Deep learning-based methods, particularly those employing Siamese network structure, are widely used in remote sensing image change detection. However, extensive experiments reveal that these methods often suffer significant performance degradation when the order of input images is altered. Notably, the ChangeFormer method exhibits a 79.86% drop in the intersection over the union (IoU) metric on the LEVIR-CD dataset, indicating a lack of chronological robustness that severely impacts the practical utility of the change detection model. To address this issue, this article proposes a novel change detection method called chronologic invariant network (CINet), which integrates chronological alignment module and cross-layer feature mixing module. During the feature extraction phase, a chronological alignment module is introduced. This module employs spatially cross-mix feature maps and chronologic reconstruction to reduce temporal information discrepancies between the two branches at the feature level. Additionally, a cross-layer feature mixing module is designed to blend deep and shallow features using a full-scale connection and difference-guided approach, effectively utilizing feature information from every layer of both branches to improve change detection accuracy under varying input sequences. Experimental results on the LEVIR-CD dataset show that CINet achieves a recall of 90.63% and an IoU of 84.13%, which represent improvements of 1.83 percentage points and 1.65 percentage points over ChangeFormer, respectively. Results from multiple datasets further demonstrate that the proposed method consistently maintains high change detection performance and robust chronological invariance, even when the order of input images is altered, outperforming other methods.
WOODCOCKC E, LOVELANDT R, HEROLDM,et al .Transitioning from change detection to monitoring with remote sensing:a paradigm shift[J]. Remote Sensing of Environment,2020,238:111558.
[2]
CHENC F, SONN T, CHANGN B,et al. Multi-decadal mangrove forest change detection and prediction in Honduras,central America,with landsat imagery and a Markov chain model[J].Remote Sensing,2013,5(12):6408-6426.
[3]
MAHDAVIS, SALEHIB, HUANGW M,et al .A PolSAR change detection index based on neighborhood information for flood mapping[J]. Remote Sensing, 2019, 11(16): 1854.
[4]
WUT J, LUOJ C, ZHOUY N,et al .Geo-object-based land cover map update for high-spatial-resolution remote sensing images via change detection and label transfer[J]. Remote Sensing, 2020, 12(1): 174.
SUIH G, FENGW Q, LIW Z,et al .Review of change detection methods for multi-temporal remote sensing imagery[J]. Geomatics and Information Science of Wuhan University, 2018, 43(12): 1885-1898.(in Chinese)
[7]
BAIT, WANGL, YIND M,et al. Deep learning for change detection in remote sensing:a review[J]. Geo-spatial Information Science,2023,26(3):262-288.
[8]
DAUDTR C, SAUXB L, BOULCHA .Fully convolutional Siamese networks for change detection[C]//2018 25th IEEE International Conference on Image Processing (ICIP). Athens,Greece. IEEE,2018:4063-4067.
[9]
ZHANGC X, YUEP, TAPETED,et al .A deeply supervised image fusion network for change detection in high resolution bi-temporal remote sensing images[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 166:183-200.
[10]
CHENH, SHIZ W. A spatial-temporal attention-based method and a new dataset for remote sensing image change detection[J].Remote Sensing, 2020, 12(10): 1662.
[11]
FANGS, LIK Y, SHAOJ Y,et al. SNUNet-CD:a densely connected Siamese network for change detection of VHR images[J]. IEEE Geoscience and Remote Sensing Letters,2021,19:8007805.
[12]
CHENH, QIZ P, SHIZ W. Remote sensing image change detection with transformers[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 60: 5607514.
[13]
FENGY C, XUH H, JIANGJ W,et al. ICIF-net:intra-scale cross-interaction and inter-scale feature fusion network for bitemporal remote sensing images change detection[J].IEEE Transactions on Geoscience and Remote Sensing,2022,60:4410213.
[14]
BANDARAW G C, PATELV M .A transformer-based Siamese network for change detection[C]//IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium. Kuala Lumpur,Malaysia. IEEE, 2022: 207-210.
ZHENGS Y, HUH L, HUANGJ,et al. 2-channel Siamese network for remote sensing change detection[J]. Computer Systems and Applications, 2022, 31(3): 56-64.(in Chinese)
[17]
XIEE Z, WANGW H, YUZ D,et al .SegFormer:simple and efficient design for semantic segmentation with transformers[J]. Advances in Neural Information Processing Systems, 2021, 34: 12077-12090.
[18]
CARIONN, MASSAF, SYNNAEVEG,et al .End-to-end object detection with transformers[M]//Computer Vision-ECCV 2020.Cham: Springer International Publishing, 2020: 213-229.
[19]
DINGX H, ZHANGX Y, HANJ G,et al .Scaling up your kernels to 31 × 31:revisiting large kernel design in CNNs[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New Orleans,LA,USA. IEEE,2022:11953-11965.
[20]
SOWRIRAJANH, YANGJ, NGA Y, et al. Moco pretraining improves representation and transferability of chest X-ray models[C]//Medical Imaging with Deep Learning. Lubeck, Germany, 2021: 728-744.
WANGJ H, QINQ M, GAOZ L,et al .Road extraction from high-resolution remote sensing imagery by including spatial texture feature[J]. Journal of Hunan University (Natural Sciences), 2016, 43(4): 153-156.(in Chinese)
LIUQ H, CAOB, ZENGY L,et al .Recent progresses on the remote sensing radiative transfer modeling over heterogeneous vegetation canopy[J].Journal of Remote Sensing,2016,20(5):933-945.(in Chinese)
[25]
FANGS, LIK Y, LIZ. Changer:feature interaction is what you need for change detection[J]. IEEE Transactions on Geoscience and Remote Sensing,2023, 61: 5610111.
[26]
SUNX D, WUP C, HOIS C H. Face detection using deep learning:an improved faster RCNN approach[J].Neurocomputing,2018, 299: 42-50.
[27]
LIZ L, TANGC, WANGL Z,et al .Remote sensing change detection via temporal feature interaction and guided refinement[J].IEEE Transactions on Geoscience and Remote Sensing,2022,60:5628711.