Generate a zero-watermark image by performing an XOR operation. :

[0034] .

[0035] In the formula This represents a scrambling encryption function based on chaotic mapping. This indicates a bitwise XOR operation.

[0036] As a further aspect of the present invention, the scrambling operation employs Henon chaotic mapping.

[0037] As a further aspect of the present invention, S4 specifically includes the following steps.

[0038] The zero-watermark image, effective region coordinates, and repair algorithm parameters are packaged into a record file.

[0039] Generate a random symmetric key Key to encrypt the record file.

[0040] Upload the published image, the watermark-free image, and the encrypted log file together to distributed storage to obtain an index.

[0041] Preferably, the record file contains the following fields: The standardization rules field is used to record rules for standardizing images to the same size.

[0042] The coordinate field records the coordinates (Coord) of the valid region, which is used to crop the valid region from the standardized image.

[0043] The repair metadata field records the repair algorithm type, key parameters, and random seed used when generating the repaired carrier image, which is used for environmental reconstruction during evidence collection.

[0044] The feature extraction parameter field records the algorithm identifier and binarization strategy for feature extraction.

[0045] The scrambling parameter field records the scrambling algorithm type and parameters.

[0046] As a further aspect of the present invention, S5 includes the following steps.

[0047] Using threshold The Shamir secret sharing algorithm splits the key into... A secret share. This represents the minimum number of keys required to reconstruct the key.

[0048] Will Each secret share is distributed to a hybrid storage layer. The hybrid storage layer includes private cloud nodes, notary nodes, and IPFS nodes.

[0049] As a further aspect of the present invention, S6 specifically includes the following steps.

[0050] Download the encrypted record file from the distributed storage system, collect enough key shares to reconstruct the key, use the key to decrypt the record file, and parse out the valid region coordinates, scrambling parameters and feature extraction strategy.

[0051] Using the effective region coordinates obtained from the analysis, the image to be verified is normalized and cropped to extract the effective region, and a test feature map is generated according to the feature extraction strategy obtained from the analysis. .

[0052] The test feature map is analyzed using the scrambling parameters obtained from the analysis. Encryption is performed to obtain And combined with the obtained zero-watermark image Computational encryption sensitive targets : .

[0053] In the formula This represents a scrambling encryption function based on chaotic mapping. This indicates a bitwise XOR operation.

[0054] Using the scrambling parameters and key pair obtained from parsing Perform the reverse scrambling operation to recover the sensitive target image. .

[0055] As a further aspect of the present invention, it also includes an infringement evidence collection step for the leaked images.

[0056] Obtain suspected infringing images, calculate their hash values, and retrieve evidence records on the blockchain to obtain the original zero-watermark and record files.

[0057] The sensitive areas of suspected infringing images are masked using the valid region coordinates in the log file.

[0058] The repair algorithm and parameters in the log file are used to re-perform the repair process on the occluded area in order to reconstruct the verification environment.

[0059] Features are extracted from the reconstructed image and combined with the on-chain zero-watermark image to perform blind restoration. If a clear and sensitive target can be restored, it is determined to be an infringement.

[0060] By adopting the above technical solution, the present invention can achieve the following technical effects: This invention brings significant benefits to the secure distribution and copyright protection of sensitive targets in remote sensing images. First, by employing zero-watermark technology, the zero-watermark image is not embedded in the published image, effectively avoiding the secondary distortion problems that may be introduced by traditional watermark embedding, thus ensuring the high quality and usability of the published image, while achieving reliable recovery of sensitive targets in authorized scenarios. Second, this invention combines a standardized coordinate system with robust feature extraction methods (such as discrete wavelet transform and singular value decomposition), enhancing adaptability to common image processing such as compression, noise, and scaling, and improving the robustness of the recovery process. Furthermore, by combining key parameter recording with blockchain notarization, immutable binding of hashes, content identifiers, and timestamps is achieved, facilitating auditable verification and traceability by third parties, enhancing the credibility and transparency of the entire system. Finally, this method is simple in engineering implementation; the generation of the published image is decoupled from the zero-watermark registration process, and the verification end only needs to reproduce the coordinate and feature flow to complete the recovery, reducing system complexity and coupling, and improving practical efficiency. Attached Figure Description

[0061] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the specific embodiments of the present invention will be briefly introduced below. It should be understood that the following drawings only show some specific embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained from these drawings without creative effort.

