高光譜影像透過數百個連續波段提供精細的光譜資訊，能夠實現精確的物質識別與詳細的地表特徵描述。高光譜變遷偵測旨在利用這些豐富的光譜資訊，分析地表隨時間產生的變遷。然而，由於遙測場景的空間覆蓋範圍廣大，獲取高品質的標註資料仍面臨巨大挑戰。人工標註過程不僅昂貴且耗時，使其難以應用於需要即時響應的載具邊緣運算。另外，監督式模型在特定場景訓練後，應用於未知環境時的泛化能力往往顯著下降。因此，開發能夠在無需標註資料的情況下維持高偵測準確度的非監督式變遷偵測方法，已成為重要的研究方向。非監督式變遷偵測的主要挑戰在於，雙時相影像常因大氣條件、季節影響或光照變化產生顯著的光譜偏移與亮度差異，導致這些與地表變遷無關的差異被誤判為真實變化。為了解決此問題，本研究提出了一套名為 SBQ-HCD 的非監督式框架，利用淺層雙向量子神經網路進行高光譜變遷偵測。SBQ-HCD 的核心在於並行的雙向光譜映射機制，該機制能同步學習正向（X to Y）與逆向（Y to X）的光譜對齊。本研究利用結合殘差結構的單層量子神經網路作為映射函數，以極低的參數開銷捕捉複雜的非線性光譜差異。為了實現非監督式學習，本框架採用自動訓練集精煉（ARTS）模組，透過迭代程序識別高信賴度的未變化像素。透過強制執行雙向一致性約束，該框架能有效抑制由光譜雜訊引起的方向性偏見與虛假變化。在多個大規模基準資料集上的廣泛實驗證明，SBQ-HCD 在偵測準確度與穩定性上均顯著優於現有的先進方法。值得注意的是，本框架具備極佳的輕量化特性，其訓練速度比傳統基於深度學習的方法快數十倍，證明了其在即時變遷偵測任務中的卓越可擴展性與實用價值。

Hyperspectral change detection (HCD) identifies land surface variations by exploiting rich spectral information across hundreds of contiguous bands. However, acquiring labeled data for HCD is challenging due to the high cost and time required for manual annotation over large spatial coverages, making supervised methods unsuitable for real-time applications like onboard edge computing. This research proposes SBQ-HCD, a novel unsupervised framework featuring a shallow bi-directional quantum neural network. The core mechanism utilizes parallel bi-directional spectral mapping to simultaneously learn forward and backward alignments between multi-temporal images. We employ a single-layer quantum neural network (QNN) with a residual structure to capture complex non-linear discrepancies with minimal parameters. To enable unsupervised learning, an Automatic Refinement of the Training Set (ARTS) module iteratively identifies high-confidence unchanged pixels. By enforcing bi-directional consistency, the framework suppresses directional bias and pseudo-changes caused by noise. Experimental results on large-scale benchmarks demonstrate that SBQ-HCD significantly outperforms state-of-the-art methods in accuracy and stability. Notably, the framework is highly lightweight, achieving inference speeds dozens of times faster than traditional deep learning approaches, proving its suitability for real-time HCD tasks.

[1] F. Bovolo and L. Bruzzone, “A theoretical framework for unsupervised change detection based on change vector analysis in the polar domain,” IEEE Transactions on Geoscience and Remote Sensing, vol. 45, no. 1, pp. 218–236, 2006.
[2] T. Celik, “Unsupervised change detection in satellite images using principal component analysis and kmeans clustering,” IEEE Geoscience and Remote Sensing Letters, vol. 6, no. 4, pp. 772–776, 2009.
[3] Z. Hou, W. Li, R. Tao, and Q. Du, “Three-order tucker decomposition and reconstruction detector for unsupervised hyperspectral change detection,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 14, pp. 6194–6205, 2021.
[4] M. Hu, C. Wu, and L. Zhang, “HyperNet: Self-supervised hyperspectral spatial–spectral feature understanding network for hyperspectral change detection,” IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1–17, 2022.
[5] F. Jiang, S. Zhang, M. Zhang, M. Gong, Y. Zhou, W. Zhao, and Z. Guan, “Adaptive center-focused hybrid attention network for change detection in hyperspectral images,” IEEE Transactions on Geoscience and Remote Sensing, 2025.
