联合多尺度高低频信息融合的变化检测方法

doi:10.19665/j.issn1001-2400.20241011

摘要/Abstract

摘要：

高光谱图像变化检测通过分析同一区域不同时间拍摄的高光谱图像,识别自然场景中地物变化。现有基于深度学习的检测方法主要包括卷积神经网络和基于注意力的方法两类:卷积神经网络方法使用卷积核提取特征,但感受野较小,关注局部信息,缺乏全局建模能力;而基于注意力的方法专注于全局依赖性建模,但对局部特征的捕捉不足,导致检测中漏检、误检现象严重。针对这些不足,提出了一种联合多尺度高低频信息融合的变化检测方法。具体而言,通过金字塔多尺度网络提取多时相高光谱图像的高低频信息,不同尺度的高频信息关注边界区域,低频信息捕捉背景区域细节。高频信息通过残差卷积算子网络提取多尺度局部特征;低频信息通过基于自注意力的网络提取全局特征,以此对图像全局和局部信息进行有效建模。为进一步增强特征提取的有效性,设计了双时相差分分类决策网络,自适应学习各分支的分类权重系数,生成最终的加权预测结果。在三个真实高光谱数据集上的实验表明,方法在可视化和定量性能上均优于现有方法,实现了更高的分类精度和更稳定的变化检测效果。

关键词: 变化检测, 卷积神经网络, 注意力机制, 图像处理, 信息融合

Abstract:

Hyperspectral image change detection has emerged as a crucial technique to identify the change of ground objects in natural scenes by incorporating abundant spectral information in hyperspectral images taken in different phases in the same area.With the thrive of deep learning,hyperspectral image change detection methods can be mainly categorized into the convolutional neural network(CNN)-based and Transformer-based method.The CNN-based methods typically adopt convolutional kernels for feature extraction,which hold the characteristics of a small receptive field and focus on local information on the image,leading to the lack of sufficient modeling of the global information.The Transformer-based methods concentrate mainly on establishing global image dependencies without taking effective local information into consideration,leading to missed or false detections in change detection tasks.To address these limitations,this paper proposes a change detection method based on multi-scale and multi-resolution information fusion.Concretely,a pyramid multi-scale high and low-frequency information extraction network is first designed to capture high-frequency details and the low-frequency content,which attach their attention on the boundary region and background region respectively at different scales of multi-temporal hyperspectral images.High-frequency information is extracted through a residual convolutional network to model local features at different scales,while low-frequency information is captured through an attention-based network to model global features.Furthermore,a dual-time-phase differential classification decision network is proposed to enhance feature extraction by adaptively learning the classification weight coefficients of each branch and generating the final weighted prediction results.The qualitative and quantitative results on three real hyperspectral datasets show that the proposed method not only showcase a superior performance on the change detection task,but also achieves a more stable and higher classification accuracy.

Key words: change detection, convolutional neural networks, attention mechanism, image processing, information fusion

中图分类号:

TP751

曲家慧, 贺杰, 董文倩, 李云松, 张同振, 杨宇菲. 联合多尺度高低频信息融合的变化检测方法[J]. 西安电子科技大学学报, 2025, 52(1): 105-116.

QU Jiahui, HE Jie, DONG Wenqian, LI Yunsong, ZHANG Tongzhen, YANG Yufei. Change detection method based on multi-scale and multi-resolution information fusion[J]. Journal of Xidian University, 2025, 52(1): 105-116.