[0062] Figure 1 This is a flowchart illustrating a method for securely distributing remotely sensed images to sensitive targets.

[0063] Figure 2 This is a flowchart of the entire process of generating zero watermarks.

[0064] Figure 3 This is a flowchart for the recovery of sensitive targets.

[0065] Figure 4 It is a sequence diagram of system interaction and storage distribution. Detailed Implementation

[0066] The technical solutions of the present invention will now be clearly and completely described with reference to the accompanying drawings in the embodiments of the present invention.

[0067] Please see Figures 1 to 4 This invention provides a secure distribution method for sensitive targets in remote sensing images based on zero watermarking and blockchain, which can be executed by a secure distribution device for sensitive targets in remote sensing images based on zero watermarking and blockchain (hereinafter referred to as: sensitive image distribution device). Specifically, it is executed by one or more processors in the sensitive image distribution device to implement steps S1 to S6.

[0068] S1. Extract sensitive target images from the original remote sensing images based on the mask, repair sensitive areas, and generate published images.

[0069] S2. Normalize the published image to a uniform size and determine the effective region, from which robust feature maps are extracted.

[0070] S3. After scrambling the sensitive target image and the robust feature map respectively, XOR them to generate a zero-watermark image.

[0071] S4. Package the zero-watermark image, effective region coordinates, and repair algorithm parameters into a record file and encrypt it. Then upload it together with the published image and the zero-watermark image to the distributed storage to obtain an index.

[0072] S5. Segment the key of the record file and write the index and key segmentation information into the blockchain for evidence storage.

[0073] S6. When it is necessary to recover sensitive targets, authorized users obtain data and keys based on blockchain records, reproduce the feature extraction process from the image to be verified based on the valid area coordinates and algorithm parameters, and recover the sensitive target image by inverse operation in combination with the zero-watermark image.

[0074] This embodiment achieves the following without embedding watermarks in the published images and while maintaining the quality of the published images as much as possible: Authorization can be recovered after sensitive targets are hidden: the authorizing party can recover the sensitive target image from the "published image + zero watermark + recorded parameters". Robustness to common processing: it can still stably recover from disturbances such as compression, noise, and scaling.

[0075] Based on the above embodiments, in an optional embodiment of the present invention, such as Figure 1 As shown, S1 specifically includes steps S11 to S14.

[0076] S11. Acquire remote sensing images Masks for sensitive areas .

[0077] S12. If the mask is empty, directly use the original remote sensing image as the published image.

[0078] Specifically, the Remote Sensing Image Owner (RSI Owner) acquires remote sensing images. Masks for sensitive areas Mask It can be generated by manual annotation, rule detection, or depth segmentation models. If If it is empty (no sensitive area), output directly. The process ends when "no sensitive area" is recorded as the status.

[0079] S13. If a sensitive region exists, use a mask to determine the bounding box of the sensitive region and crop out the sensitive target image. If there are multiple sensitive areas, each area will be cropped separately.

[0080] Specifically, the RSI Owner bases on Calculate the bounding box of the sensitive region, and from The sensitive target image is obtained by cropping the middle. If multiple sensitive targets exist, a corresponding [database name] can be generated for each target. The target number and location coordinates are recorded in the record.

[0081] S14. Fill the original remote sensing image using an image inpainting algorithm. The sensitive area is made continuous with the background to obtain the published image. The image inpainting algorithm is selected from inpainting based on partial differential equations, inpainting based on sample block matching, or inpainting based on deep generative models.

[0082] Specifically, the RSI Owner has... The sensitive areas are processed using an image inpainting algorithm to generate the repaired carrier image. This makes the sensitive area visually continuous with the background.

[0083] Patching algorithms may include, but are not limited to: PDE-based patching, PatchMatch-based sample block matching patching, and deep generative model-based patching (GAN / diffusion model, etc.).

[0084] Based on the above embodiments, in an optional embodiment of the present invention, such as Figure 1 As shown, S2 specifically includes S21 to S27.

[0085] S21, Images to be published Normalized to standard dimensions Image for The width. for The height. Specifically, the repaired carrier image. Normalized to standard size (For example, 1024×1024) .

