TY - JOUR
T1 - GITomo-Net
T2 - Geometry-independent deep learning imaging method for SAR tomography
AU - Liu, Changhao
AU - Wang, Yan
AU - Zhang, Guangbin
AU - Ding, Zegang
AU - Zeng, Tao
N1 - Publisher Copyright:
© 2025 The Authors
PY - 2025/2
Y1 - 2025/2
N2 - The utilization of deep learning in Tomographic SAR (TomoSAR) three-dimensional (3D) imaging technology addresses the inefficiency inherent in traditional compressed Sensing (CS)-based TomoSAR algorithms. However, current deep learning TomoSAR imaging methods heavily depend on prior knowledge of observation geometries, as the network training requires a predefined observation prior distribution. Additionally, discrepancies often exist between actual and designed observations in a TomoSAR task, making it challenging to train imaging networks before the task begins. Therefore, the current TomoSAR imaging networks suffer from high costs and lack universality. This paper introduces a new geometry-independent deep learning-based method for TomoSAR without the necessity of geometry as prior information, forming an adaptability to different observation geometries. First, a novel geometry-independent deep learning imaging model is introduced to adapt TomoSAR imaging tasks with unknown observation geometries by consolidating the data features of multiple geometries. Second, a geometry-independent TomoSAR imaging network (GITomo-Net) is proposed to adapt the new geometry-independent deep learning imaging model by introducing a transformation-feature normalization (TFN) module and a fully connected-based feature extraction (FCFE) layer, enabling the network to be capable of handling multi-geometries tasks. The proposed method has been validated using real spaceborne SAR data experiments. The average gradient (AG) and image entropy (IE) metrics for the Regent Beijing Hotel region are 7.11 and 2.85, respectively, while those for the COFCO Plaza region are 3.90 and 1.73, respectively. Compared to the advanced deep learning-based TomoSAR imaging method MAda-Net, the proposed method achieves higher imaging accuracy when network training is conducted without prior knowledge of the observation configuration. Additionally, compared to the advanced CS-based TomoSAR imaging method, the proposed method delivers comparable accuracy while improving efficiency by 51.6 times. The code and the data of our paper are available at https://github.com/Sunshine-lch/Paper_Geometry-Idenpendent-TomoSAR-imaging.git.
AB - The utilization of deep learning in Tomographic SAR (TomoSAR) three-dimensional (3D) imaging technology addresses the inefficiency inherent in traditional compressed Sensing (CS)-based TomoSAR algorithms. However, current deep learning TomoSAR imaging methods heavily depend on prior knowledge of observation geometries, as the network training requires a predefined observation prior distribution. Additionally, discrepancies often exist between actual and designed observations in a TomoSAR task, making it challenging to train imaging networks before the task begins. Therefore, the current TomoSAR imaging networks suffer from high costs and lack universality. This paper introduces a new geometry-independent deep learning-based method for TomoSAR without the necessity of geometry as prior information, forming an adaptability to different observation geometries. First, a novel geometry-independent deep learning imaging model is introduced to adapt TomoSAR imaging tasks with unknown observation geometries by consolidating the data features of multiple geometries. Second, a geometry-independent TomoSAR imaging network (GITomo-Net) is proposed to adapt the new geometry-independent deep learning imaging model by introducing a transformation-feature normalization (TFN) module and a fully connected-based feature extraction (FCFE) layer, enabling the network to be capable of handling multi-geometries tasks. The proposed method has been validated using real spaceborne SAR data experiments. The average gradient (AG) and image entropy (IE) metrics for the Regent Beijing Hotel region are 7.11 and 2.85, respectively, while those for the COFCO Plaza region are 3.90 and 1.73, respectively. Compared to the advanced deep learning-based TomoSAR imaging method MAda-Net, the proposed method achieves higher imaging accuracy when network training is conducted without prior knowledge of the observation configuration. Additionally, compared to the advanced CS-based TomoSAR imaging method, the proposed method delivers comparable accuracy while improving efficiency by 51.6 times. The code and the data of our paper are available at https://github.com/Sunshine-lch/Paper_Geometry-Idenpendent-TomoSAR-imaging.git.
KW - Compressed sensing (CS)
KW - Deep learning imaging (GITomo-net)
KW - Geometry-independent
KW - Tomographic SAR (TomoSAR)
KW - Transformation-feature normalization
UR - http://www.scopus.com/inward/record.url?scp=85215361901&partnerID=8YFLogxK
U2 - 10.1016/j.isprsjprs.2025.01.004
DO - 10.1016/j.isprsjprs.2025.01.004
M3 - Article
AN - SCOPUS:85215361901
SN - 0924-2716
VL - 220
SP - 608
EP - 620
JO - ISPRS Journal of Photogrammetry and Remote Sensing
JF - ISPRS Journal of Photogrammetry and Remote Sensing
ER -