Zero-watermark copyright protection method for remote sensing images based on coupled neural P system and blockchain

doi:10.11947/j.AGCS.2025.20250156

Abstract

Abstract:

Currently, mainstream zero-watermark approaches fail to adequately capture the unique spectral-spatial multidimensional characteristics of remote sensing images. This limitation renders them vulnerable to targeted attacks. Additionally, their reliance on third-party intellectual property management organizations introduces potential risks of data tampering and undermines mutual trust in transactions. To this end, a zero-watermark copyright protection method for remote sensing images based on coupled neural P system and blockchain is proposed. Firstly, the non-subsampled shearlet transform is used to obtain the corresponding low-frequency components by multi-scale decomposition of the R, G, and B bands of the remote sensing image, respectively. Secondly, a coupled neural P system model of multilayer perception is constructed to simulate the coupled interaction of neurons to extract the spatiotemporal dynamic features of each low-frequency component, and the external inputs of the model are optimized according to the multi-scale morphological gradient to enhance the spatial correlation of the features. Thirdly, an encrypted feature image is generated using an asymmetric Tent map, which is then scrambled and subjected to XOR operations to form the zero-watermark. Finally, a decentralized copyright registration framework is established by integrating Hyperledger Fabric and the Inter Planetary File System. This framework leverages smart contracts to facilitate the on-chain storage and automated verification of copyright information. The experimental results show that the normalized correlation coefficient of the proposed method stably stays above 0.99 in the face of different degrees of geometric, non-geometric, and combinatorial attacks, demonstrating high robustness and attack resistance.

Key words: remote sensing images, blockchain, coupled neural P system, zero-watermark, copyright protection

CLC Number:

P237

Zhaoyang HOU, Haowen YAN, Liming ZHANG, Rongjuan MA, Ruitao QU. Zero-watermark copyright protection method for remote sensing images based on coupled neural P system and blockchain[J]. Acta Geodaetica et Cartographica Sinica, 2025, 54(12): 2247-2261.

Figures/Tables 13

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Fig. 6

Tab. 1

Tab. 2

Fig. 7

Tab. 3

Experimental results for non-geometric attacks"

攻击方式	参数	PSNR	DFT-DCT^[11]		DCT-DFT^[12]		BEMD-DFT^[14]		NSST-SVD^[15]		本文方法
攻击方式	参数	PSNR	BER	NC	BER	NC	BER	NC	BER	NC	BER	NC
均值滤波	[3，3]	28.908	0.006	0.988	0.006	0.989	0.002	0.995	0.006	0.987	0.000	1.000
	[5，5]	26.672	0.010	0.979	0.009	0.981	0.004	0.992	0.009	0.981	0.000	1.000
	[7，7]	25.411	0.015	0.970	0.013	0.974	0.006	0.987	0.013	0.975	0.000	1.000
	[9，9]	24.552	0.020	0.960	0.017	0.966	0.009	0.982	0.016	0.968	0.000	0.999
中值滤波	[3，3]	29.102	0.018	0.964	0.017	0.966	0.003	0.993	0.004	0.991	0.000	1.000
	[5，5]	27.176	0.031	0.937	0.030	0.939	0.007	0.986	0.009	0.982	0.000	1.000
	[7，7]	25.997	0.044	0.912	0.042	0.915	0.010	0.979	0.013	0.974	0.000	0.999
	[9，9]	25.168	0.055	0.889	0.053	0.893	0.014	0.972	0.016	0.967	0.001	0.998
高斯滤波	[3，3]	29.858	0.005	0.989	0.005	0.990	0.003	0.994	0.006	0.989	0.000	1.000
	[5，5]	28.586	0.007	0.985	0.007	0.987	0.004	0.991	0.007	0.985	0.000	1.000
	[7，7]	28.367	0.008	0.984	0.007	0.986	0.006	0.987	0.008	0.984	0.000	0.999
	[9，9]	28，247	0.008	0.984	0.007	0.986	0.007	0.986	0.008	0.984	0.001	0.998
维纳滤波	[3，3]	43.026	0.002	0.997	0.001	0.997	0.000	1.000	0.000	0.999	0.000	1.000
	[5，5]	38.980	0.002	0.995	0.002	0.996	0.000	0.999	0.001	0.999	0.000	1.000
	[7，7]	36.787	0.003	0.994	0.003	0.994	0.000	0.999	0.001	0.998	0.000	1.000
	[9，9]	35.386	0.004	0.992	0.004	0.992	0.001	0.998	0.001	0.998	0.000	1.000
压缩	10	27.848	0.037	0.925	0.037	0.926	0.013	0.972	0.005	0.989	0.006	0.988
	30	32.496	0.013	0.974	0.013	0.975	0.005	0.991	0.001	0.997	0.001	0.999
	50	34.567	0.008	0.983	0.008	0.985	0.003	0.996	0.001	0.998	0.000	1.000
锐化	5	23.978	0.031	0.937	0.030	0.940	0.006	0.987	0.010	0.980	0.000	0.999
	7	21.390	0.043	0.914	0.042	0.916	0.011	0.978	0.015	0.970	0.001	0.998
	9	19.618	0.054	0.892	0.052	0.894	0.015	0.970	0.020	0.960	0.002	0.996
椒盐噪声	0.03	20.567	0.040	0.918	0.039	0.921	0.006	0.988	0.009	0.982	0.001	0.998
	0.05	18.345	0.046	0.907	0.044	0.910	0.008	0.983	0.012	0.976	0.001	0.997
	0.1	15.333	0.063	0.872	0.062	0.873	0.012	0.976	0.018	0.963	0.001	0.997
高斯噪声	0.03	19.757	0.032	0.936	0.032	0.934	0.009	0.982	0.011	0.977	0.000	0.999
	0.05	19.169	0.039	0.921	0.043	0.923	0.013	0.974	0.015	0.969	0.001	0.998
	0.1	17.156	0.048	0.903	0.046	0.906	0.018	0.964	0.021	0.958	0.001	0.998
泊松噪声	—	28.047	0.012	0.975	0.012	0.976	0.002	0.996	0.002	0.996	0.000	1.000