[0086] S22. Read the image of the sensitive target. Size for The width. for The height.

[0087] S23, Calculation satisfies and , Scale factor ,in This determines the base size for the singular value decomposition sub-blocks. This step is used to determine the robust feature extraction region Coord and ensure reproducibility at the validation end.

[0088] Reading sensitive target images Size Then, the scaling factor is calculated according to the feature extraction constraints. . It must be a positive even number, and must simultaneously satisfy the following feature extraction effectiveness constraints and boundary constraints.

[0089] Feature Capacity Constraint: To ensure that the effective region still has enough pixels in the low-frequency subband to support partitioning after performing a two-level discrete wavelet transform (DWT). 3 non-overlapping SVD sub-blocks (each sub-block being at least [size missing]) (pixels). The scaling factor k must satisfy: .in The base size for singular value decomposition sub-blocks (recommended value) That is, requirements Preferred ,Right now ).

[0090] Boundary Constraint: To ensure that the extracted effective region does not exceed the boundary of the standardized image, the following must be satisfied: and Preferably, the preferred sub-block size is set. (correspond ), and calculate the maximum allowable multiple that satisfies the boundary constraints. .like Then take .like ,Pick .like If so, the fallback strategy described in step (2.3) will be executed.

[0091] like Then, a fallback strategy will be implemented, adjusting the standardized dimensions. Alternatively, boundary padding (mirroring / zero padding) can be applied to the effective region to make subsequent feature extraction available, and a fallback strategy can be written into the record.

[0092] by Using the center point as a reference, calculate the rectangle Coord=(x0,y0,x1,y1), and agree on boundary processing rules (truncation / mirror fill / zero fill) to ensure that the extracted area can be reproduced.

[0093] S24, with The rectangular area is calculated based on the center point as the effective region coordinate (Coord), and boundary processing rules are defined. Boundary processing rules include truncation and / or mirror fill and / or zero fill.

[0094] S25, Based on the effective area coordinates Coord from The effective area is obtained by cropping the middle. .

[0095] Specifically, according to Coord from Cropping to obtain the effective area If a boundary violation occurs, a valid region will be generated according to the agreed boundary handling rules. .

[0096] S25, For the effective area Extracting low-frequency subbands by performing two-stage discrete wavelet transform and the low-frequency subband Divided into Individual blocks.

[0097] Specifically, for the effective area Perform a two-stage discrete wavelet transform (DWT) to extract the low-frequency subband containing the main energy of the image. This is done to filter out high-frequency noise interference and compress data dimensions. Then, based on the sensitive target image... Target size , low frequency subband Divided into Each sub-block consists of non-overlapping sub-blocks. According to the constraints of step (2.2) in Example 2, the size of each sub-block is at least [size missing]. (For example (pixels).

[0098] S26. Perform singular value decomposition on each sub-block and extract the maximum singular value. And use the mean of all the largest singular values ​​as the threshold. Generate binary feature matrix .

[0099] .

[0100] In the formula, and These are the row index and column index of the sub-block, respectively.

[0101] Specifically, firstly, singular value decomposition (SVD) is performed on each sub-block to extract the maximum singular value of each sub-block. Then, the average of the maximum singular values ​​of all sub-blocks is calculated as the adaptive threshold. .like If the value is 1, then the feature at that location is determined to be 1. Otherwise, it is 0, and a binary feature matrix is ​​generated. .

[0102] S27, to Perform bit expansion to generate a robust feature map of the same size as the sensitive target image. .

[0103] Just consider him, to Perform bit extension operation: if If so, it expands to a pixel value of 255. If the value is 0, it is expanded to a pixel value of 0. This is used to generate sensitive targets. Extended feature maps of the same size and depth .

[0104] Based on the above embodiments, in an optional embodiment of the present invention, such as Figure 1 As shown, S3 specifically includes the following steps.

[0105] A scrambled sequence is generated based on chaotic mapping parameters. The chaotic mapping parameters include mapping type, initial value, control parameters, number of iterations, or sequence length.

[0106] Using the generated scrambled sequence, sensitive target images are processed. robust feature map Perform scrambling operations separately to obtain encrypted images. and encryption feature map Preferably, the scrambling operation employs a Henon chaotic map.

[0107] Generate a zero-watermark image by performing an XOR operation. : .