图/表 11

图1

图2

图3

图4

图5

表1

图6

图7

图8

图9

图10

参考文献 28

[1]	蔡明娇, 蒋俊正, 蔡万源, 等. 张量分解和自适应图全变分的高光谱图像去噪[J]. 西安电子科技大学学报, 2024, 51(2):157-169.
	CAI Mingjiao, JIANG Junzheng, CAI Wanyuan, et al. Hyperspectral Image Denoising Based on Tensor Decomposition and Adaptive Weight Graph Total Variation[J]. Journal of Xidian University, 2024, 51(2):157-169.
[2]	YANG Y G, QU J H, DONG W Q, et al. TMCFN:Text-Supervised Multidimensional Contrastive Fusion Network for Hyperspectral and LiDAR Classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62:1-15.
[3]	QU J H, LIU X Y, DONG W Q, et al. Progressive Multi-Iteration Registration-Fusion Co-Optimization Network for Unregistered Hyperspectral Image Super-Resolution[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62:1-14.
[4]	DONG W Q, LIU S, XIAO S, et al. ISPDiff:Interpretable Scale-Propelled Diffusion Model for Hyperspectral Image Super-Resolution[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62:1-14.
[5]	李娇娇, 刘志强, 宋锐, 等. 一种改进Unet网络的遥感影像分割算法[J]. 西安电子科技大学学报, 2022, 49(6):67-75.
	LI Jiaojiao, LIU Zhiqiang, SONG Rui, et al. Algorithm for Segmentation of Remote Sensing Imagery Using the Improved Unet[J]. Journal of Xidian University, 2022, 49(6):67-75.
[6]	AMINIKHANGHAHI S, COOK D J. A Survey of Methods for Time Series Change Point Detection[J]. Knowledge and Information Systems, 2017, 51(2):339-367. doi: 10.1007/s10115-016-0987-z pmid: 28603327
[7]	HUANG X, WEN D, LI J, et al. Multi-Level Monitoring of Subtle Urban Changes for the Megacities of China Using High-resolution Multi-View Satellite Imagery[J]. Remote Sensing of Environment, 2017, 196:56-75.
[8]	DEMIR B, BOVOLE F, BRUZZONE L. Updating Land-Cover Maps by Classification of Image Time Series:A Novel Change-Detection-Driven Transfer Learning Approach[J]. IEEE Transactions on Geoscience and Remote Sensing, 2013, 51(1):300-312.
[9]	KHAN M J, KHAN H S, YOUSAF A, et al. Modern Trends in Hyperspectral Image Analysis:A Review[J]. IEEE Access, 2018, 6:14118-14129.
[10]	BOVOLO F, BRUZZONE L. A Theoretical Framework for Unsupervised Change Detection Based on Change Vector Analysis in the Polar Domain[J]. IEEE Transactions on Geoscience and Remote Sensing, 2007, 45:218-236.
[11]	THONFELD F, FEILHAUER H, BRAUN M, et al. Robust Change Vector Analysis(RCVA) for Multi-Sensor Very High Resolution Optical Satellite Data[J]. International Journal of Applied Earth Observation and Geoinformation, 2016, 50:131-140.
[12]	DENG J S, WANG K, DENG Y H, et al. PCA-Based Land-Use Change Detection and Analysis Using Multitemporal and Multisensor Satellite Data[J]. International Journal of Remote Sensing, 2008, 29(16):4823-4838.
[13]	WU C, DU B, ZHANG L. Slow Feature Analysis for Change Detection in Multispectral Imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(5):2858-2874.
[14]	CANTY M J, NIELSEN A A. Automatic Radiometric Normalization of Multitemporal Satellite Imagery with the Iteratively Re-Weighted MAD Transformation[J]. Remote Sensing of Environment, 2008, 112(3):1025-1036.
[15]	NEMMOUR H, CHIBANI Y. Multiple Support Vector Machines for Land Cover Change Detection:An Application for Mapping Urban Extensions[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2006, 61(2):125-133.
[16]	HOBERG T, ROTTENSTEINER F, FEITOSA R Q, et al. Conditional Random Fields for Multitemporal and Multiscale Classification of Optical Satellite Imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(2):659-673.
[17]	LV P, ZHONG Y, ZHAN J, et al. Unsupervised Change Detection Based on Hybrid Conditional Random Field Model for High Spatial Resolution Remote Sensing Imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(7):4002-4015.
[18]	QU J H, DONG W Q, LI Y S, et al. An Interpretable Unsupervised Unrolling Network for Hyperspectral Pansharpening[J]. IEEE Transactions on Cybernetics, 2023, 53(12):7943-7956.
[19]	MOU L, BRUZZONE L, ZHU X. Learning Spectral-Spatial-Temporal Features via a Recurrent Convolutional Neural Network for Change Detection in Multispectral Imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(2):924-935.
[20]	LIN Y, LI S T, FANG L Y, et al. Multispectral Change Detectionwith Bilinear Convolutional Neural Networks[J]. IEEE Geoscience and Remote Sensing Letters, 2020, 17(10):757-761.
[21]	ZHAN T M, SONG B, SUN L, et al. TDSSC:A Three-Directions Spectral-Spatial Convolution Neural Network for Hyperspectral Image Change Detection[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14:377-388.
[22]	刘晓雯, 郭继昌, 郑司达. 采用渐进式网络的弱监督显著性目标检测算法[J]. 西安电子科技大学学报, 2023, 50(1):48-57.
	LIU Xiaowen, GUO Jichang, ZHENG Sida. Weakly-Supervised Salient Object Detection with the Multi-Scale Progressive Network[J]. Journal of Xidian University, 2023, 50(1):48-57.
[23]	王娟, 刘子杉, 武明虎, 等. 融合超分辨率重建技术的多尺度目标检测算法[J]. 西安电子科技大学学报, 2023, 50(3):122-131.
	WANG Juan, LIU Zishan, WU Minghu, et al. Multi-Scale Object Detection Algorithm Combined with Super-Resolution Reconstruction Technology[J]. Journal of Xidian University, 2023, 50(3):122-131.
[24]	YANG Y F, QU J H, XIAO S, et al. A Deep Multiscale Pyramid Network Enhancedwith Spatial-Spectral Residual Attention for Hyperspectral Image Change Detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60:1-13.
[25]	WANG X H, ZHAO K Y, ZHAO X Y, et al. TriTF:A Triplet Transformer Framework Based on Parents and Brother Attention for Hyperspectral Image Change Detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61:1-13.
[26]	LUO F L, ZHOU T Y, LIU J M, et al. Multiscale Diff-Changed Feature Fusion Network for Hyperspectral Image Change Detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61:1-13.
[27]	DING J, LI X, XIANG S, et al. Multilevel Features Fused and Change Information Enhanced Neural Network for Hyperspectral Image Change Detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62:1-13.
[28]	CHEN H, SHI Z W. A Spatial-Temporal Attention-Based Method and a New Dataset for Remote Sensing Image Change Detection[J]. Remote Sensing, 2020, 12(10):1662.

对比方法	Farmland		Santa Barbara		Bay Area
对比方法	OA	Kappa	OA	Kappa	OA	Kappa
CVA	0.878 7	0.738 2	0.727 8	0.430 3	0.859 9	0.630 3
PCA	0.889 2	0.732 2	0.788 1	0.569 2	0.871 2	0.663 5
SVM	0.890 9	0.873 7	0.865 7	0.733 3	0.971 4	0.904 6
BIT	0.958 3	0.902 0	0.992 2	0.983 7	0.994 9	0.988 2
ReCNN	0.960 1	0.965 0	0.997 1	0.999 7	0.995 4	0.996 2
BCNN	0.955 6	0.896 4	0.997 7	0.995 2	0.995 9	0.990 3
MSDFFN	0.963 1	0.914 9	0.998 7	0.997 4	0.995 7	0.990 1
Proposed	0.965 0	0.918 1	0.999 7	0.999 3	0.996 2	0.991 1