Tab. 3

Fig. 8

Tab. 4

Fig. 9

References 28

[1]	ZHANG Xinchang, SHI Qian, SUN Ying, et al. The review of land use/land cover mapping AI methodology and application in the era of remote sensing big data[J]. Journal of Geodesy and Geoinformation Science, 2024, 7(3): 1-23.
[2]	WANG Mengyu, YAN Zhiyuan, FENG Yingchao, et al. Multi-task learning of semantic segmentation and height estimation for multi-modal remote sensing images[J]. Journal of Geodesy and Geoinformation Science, 2023, 6(4): 27-39.
[3]	LI Jiaxin, HONG Danfeng, GAO Lianru, et al. Deep learning in multimodal remote sensing data fusion: a comprehensive review[J]. International Journal of Applied Earth Observation and Geoinformation, 2022, 112: 102926.
[4]	HOU Zhaoyang, YAN Haowen, ZHANG Liming, et al. A secure and efficient remote sensing image retrieval method with verifiable and traceable in cloud environment[J]. IEEE Transactions on Geoscience and Remote Sensing, 2025, 63: 4701216.
[5]	朱长青, 任娜, 徐鼎捷. 地理信息安全技术研究进展与展望[J]. 测绘学报, 2022, 51(6): 1017-1028. DOI: . doi: 10.11947/j.AGCS.2022.20220172
	ZHU Changqing, REN Na, XU Dingjie. Geo-information security technology: progress and prospects[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(6): 1017-1028. DOI: . doi: 10.11947/j.AGCS.2022.20220172
[6]	奚旭, 张新长. 基于区间映射和最大扰动区域的矢量地图可逆水印算法[J]. 测绘学报, 2022, 51(11): 2379-2389. DOI: . doi: 10.11947/j.AGCS.2022.20210552
	XI Xu, ZHANG Xinchang. Reversible watermarking for vector maps based on interval mapping and maximum perturbation region[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(11): 2379-2389. DOI: . doi: 10.11947/j.AGCS.2022.20210552
[7]	REN Na, GUO Shuitao, ZHU Changqing, et al. A zero-watermarking scheme based on spatial topological relations for vector dataset[J]. Expert Systems with Applications, 2023, 226: 120217.
[8]	朱长青, 徐鼎捷, 任娜, 等. 区块链与数字水印相结合的地理数据交易存证及版权保护模型[J]. 测绘学报, 2021, 50(12): 1694-1704. DOI: . doi: 10.11947/j.AGCS.2021.20200559
	ZHU Changqing, XU Dingjie, REN Na, et al. Model and implementation of geographic data transaction certificate and copyright protection based on blockchain and digital watermarking[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(12): 1694-1704. DOI: . doi: 10.11947/j.AGCS.2021.20200559
[9]	赵蕾, 桂小林, 邵屹杨, 等. 数字图像多功能水印综述[J]. 计算机辅助设计与图形学学报, 2024, 36(2): 195-222.
	ZHAO Lei, GUI Xiaolin, SHAO Yiyang, et al. Survey on multipurpose digital image watermarking[J]. Journal of Computer-Aided Design & Computer Graphics, 2024, 36(2): 195-222.
[10]	TAN Tao, ZHANG Liming, ZHANG Mingwang, et al. Commutative encryption and watermarking algorithm based on compound chaotic systems and zero-watermarking for vector map[J]. Computers & Geosciences, 2024, 184: 105530.
[11]	XU Dingjie, REN Na, ZHU Changqing. High-resolution remote sensing image zero-watermarking algorithm based on blockchain and SDAE[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024, 17: 323-339.
[12]	JING Liang, SUN Zhentao, CHEN Kexin, et al. Remote sensing image zero watermarking algorithm based on DFT[J]. Journal of Physics: Conference Series, 2021, 1865(4): 042034.
[13]	XING Siming, LI Tongyi, LIANG Jing. A zero-watermark hybrid algorithm for remote sensing images based on DCT and DFT[J]. Journal of Physics: Conference Series, 2021, 1952(2): 022049.