[0108] In the formula This represents a scrambling encryption function based on chaotic mapping. This indicates a bitwise XOR operation.

[0109] Specifically, a scrambled sequence is generated based on chaotic mapping parameters (mapping type, initial value, control parameters, number of iterations / sequence length, etc.). This scrambled sequence is then used to process sensitive target images. and extended feature maps Performing the Henon scrambling operation scrambles the pixel positions to obtain an encrypted image. With encryption feature map Finally, an XOR operation is performed to obtain the zero watermark. : .

[0110] Based on the above embodiments, in an optional embodiment of the present invention, such as Figure 4 As shown, S4 specifically includes S41 to S43.

[0111] S41. Package the zero-watermark image, effective region coordinates, and repair algorithm parameters into a record file.

[0112] Preferably, the record file contains the following fields: The standardization rules field is used to record rules for standardizing images to the same size.

[0113] The coordinate field records the coordinates (Coord) of the valid region, which is used to crop the valid region from the standardized image.

[0114] The repair metadata field records the repair algorithm type, key parameters, and random seed used when generating the repaired carrier image, which is used for environmental reconstruction during evidence collection.

[0115] The feature extraction parameter field records the algorithm identifier and binarization strategy for feature extraction.

[0116] The scrambling parameter field records the scrambling algorithm type and parameters.

[0117] Specifically, a record file (e.g., record.json) must contain at least the following fields (example); The record structure version number (schema_version) is used for parsing compatibility and subsequent upgrades (used by the verification / forensics end to select the corresponding field interpretation rules when reading the record).

[0118] Standardization rules (standardize): used to... Unify to the same size (width / height) to ensure that the features and coordinate system can be reproduced at the verification end.

[0119] Effective region coordinates (feature extraction / recovery coordinates) (coord): Provides the cropping box (x0, y0, x1, y1) in the coordinate system specified by coord_system, used to crop the effective region from the standardized image. To extract robust features.

[0120] Inpainting algorithm metadata (inpainting_meta): Records the type of inpainting algorithm (such as PatchMatch / GAN), key parameters, and random seed (RandomSeed) used when generating and publishing the image.

[0121] Pasteback coordinates (reconstruct coordinates) (pasteback_coord): Used to restore sensitive targets. Post back The corresponding positions form a visual reconstructed image (e.g., {xMin, yMin, xMax, yMax}).

[0122] The default parameter set identifier for feature extraction (feature_profile_id): such as the number of DWT layers, wavelet type, block / SVD value rules, etc., is used by the verification end to select the same feature extraction implementation as the registration end. By default, detailed parameters are not transmitted item by item.

[0123] Feature binarization / quantization strategies and parameters (methods, thresholds) (feature_binarize): Used to enhance the consistency of XOR operations. This is a required field in this embodiment.

[0124] Scramble parameters (scramble_algo): include the algorithm type (Henon / Logistic / Arnold, etc.) and the scramble parameter K.

[0125] S42. Generate a random symmetric key Key to encrypt the record file.

[0126] Specifically, the RSI Owner generates a random symmetric key (such as AES-256 Key). Then, the key is used to encrypt the record file containing the sensitive target recovery parameters, generating a ciphertext file record.enc.

[0127] S43. Upload the published image, the zero-watermark image, and the encrypted record file together to the distributed storage to obtain an index.

[0128] Specifically, the images will be anonymized and released. Zero watermark The encrypted record.enc file is uploaded to IPFS. Returning Content Identifiers (CIDs): This retrieves carrier_cid, watermark_cid, and meta_cid (pointing to record.enc).

[0129] Based on the above embodiments, in an optional embodiment of the present invention, such as Figure 4 As shown, S5 includes S51 to S52.

[0130] S51, Using a threshold as The Shamir secret sharing algorithm splits the key into... A secret share. This represents the minimum number of keys required to reconstruct the key.

[0131] S52, will Each secret share is distributed to a hybrid storage layer. The hybrid storage layer includes private cloud nodes, notary nodes, and IPFS nodes.

[0132] First, key splitting (SSS Sharding) is performed. The RSI Owner uses... The threshold-based Shamir's Secret Sharing algorithm splits the key into... Each "secret share". For example: Set =3, =2, meaning 3 shares are generated, and holding any 2 shares is sufficient to reconstruct the original record.

