Learning synthetic aperture radar image despeckling without clean data

Zhang, Gang; Zhi, Li; Li, Xuewei; Xu, Yiqiao

doi:10.1117/1.jrs.14.026518

Cited by 15 publications

(4 citation statements)

References 48 publications

(94 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Those authors have argued that because the network is applied on US images, investigating the semantic information of neighboring video frames and 3D DNN models is important. Other authors have reported better processing times as well [26,27].…”

Section: Related Workmentioning

confidence: 80%

See 1 more Smart Citation

Speckle noise reduction on aligned consecutive ultrasound frames via deep neural network

Mikaeili,

Bilge,

Kılıçaslan

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Despite the benefits of ultrasound imaging systems for medical diagnosis and treatment, ultrasound images are prone to low resolution and contrast due to ultrasound’s inherent attributes, as well as affected by speckle noise that directly influences their quality. In retrospective studies, diverse filters have been applied to minimize the effects of speckle noise and enhance the quality of ultrasound images. In this article, we propose a method of enhancing ultrasound images inspired by synthetic aperture imaging, which provides high-resolution images by adding low-resolution images and measuring the probe’s movement. Our proposed method does not involve synthetic aperture imaging but compensates for the motion effect in the temporal dimension, aligns consecutive images, and stacks aligned images to suppress speckle noise and consequently enhance the resolution of ultrasound images. We exploited deep neural network models to estimate motion parameters between consecutive ultrasound images. In a new database of ultrasound images, we also collected the images’ position-related information implicitly measured in inertial measurement units, which was exploited as a ground truth for motion parameters between consecutive images. Compared with other image-enhancing techniques involving conventional filters and deep neural network modalities, our method demonstrated superiority in enhancing the quality of ultrasound images. We also found that estimating motion parameters directly influenced the success of the image-stacking process. As in ablation studies in deep neural networks, we additionally investigated the effect of dropping some images in the temporal dimension, which revealed that contextual differences and excessive rates of movement in successive ultrasound images weakens the image-stacking process and thus the potential enhancement of ultrasound images.

show abstract

Section: Related Workmentioning

confidence: 80%

“…Another study which deals with speckle noise reduction in optical coherence tomography is [26]. The study introduces a novel self-supervised denoising approach, Sub2Full (S2F), for enhancing image quality in visible light optical coherence tomography (vis-OCT) without the need for clean data.…”

Section: Related Workmentioning

confidence: 99%

Speckle noise reduction on aligned consecutive ultrasound frames via deep neural network

Mikaeili,

Bilge,

Kılıçaslan

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Different observations of the same land area cannot be deemed fully stationary, as the land feature is constantly changing. Addressing this problem, some researchers try to construct the image pairs by using synthesized speckled images [14,32,33], either directly for network training [32,33] or as an initial process [14] to evaluate and compensate for the change that occurs between multi-temporal images acquired over the same area. The training process using synthesized noisy images may inevitably bring in the domain gap.…”

Section: Related Workmentioning

confidence: 99%

SAR Image Despeckling Based on Block-Matching and Noise-Referenced Deep Learning Method

Wang

Yin

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

The noise2noise-based despeckling method, capable of training the despeckling deep neural network with only noisy synthetic aperture radar (SAR) image, has presented very good performance in recent research. This method requires a fine-registered multi-temporal dataset with minor time variance and uses similarity estimation to compensate for the time variance. However, constructing such a training dataset is very time-consuming and may not be viable for a certain practitioner. In this article, we propose a novel single-image-capable speckling method that combines the similarity-based block-matching and noise referenced deep learning network. The denoising network designed for this method is an encoder–decoder convolutional neural network and is accommodated to small image patches. This method firstly constructs a large number of noisy pairs as training input by similarity-based block-matching in either one noisy SAR image or multiple images. Then, the method trains the network in a Siamese manner with two parameter-sharing branches. The proposed method demonstrates favorable despeckling performance with both simulated and real SAR data with respect to other state-of-the-art reference filters. It also presents satisfying generalization capability as the trained network can despeckle well the unseen image of the same sensor. The main advantage of the proposed method is its application flexibility. It could be trained with either one noisy image or multiple images. Furthermore, the despeckling could be inferred by either the ad hoc trained network or a pre-trained one of the same sensor.

show abstract

“…It uses an architecture called Generative Adversarial Network (GAN). However, due to the high computation cost, these are generally applied for low-resolution images, such as in target recognition [19,20], or in a limited scene understanding, such as reducing speckle filters [21,22]. Another promising form of adding synthetic data for SAR is by using simulations.…”

Section: Introductionmentioning

confidence: 99%

Data Augmentation for Building Footprint Segmentation in SAR Images: An Empirical Study

2022

View full text Add to dashboard Cite

Building footprints provide essential information for mapping, disaster management, and other large-scale studies. Synthetic Aperture Radar (SAR) provides consistent data availability over optical images owing to its unique properties, which consequently makes it more challenging to interpret. Previous studies have demonstrated the success of automated methods using Convolutional Neural Networks to detect buildings in Very High Resolution (VHR) SAR images. However, the scarcity of such datasets that are available to the public can limit research progress in this field. We explored the impact of several data augmentation (DA) methods on the performance of building detection on a limited dataset of SAR images. Our results show that geometric transformations are more effective than pixel transformations. The former improves the detection of objects with different scale and rotation variations. The latter creates textural changes that help differentiate edges better, but amplifies non-object patterns, leading to increased false positive predictions. We experimented with applying DA at different stages and concluded that applying similar DA methods in training and inference showed the best performance compared with DA applied only during training. Some DA can alter key features of a building’s representation in radar images. Among them are vertical flips and quarter circle rotations, which yielded the worst performance. DA methods should be used in moderation to prevent unwanted transformations outside the possible object variations. Error analysis, either through statistical methods or manual inspection, is recommended to understand the bias presented in the dataset, which is useful in selecting suitable DAs. The findings from this study can provide potential guidelines for future research in selecting DA methods for segmentation tasks in radar imagery.

show abstract

Learning synthetic aperture radar image despeckling without clean data

Cited by 15 publications

References 48 publications

Speckle noise reduction on aligned consecutive ultrasound frames via deep neural network

Speckle noise reduction on aligned consecutive ultrasound frames via deep neural network

SAR Image Despeckling Based on Block-Matching and Noise-Referenced Deep Learning Method

Data Augmentation for Building Footprint Segmentation in SAR Images: An Empirical Study

Contact Info

Product

Resources

About