[14]	XING Siming, CHENG Zhilin, JI Chunyu, et al. Remote sensing image zero-watermark algorithm based on BEMD[J]. Journal of Physics: Conference Series, 2021, 1865(4): 042035.
[15]	徐依朋, 胡坤, 王小超, 等. 基于BEMD和DFT的遥感图像零水印算法[J]. 计算机辅助设计与图形学学报, 2022, 34(11): 1731-1741.
	XU Yipeng, HU Kun, WANG Xiaochao, et al. Zero-watermarking algorithm for remote sensing image via BEMD and DFT[J]. Journal of Computer-Aided Design & Computer Graphics, 2022, 34(11): 1731-1741.
[16]	XU Dingjie, ZHU Changqing, REN Na. A zero-watermark algorithm for copyright protection of remote sensing image based on blockchain[C]//Proceedings of 2022 International Conference on Blockchain Technology and Information Security. Huaihua: IEEE, 2022: 111-116.
[17]	OUYANG Xue, XU Yanyan, MAO Yangsu, et al. Blockchain-assisted verifiable and secure remote sensing image retrieval in cloud environment[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023, 16: 1378-1389.
[18]	SONG Hongyu, ZHU Nafei, XUE Ruixin, et al. Proof-of-contribution consensus mechanism for blockchain and its application in intellectual property protection[J]. Information Processing & Management, 2021, 58(3): 102507.
[19]	PENG Shaoliang, BAO Wenxuan, LIU Hao, et al. A peer-to-peer file storage and sharing system based on consortium blockchain[J]. Future Generation Computer Systems, 2023, 141: 197-204.
[20]	侯昭阳, 吕开云, 龚循强, 等. 一种结合低级视觉特征和PAPCNN的NSST域遥感影像融合方法[J]. 武汉大学学报(信息科学版), 2023, 48(6): 960-969.
	HOU Zhaoyang, LÜ Kaiyun, GONG Xunqiang, et al. Remote sensing image fusion based on low-level visual features and PAPCNN in NSST domain[J]. Geomatics and Information Science of Wuhan University, 2023, 48(6): 960-969.
[21]	ROY K, JAISWAL A, PANDA P. Towards spike-based machine intelligence with neuromorphic computing[J]. Nature, 2019, 575(7784): 607-617.
[22]	龚循强, 侯昭阳, 吕开云, 等. 结合改进Laplacian能量和参数自适应双通道ULPCNN的遥感影像融合方法[J]. 测绘学报, 2023, 52(11): 1892-1905. DOI: . doi: 10.11947/j.AGCS.2023.20220541
	GONG Xunqiang, HOU Zhaoyang, LÜ Kaiyun. Remote sensing image fusion method combining improved Laplacian energy and parameter adaptive dual-channel unit-linking pulse coupled neural network[J]. Acta Geodaetica et Cartographica Sinica, 2023, 52(11): 1892-1905. DOI: . doi: 10.11947/j.AGCS.2023.20220541
[23]	PENG Hong, WANG Jun. Coupled neural P systems[J]. IEEE Transactions on Neural Networks and Learning Systems, 2018, 30(6): 1672-1682.
[24]	GONG Xunqiang, HOU Zhaoyang, WAN Yuting, et al. Multispectral and SAR image fusion for multiscale decomposition based on least squares optimization rolling guidance filtering[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 1-20.
[25]	HOU Zhaoyang, LÜ Kaiyun, GONG Xunqiang, et al. A remote sensing image fusion method combining low-level visual features and parameter-adaptive dual-channel pulse-coupled neural network[J]. Remote Sensing, 2023, 15(2): 344.
[26]	YU Chengting, GU Zheming, LI Da, et al. STSC-SNN: spatio-temporal synaptic connection with temporal convolution and attention for spiking neural networks[J]. Frontiers in Neuroscience, 2022, 16: 1079357.
[27]	EL HAJJI M, ES-SAADY Y, AIT ADDI M, et al. Optimization of agrifood supply chains using Hyperledger Fabric blockchain technology[J]. Computers and Electronics in Agriculture, 2024, 227: 109503.
[28]	ZHU Changpeng, FAN Bincheng, XIANG Nan, et al. A fine-grained compression scheme for block transmission acceleration over IPFS network[J]. Computer Networks, 2025, 261: 111131.