[0133] Then, Shares are distributed: the generated Shares are distributed to different nodes in the Hybrid Storage Layer to eliminate single points of failure and enhance security.

[0134] Node 1: Private Cloud (RSI Owner's private cloud, fully controlled).

[0135] Node 2: Notary Node (Third-party notary node / regulatory node).

[0136] Node 3: IPFS (encrypted and publicly stored, or stored in decentralized confidential storage).

[0137] Finally, register metadata: write carrier_cid, watermark_cid, meta_cid, and the storage index address of each share to the smart contract.

[0138] Based on the above embodiments, in an optional embodiment of the present invention, such as Figure 4 As shown, S6 specifically includes S61 to S64.

[0139] S61. Download the encrypted record file from the distributed storage system, collect enough key shares to reconstruct the key, use the key to decrypt the record file, and parse out the valid region coordinates, scrambling parameters and feature extraction strategy.

[0140] First, a metadata query is performed: The remote sensing image buyer (RSI Buyer) sends a query request to the smart contract (e.g., querying a remote sensing image for a specific area or ID). The smart contract returns the image's Return Content Identifiers (CIDs) and indices, including carrier_cid, watermark_cid, meta_cid, and index information for the recovery key shares.

[0141] Then proceed with the asset download: Download. , And the encrypted record file (record.enc): RSI Buyer downloads the published image directly from the IPFS network based on the returned CID. Zero watermark The encrypted record file (record.enc).

[0142] Next, a share request is made: the remote sensing image user (RSI Buyer) initiates a request to each node in the hybrid storage layer (Private Cloud, Notary Node, IPFS) to obtain Shares. The storage nodes (especially Private Cloud and Notary Node) verify the user's purchase credentials (NFT / Token) or authorization signature. Only after successful verification is the corresponding Share data returned.

[0143] Finally, the key is reconstructed: RSI Buyer has collected at least... 1 valid Shares (e.g., 2). Decrypt record.enc with K to obtain the original record parameter packet. Parse the record to obtain key information such as normalized size, valid region coordinates (Coord), feature extraction parameters, and scrambling key reference.

[0144] S62. Using the effective region coordinates obtained from the analysis, normalize and crop the image to be verified, extract the effective region, and generate a test feature map according to the feature extraction strategy obtained from the analysis. .

[0145] Specifically, will Normalize to the same size W×H according to the normalization rules in the record file, and get Then press the record. The rules and boundary handling rules reproduce the Coord, and are processed according to the Coord. Extract effective region Then, based on the feature extraction algorithm, binarization strategy, and scrambling parameters recorded in the record file, the effective region is... Execute the processing flow that is completely consistent with the RSIowner side: then... Two-stage Discrete Wavelet Transform (DWT) and Block Singular Value Decomposition (SVD) are performed to extract the maximum singular value and generate a binary feature matrix based on a recorded strategy (such as adaptive mean thresholding). Finally, a bit-expansion operation is performed on the binary feature matrix (expanding logic 1 to pixel value 255 and logic 0 to pixel value 0) to generate a test feature map with the same bit depth as the sensitive target. .

[0146] S63. Use the scrambling parameters obtained from the analysis to test the feature map. Encryption is performed to obtain And combined with the obtained zero-watermark image Computational encryption sensitive targets : .

[0147] In the formula This represents a scrambling encryption function based on chaotic mapping. This indicates a bitwise XOR operation.

[0148] Specifically, according to the scrambling parameters in the record, for Perform Henon scrambling to obtain the encryption test feature map. Then perform the XOR operation: .

[0149] S64. Utilize the scrambling parameters and key pair obtained through parsing. Perform the reverse scrambling operation to recover the sensitive target image. .

[0150] Specifically, the scramble_algo parameter recorded in the record is used to... Perform reverse scrambling to restore sensitive target images Then, based on the pasting coordinates contained in the record, ... Post back The corresponding position is used for visual reconstruction.

[0151] Based on the above embodiments, in an optional embodiment of the present invention, the remote sensing image sensitive target secure distribution method based on zero watermark and blockchain further includes an infringement evidence collection step for leaked images.

[0152] Obtain suspected infringing images, calculate their hash values, and retrieve evidence records on the blockchain to obtain the original zero-watermark and record files.