[6] J. Deng, K. Wang, Y. Deng, and G. Qi, “PCA-based land-use change detection and analysis using multitemporal and multisensor satellite data,” Int. J. Remote Sens., vol. 29, no. 16, pp. 4823–4838, 2008.
[7] A. A. Nielsen, K. Conradsen, and J. J. Simpson, “Multivariate alteration detection (MAD) and MAF postprocessing in multispectral, bitemporal image data: New approaches to change detection studies,” Remote Sens. Environ., vol. 64, no. 1, pp. 1–19, 1998.
[8] T.-H. Lin and C.-H. Lin, “Hyperspectral change detection using semi-supervised graph neural network and convex deep learning,” IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1–18, 2023.
[9] C.-H. Lin, T.-H. Lin, and J. Chanussot, “Quantum information-empowered graph neural network for hyperspectral change detection,” IEEE Transactions on Geoscience and Remote Sensing, 2024.
[10] Q. Wang, Z. Yuan, Q. Du, and X. Li, “GETNET: A general end-to-end 2-D CNN framework for hyperspectral image change detection,” IEEE Trans. Geosci. Remote Sens., vol. 57, no. 1, pp. 3–13, 2018.
[11] R. Song, W. Ni, W. Cheng, and X. Wang, “CSANet: Cross-temporal interaction symmetric attention network for hyperspectral image change detection,” IEEE Geosci. Remote Sens. Lett., vol. 19, pp. 1–5, 2022. 35
[12] R. H. Yuhas, A. F. Goetz, and J. W. Boardman, “Discrimination among semi-arid landscape endmembers using the spectral angle mapper (SAM) algorithm,” in JPL, Summaries of the Third Annual JPL Airborne Geoscience Workshop. Volume 1: AVIRIS Workshop, 1992.
[13] B. Xu, N. Wang, T. Chen, and M. Li, “Empirical evaluation of rectified activations in convolutional network,” arXiv preprint arXiv:1505.00853, 2015.
[14] J. R. McClean, S. Boixo, V. N. Smelyanskiy, R. Babbush, and H. Neven, “Barren plateaus in quantum neural network training landscapes,” Nature communications, vol. 9, no. 1, p. 4812, 2018.
[15] Z. Wu, W. Zhu, J. Chanussot, Y. Xu, and S. Osher, “Hyperspectral anomaly detection via global and local joint modeling of background,” IEEE Trans. Signal Process., vol. 67, no. 14, pp. 3858–3869, 2019.
[16] W.-C. Zheng, C.-H. Lin, K.-H. Tseng, C.-Y. Huang, T.-H. Lin, C.-H. Wang, and C.-Y. Chi, “Unsupervised change detection in multitemporal multispectral satellite images: A convex relaxation approach,” in IEEE IGARSS, Yokohama, Japan, Jul. 2019, pp. 1546–1549.
[17] K. Janocha and W. M. Czarnecki, “On loss functions for deep neural networks in classification,” arXiv preprint arXiv:1702.05659, 2017.
[18] K. Diederik, “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, 2014.
[19] S. Liu, D. Marinelli, L. Bruzzone, and F. Bovolo, “A review of change detection in multitemporal hyperspectral images: Current techniques, applications, and challenges,” IEEE Geoscience and Remote Sensing Magazine, vol. 7, no. 2, pp. 140–158, 2019.
[20] Q. Guo, J. Zhang, C. Zhong, and Y. Zhang, “Change detection for hyperspectral images via convolutional sparse analysis and temporal spectral unmixing,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 14, pp. 4417–4426, 2021.
[21] Y. Wang, D. Hong, J. Sha, L. Gao, L. Liu, Y. Zhang, and X. Rong, “Spectral–spatial–temporal transformers for hyperspectral image change detection,” IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1–14, 2022.
[22] Q. Guo, J. Zhang, C. Zhong, and Y. Zhang, “Change detection for hyperspectral images via convolutional sparse analysis and temporal spectral unmixing,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 14, pp. 4417–4426, 2021.
[23] Q. Wang, Z. Yuan, Q. Du, and X. Li, “GETNET: A general end-to-end 2-D CNN framework for hyperspectral image change detection,” IEEE Trans. Geosci. Remote Sens., vol. 57, no. 1, pp. 3–13, 2018.
[24] R. L. Brennan and D. J. Prediger, “Coefficient kappa: Some uses, misuses, and alternatives,” Educ. Psychol. Meas., vol. 41, no. 3, pp. 687–699, 1981.