影像	飞机场1	飞机场2	储油罐1	储油罐2	立交桥1	立交桥2	操场1	操场2
飞机场1	1.000 0	0.658 3	0.528 9	0.482 1	0.379 4	0.472 9	0.527 3	0.594 6
飞机场2	0.658 3	1.000 0	0.563 2	0.529 4	0.527 8	0.514 7	0.612 9	0.631 8
储油罐1	0.528 9	0.563 2	1.000 0	0.624 8	0.492 4	0.472 8	0.492 7	0.548 7
储油罐2	0.482 1	0.529 4	0.624 8	1.000 0	0.484 5	0.527 3	0.523 8	0.524 3
立交桥1	0.379 4	0.527 8	0.492 4	0.484 5	1.000 0	0.652 8	0.638 1	0.591 3
立交桥2	0.472 9	0.514 7	0.472 8	0.527 3	0.652 8	1.000 0	0.617 7	0.583 6
操场1	0.527 3	0.612 9	0.492 7	0.523 8	0.638 1	0.617 7	1.000 0	0.683 5
操场2	0.594 6	0.631 8	0.548 7	0.524 3	0.591 3	0.583 6	0.683 5	1.000 0

攻击方式	参数	PSNR	DFT-DCT^[11]		DCT-DFT^[12]		BEMD-DFT^[14]		NSST-SVD^[15]		本文方法
攻击方式	参数	PSNR	BER	NC	BER	NC	BER	NC	BER	NC	BER	NC
裁剪	左上角1/4	13.339	0.184	0.629	0.184	0.628	0.077	0.843	0.085	0.827	0.003	0.994
裁剪	中心1/4	12.950	0.201	0.593	0.197	0.605	0.085	0.827	0.102	0.794	0.003	0.994
翻转	上下	13.750	0.491	0.102	0.497	0.067	0.014	0.972	0.018	0.963	0.000	1.000
翻转	左右	13.612	0.503	0.062	0.489	0.128	0.020	0.959	0.021	0.957	0.000	1.000
旋转	5°	12.962	0.255	0.482	0.065	0.867	0.038	0.922	0.083	0.832	0.001	0.997
	10°	11.403	0.262	0.469	0.097	0.822	0.056	0.886	0.092	0.814	0.001	0.996
	20°	10.144	0.274	0.447	0.109	0.776	0.103	0.791	0.115	0.767	0.002	0.995
缩放	0.25	26.206	0.028	0.944	0.027	0.945	0.002	0.995	0.003	0.995	0.000	1.000
	0.5	28.128	0.025	0.948	0.025	0.950	0.002	0.996	0.002	0.995	0.000	1.000
	2	38.847	0.002	0.997	0.001	0.997	0.000	0.999	0.000	1.000	0.000	1.000
	4	39，187	0.002	0.997	0.001	0.998	0.000	1.000	0.000	1.000	0.000	1.000