[0153] The sensitive areas of suspected infringing images are masked using the valid region coordinates in the log file.

[0154] The repair algorithm and parameters in the log file are used to re-perform the repair process on the occluded area in order to reconstruct the verification environment.

[0155] Features are extracted from the reconstructed image and combined with the on-chain zero-watermark image to perform blind restoration. If a clear and sensitive target can be restored, it is determined to be an infringement.

[0156] This embodiment achieves full-scenario forensics and auditable evidence storage: it can not only address the theft of published images but also trace the source of leaked original sensitive images. Key coordinates, repair parameters, and hash / CID information are standardized and recorded, and can be permanently stored on the blockchain, facilitating third-party verification of consistency and timestamps.

[0157] Specifically, obtaining suspected infringing images .right Calculate the SHA-256 digest and the perceptual hash (pHash), and add a trusted timestamp.

[0158] It should be noted that infringing samples may fall into the following two categories: Unauthorized use and publication of images: Similar to the release image (May have undergone compression / scaling / cropping during propagation), the sensitive area is the repaired background. Leakage recovery type: For images that have been "restored and pasted back" or directly leaked original images I, whose sensitive areas contain real target content, and which are consistent with the published images. Significantly different.

[0159] use The perceptual hash or related business ID is retrieved on the blockchain to locate the evidence storage record and obtain the original zero watermark. And the index of the record (and the decrypted parameters).

[0160] Verification Environment Reconstruction: If the sample is determined to be of the "Leakage Recovery" type, the sensitive area must first be masked using the Coord coordinates in the record, and then the repair area must be regenerated using the repair algorithm and parameters recorded in the record, so that its background features match the published image. Maintain consistency.

[0161] Blind extraction and recovery: Extracting and recovering data without knowing the original sensitive target, using the processed data... and publicly available on the chain , record, execute the recovery process in Example 4.

[0162] Result determination: If a clear and sensitive target can be recovered. (and If the explicit target or the original filing target has a high degree of semantic consistency, then it constitutes direct evidence of infringement.

[0163] Report generation: Output a complete forensic report containing "on-chain evidence hash + off-chain recovery results + traceability identity ID".

[0164] In summary, when it is necessary to publicly release remote sensing images containing sensitive targets while retaining the ability to restore them to their authorized state, the processing steps of this invention are as follows: I. Zero-watermark generation and registration steps: Sensitive target images are obtained by cropping from the original remote sensing image based on the sensitive area mask. The repair process was then performed on the sensitive areas to obtain the repaired carrier image. (As an image to be released to the public). [The image will be...] Normalize to a uniform size and determine the effective region coordinates (Coord) based on the center point, then extract robust feature maps from the effective region. .right and After performing chaotic scrambling encryption, an XOR operation is performed to obtain a zero-watermark image. Ultimately, it will The Coord, repair algorithm parameters (used for environment reconstruction), and scrambling parameters are packaged and saved to form a reproducible record.

[0165] II. Evidence Binding Steps: Encrypt the log file containing the Coord and repair parameters (generating ciphertext record.enc), and then... , The image hash, CID, and key index information are uploaded to distributed storage via record.enc to obtain the CID. The decryption key is then managed through sharding or hybrid storage. Finally, the image hash, CID, and key index information are written into the blockchain transaction to obtain on-chain timestamps and verifiability.

[0166] III. Sensitive Target Recovery Steps: Image to be Verified Normalize according to the same rules as in the registration phase and determine the Coord, then extract test features. And get messed up . And on Performing reverse scrambling yields a recovered image of the sensitive target. .

[0167] IV. Infringement Evidence Collection and Closed-Loop Verification Steps: Calculate the hash of suspected infringing images and retrieve on-chain evidence records. For leaked images containing genuine sensitive content (i.e., "leakage recovery type"), use the repair algorithm parameters and coordinates of the records to perform verification environment reconstruction (i.e., masking sensitive areas and forcing the same parameters to be used for re-repair to reproduce the background features at the time of registration). Subsequently, utilize on-chain... Blind recovery is performed on the reconstructed features. If a clear sensitive target can be recovered, a complete chain of evidence is constructed, consisting of "on-chain evidence index + off-chain technical reproduction," thus achieving closed-loop rights confirmation.

