Complex-Valued Vs. Real-Valued Convolutional Neural Network for Polsar Data Classification

Asiyabi, Reza Mohammadi; Datcu, Mihai; Nies, Holger; Anghel, Andrei

doi:10.1109/igarss46834.2022.9884081

Cited by 8 publications

(14 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach showcased substantial classification accuracy improvements even with smaller training datasets. Similarly, [44] compared complex-valued and real-valued CNN models for radar classification, revealing the superior performance of complex-valued CNNs in terms of accuracy. Complex-valued CNN models have also been applied to image enhancement and denoising problems.…”

Section: Related Workmentioning

confidence: 99%

Single Radar Image Motion Deblurring Through PSF Estimation and Convolution Regularizer

Sharma,

García-Fernández,

Álvarez-Narciandi

et al. 2024

Trans. Rad. Sys.

View full text Add to dashboard Cite

This paper proposes a deep learning-based motion deblurring method for radar images using point-spread function (PSF) estimations. Motion blur is a common problem in radar imaging due to the movement of the radar platform or the target. The proposed method uses a convolutional neural network (CNN) to learn the mapping between the blurred and sharp images. In addition, the PSF of the motion blur is estimated using a separate CNN. The estimated point spread function (PSF) is utilized in conjunction with the input image to reconstruct a deblurred image. The reconstruction process is further optimized by incorporating the relationship between the input image, PSF, and the ground truth into the training loss term and optimizing it. The network is trained on a large dataset of simulated blurred and sharp radar images with corresponding PSFs. The developed method is evaluated on blurred radar images, subjected to varying degrees and lengths of blur, and compared with state-of-the art methods. The results show that the proposed method outperforms the existing methods both qualitatively and quantitatively. The proposed method can be used for various radar imaging applications, such as target detection and recognition, surveillance and navigation.

show abstract

Section: Related Workmentioning

confidence: 99%

Single Radar Image Motion Deblurring Through PSF Estimation and Convolution Regularizer

Sharma,

García-Fernández,

Álvarez-Narciandi

et al. 2024

Trans. Rad. Sys.

View full text Add to dashboard Cite

show abstract

“…Choosing when and how best to perform the centre of mass estimation and the precise geolocation of ships is also essential, as well as investigating different inputs to the network (e.g. using complex-valued neural networks [49]). Finally, the evaluation of real-time capabilities as well as investigation of any potential changes to detection accuracy (e.g.…”

Section: On-board Data Computationmentioning

confidence: 99%

Ship Detection From Raw SAR Echoes Using Convolutional Neural Networks

De Sousa,

Pilikos,

Azcueta

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Synthetic Aperture Radar (SAR) is an indispensable tool for marine monitoring. Conventional data processing involves data down-linking and on-ground operations for image focusing, analysis and ship detection. These steps take significant amount of time, resulting in potentially critical delays. In this work, we propose a ship detection algorithm that operates directly on raw SAR echoes, based on convolutional neural networks. To evaluate our approach, we performed experiments using raw data simulations and real raw SAR data from Sentinel-1 stripmap mode scenes. Preliminary results on this set show the capability of detecting multiple ships from raw data with similar accuracy as using Single-Look-Complex (SLC) images as input. Simultaneously, running time is reduced significantly, by-passing the image focusing step. This illustrates the great potential of deep learning, moving towards more intelligent SAR systems.

show abstract

“…All of the elements of the CV network, including the weight and bias kernels, different layers (e.g., convolutional, fully connected, batch normalization, and pooling layers), and activation functions, are in the complex domain. However, loss function remains in the real domain to prevent empirical problems during the learning process (more explanation is provided in the loss function subsection) [21], [28]. Comprehensively detailed explanations and equations of the various CV operators are included in this article to provide the possibility of reproducing the network and repeating the experiments.…”

Section: B Complex-valued Operatorsmentioning

confidence: 99%

“…Sigmoid as a special form of the logistic function is another frequently used activation function in deep learning. Sigmoid function is a S-shaped curve with a range between 0 and 1, and as a result it is used for the networks with probability output (See (21) where σ() is the sigmoid function and 𝑥 is a real number).…”

Section: Batch Normalization Layermentioning

confidence: 99%

“…The Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset is used and the results are compared with the state-of-the-art real valued based models. Asiyabi et al [21] carried out a comprehensive comparison between the CV-and RV-CNN for PolSAR data classification and demonstrated the superiority of the CV-CNN. In another recent study, Asiyabi et al [22] evaluated the significance of the coherency preservation for CV deep networks.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Complex-Valued End-to-End Deep Network With Coherency Preservation for Complex-Valued SAR Data Reconstruction and Classification

Asiyabi

Datcu

Anghel

et al. 2023

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Deep learning models have achieved remarkable success in many different fields and attracted many interests. Several researchers attempted to apply deep learning models to Synthetic Aperture Radar (SAR) data processing, but it did not have the same breakthrough as the other fields, including optical remote sensing. SAR data are in complex domain by nature and processing them with Real-Valued (RV) networks neglects the phase component which conveys important and distinctive information. A Complex-Valued (CV) end-to-end deep network is developed in this study for the reconstruction and classification of CV-SAR data. Azimuth subaperture decomposition is utilized to incorporate physics-aware attributes of the CV-SAR into the deep model. Moreover, the correlation coefficient amplitude (Coherence) of the CV-SAR images depends on the SAR system characteristics and physical properties of the target. This coherency should be considered and preserved in the processing chain of the CV-SAR data. The coherency preservation of the CV deep networks for CV-SAR images, which is mostly neglected in the literature, is evaluated in this study. Furthermore, a large-scale CV-SAR annotated dataset for the evaluation of the CV deep networks is lacking. A semantically annotated CV-SAR dataset from Sentinel-1 Single Look Complex StripMap mode data (S1SLC_CVDL dataset) is developed and introduced in this study. The experimental analysis demonstrated the better performance of the developed CV deep network for CV-SAR data classification and reconstruction in comparison to the equivalent RV model and more complicated RV architectures, as well as its coherency preservation and physics-aware capability.

show abstract

Complex-Valued Vs. Real-Valued Convolutional Neural Network for Polsar Data Classification

Cited by 8 publications

References 19 publications

Single Radar Image Motion Deblurring Through PSF Estimation and Convolution Regularizer

Single Radar Image Motion Deblurring Through PSF Estimation and Convolution Regularizer

Ship Detection From Raw SAR Echoes Using Convolutional Neural Networks

Complex-Valued End-to-End Deep Network With Coherency Preservation for Complex-Valued SAR Data Reconstruction and Classification

Contact Info

Product

Resources

About