[0168] Based on the above steps, the publishing phase achieves zero-embedding, seamless publishing, and outputs the repaired carrier image. It retains usability while completely isolating sensitive information. The evidence preservation stage employs a "ciphertext off-chain storage + hash chain solidification" strategy, ensuring both the privacy and security of recovery parameters and achieving immutable ownership binding. During the recovery and evidence collection stage, the legitimate authorizer or evidence collector can use the decrypted parameters (especially the repair algorithm parameters) to accurately reproduce the feature extraction context through the "environment reconstruction" mechanism. This enables stable recovery and closed-loop ownership confirmation of sensitive targets in complex infringement scenarios such as conventional authorization recovery and original image leakage.

[0169] This embodiment of the secure distribution method for sensitive targets in remote sensing images based on zero-watermarking and blockchain addresses the problems of existing sensitive target concealment schemes, namely, the difficulty in balancing the availability of published images with the recoverability of authorized sensitive targets, as well as the challenges of scattered and difficult-to-reproduce and auditable coordinates and parameters required for recovery. This embodiment focuses on "zero-watermark non-embedding," combining robust feature extraction and a reproducible coordinate system to generate a zero-watermark. Optionally, it uses distributed storage and blockchain to bind and store key hashes, CIDs, and Coords, thereby achieving authorized recovery and verifiable traceability while maintaining the quality of published images.

[0170] The secure distribution method for sensitive targets in remote sensing images based on zero watermarking and blockchain of the present invention has the following beneficial effects.

[0171] 1. Non-embedded, low distortion: zero watermark Do not embed published images To avoid secondary distortion, the published image should be identical or nearly identical to the restored image.

[0172] 2. Authorization is recoverable: The authorizing party can, based on... Robust feature recovery of sensitive target map from the image to be verified .

[0173] 3. Enhanced robustness: Improved adaptability to common processing such as compression and noise through "standardization + central benchmark Coord + robust features (such as DWT + SVD)".

[0174] 4. Auditable Evidence: Key credentials and coordinates are solidified through hashing, CID, and blockchain timestamps, facilitating third-party verification of consistency and traceability.

[0175] 5. Simplified Project Implementation: Image generation and zero-watermark registration are decoupled. The verification end only needs to reproduce the Coord and feature processes to restore the project, reducing the complexity of cross-system coupling.

[0176] It is understood that the sensitive image distribution device can be an electronic device with computing power, such as a portable laptop computer, desktop computer, server, smartphone, or tablet computer.

[0177] Obviously, the embodiments described above are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0178] In the several embodiments provided in this invention, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus and method embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0179] In addition, the functional modules in the various embodiments of the present invention can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0180] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, electronic device, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory, random access memory, magnetic disks, or optical disks. It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0181] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” used in the embodiments of this invention are also intended to include the plural forms unless the context clearly indicates otherwise.

[0182] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0183] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0184] The use of "first" and "second" in the embodiments is merely to distinguish similar objects and does not represent a specific ordering of objects. It is understood that "first" and "second" can be interchanged in a specific order or sequence where permitted. It should be understood that the objects distinguished by "first" and "second" can be interchanged where appropriate so that the embodiments described herein can be implemented in an order other than those illustrated or described herein.

[0185] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for secure distribution of sensitive targets in remote sensing images based on zero-watermarking and blockchain, characterized in that, Comprise: S1, extract sensitive target image from original remote sensing image according to mask, and repair sensitive area to generate release image; S2, normalize release image to uniform size and determine effective area, from which robust feature map is extracted; S3, exclusive or sensitive target image and robust feature map after scrambling respectively, to generate zero watermark image; S4, pack zero watermark image, effective area coordinates and repair algorithm parameters into record file and encrypt, then upload to distributed storage together with release image and zero watermark image to obtain index; S5, split the key of record file, and write the index and key split information into the blockchain; S6, when sensitive target needs to be recovered, authorized user obtains data and key according to blockchain record, and recovers feature extraction process from to-be-verified image according to the effective area coordinates and algorithm parameters, and restores sensitive target image by inverse operation combined with the zero watermark image; S3 specifically comprises: Generate scrambling sequence based on chaotic mapping parameters; chaotic mapping parameters include mapping type, initial value, control parameter, iteration number or sequence length; The scrambled sequence is used to scramble the sensitive target image and the robust feature map respectively to obtain an encrypted image and an encrypted feature map respectively Performing exclusive-or operation to generate zero-watermark image : ； In the formula represents a scrambling encryption function based on a chaotic mapping; represents a bitwise XOR operation.

2. The method of claim 1, wherein, S1 specifically comprises: Acquiring remote sensing images Masking sensitive areas ; If the mask is empty, directly use the original remote sensing image as the release image; If there is a sensitive area, the sensitive area bounding box is determined by using a mask, and the sensitive target image is cropped If there are multiple sensitive areas, each area is cropped respectively Filling original remote sensing images with an inpainting algorithm of sensitive areas, making it continuous with the background, getting the publishing image ; wherein the inpainting algorithm is selected from partial differential equation-based inpainting, sample block matching-based inpainting or deep generative model-based inpainting.

3. The method of claim 1, wherein, S2 specifically comprises: publishing an image to a standard size of the image ; to a width of to a height of Reading sensitive target image of the size ; is width; is height; Computing satisfying and , a scale factor where is the base size of the singular value decomposition sub-block; In The rectangular range is calculated as the effective area coordinate Coord based on the center point, and a boundary processing rule is set; the boundary processing rule includes truncation and / or mirror filling and / or zero filling; According to the effective region coordinate Coord, the effective region is cropped from .​ 4. The method of claim 3, wherein, S2 further comprises: effective region performing two-level discrete wavelet transform to extract low-frequency subbands and dividing the low-frequency subbands into sub-blocks Perform singular value decomposition on each sub-block, extract the largest singular value and take the mean of all largest singular values as the threshold Generate a binary feature matrix ; ； wherein and are the row index and column index of the sub-block, respectively; To Perform bit expansion to generate robust feature maps of the same size as the sensitive target image .

5. The method of claim 1, wherein, The scrambling operation uses Henon chaotic mapping.

6. The method of claim 1, wherein, S4 specifically comprises: Pack zero watermark image, effective area coordinates and repair algorithm parameters into record file; Generate a random symmetric key Key to encrypt the record file; Upload release image, zero watermark image and encrypted record file to distributed storage to obtain index; The record file contains the following fields: Standardization rule field, used to record the rule of unifying the image to the same size; Coordinate field, recording effective area coordinates Coord, used to crop the effective area from the standardized image; Repair metadata field, recording the repair algorithm type, key parameters and random seed used when generating the repaired carrier image, used for environment reconstruction during forensic; Feature extraction parameter field, recording the algorithm identifier and binary strategy of feature extraction; Scrambling parameter field, recording the scrambling algorithm type and parameters.

7. The method of claim 1, wherein S5 Comprise: The Shamir secret sharing algorithm with a threshold of is used to split the key Key into secret shares; is the minimum number of secret shares needed to reconstruct the key. Will Each secret share is distributed to a hybrid storage layer, which includes private cloud nodes, notary nodes, and IPFS nodes. 8.The method of claim 1 to 7, wherein, S6 specifically comprises: Download encrypted record file from distributed storage system, collect enough key shares to reconstruct key, decrypt the record file using the key, and parse to obtain effective area coordinates, scrambling parameters and feature extraction strategy; The effective region coordinates obtained by analysis are used to normalize and cut the to-be-verified image, extract the effective region, and generate a test feature map according to the feature extraction strategy obtained by analysis ; The test feature map is encrypted by using the obtained scrambling parameters , and the obtained zero-watermark image is combined to obtain the encrypted sensitive target : ； In the formula represents a scrambling encryption function based on a chaotic mapping; represents a bitwise XOR operation; The scrambling parameters and the key are obtained by analysis An inverse scrambling operation is performed to restore the sensitive target image . 9.The method of claim 1 to 7, wherein, Further comprising the steps of infringing evidence for leaked image: Obtain suspected infringing image, calculate its hash value and retrieve storage record on the blockchain, obtain original zero watermark and record file; Use the effective area coordinates in the record file to mask the sensitive area of the suspected infringing image; Use the repair algorithm and parameters in the record file to re-execute the repair processing of the masked area to reconstruct the verification environment; Extract features on the reconstructed image, and combine the on-chain zero watermark image to perform blind recovery; If the sensitive target can be recovered clearly, it is determined as infringement.

Images