SquiggleMilli

2021 ◽  
Vol 5 (3) ◽  
pp. 1-26
Author(s):  
Hem Regmi ◽  
Moh Sabbir Saadat ◽  
Sanjib Sur ◽  
Srihari Nelakuditi
Keyword(s):  
Performance Improvement ◽  
Motion Compensation ◽  
Rigid Bodies ◽  
Synthetic Aperture ◽  
Security Applications ◽  
Spatial Frequencies ◽  
Machine Learning Model ◽  
Training Samples ◽  
Low Visibility ◽  
Limited Training Samples

This paper proposes SquiggleMilli, a system that approximates traditional Synthetic Aperture Radar (SAR) imaging on mobile millimeter-wave (mmWave) devices. The system is capable of imaging through obstructions, such as clothing, and under low visibility conditions. Unlike traditional SAR that relies on mechanical controllers or rigid bodies, SquiggleMilli is based on the hand-held, fluidic motion of the mmWave device. It enables mmWave imaging in hand-held settings by re-thinking existing motion compensation, compressed sensing, and voxel segmentation. Since mmWave imaging suffers from poor resolution due to specularity and weak reflectivity, the reconstructed shapes could be imperceptible by machines and humans. To this end, SquiggleMilli designs a machine learning model to recover the high spatial frequencies in the object to reconstruct an accurate 2D shape and predict its 3D features and category. We have customized SquiggleMilli for security applications, but the model is adaptable to other applications with limited training samples. We implement SquiggleMilli on off-the-shelf components and demonstrate its performance improvement over the traditional SAR qualitatively and quantitatively.

scholarly journals PolSAR Image Classification Using a Superpixel-Based Composite Kernel and Elastic Net

2021 ◽  
Vol 13 (3) ◽  
pp. 380
Author(s):  
Yice Cao ◽  
Yan Wu ◽  
Ming Li ◽  
Wenkai Liang ◽  
Peng Zhang
Keyword(s):  
Image Classification ◽  
Feature Fusion ◽  
Classification Performance ◽  
Elastic Net ◽  
Synthetic Aperture ◽  
Polarimetric Synthetic Aperture Radar ◽  
Training Samples ◽  
Composite Kernel ◽  
Limited Training Samples ◽  
State Of Art

The presence of speckles and the absence of discriminative features make it difficult for the pixel-level polarimetric synthetic aperture radar (PolSAR) image classification to achieve more accurate and coherent interpretation results, especially in the case of limited available training samples. To this end, this paper presents a composite kernel-based elastic net classifier (CK-ENC) for better PolSAR image classification. First, based on superpixel segmentation of different scales, three types of features are extracted to consider more discriminative information, thereby effectively suppressing the interference of speckles and achieving better target contour preservation. Then, a composite kernel (CK) is constructed to map these features and effectively implement feature fusion under the kernel framework. The CK exploits the correlation and diversity between different features to improve the representation and discrimination capabilities of features. Finally, an ENC integrated with CK (CK-ENC) is proposed to achieve better PolSAR image classification performance with limited training samples. Experimental results on airborne and spaceborne PolSAR datasets demonstrate that the proposed CK-ENC can achieve better visual coherence and yield higher classification accuracies than other state-of-art methods, especially in the case of limited training samples.

scholarly journals The MindGomoku: An Online P300 BCI Game Based on Bayesian Deep Learning

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1613
Author(s):  
Man Li ◽  
Feng Li ◽  
Jiahui Pan ◽  
Dengyong Zhang ◽  
Suna Zhao ◽  
...  
Keyword(s):  
Brain Computer Interface ◽  
Computer Interface ◽  
System Control ◽  
Average Accuracy ◽  
Training Samples ◽  
The Disabled ◽  
Limited Training Samples ◽  
The Stability ◽  
Electroencephalogram Eeg ◽  
Bci System

In addition to helping develop products that aid the disabled, brain–computer interface (BCI) technology can also become a modality of entertainment for all people. However, most BCI games cannot be widely promoted due to the poor control performance or because they easily cause fatigue. In this paper, we propose a P300 brain–computer-interface game (MindGomoku) to explore a feasible and natural way to play games by using electroencephalogram (EEG) signals in a practical environment. The novelty of this research is reflected in integrating the characteristics of game rules and the BCI system when designing BCI games and paradigms. Moreover, a simplified Bayesian convolutional neural network (SBCNN) algorithm is introduced to achieve high accuracy on limited training samples. To prove the reliability of the proposed algorithm and system control, 10 subjects were selected to participate in two online control experiments. The experimental results showed that all subjects successfully completed the game control with an average accuracy of 90.7% and played the MindGomoku an average of more than 11 min. These findings fully demonstrate the stability and effectiveness of the proposed system. This BCI system not only provides a form of entertainment for users, particularly the disabled, but also provides more possibilities for games.

scholarly journals Effects of Motion Compensation Residual Error and Polarization Distortion on UAV-Borne PolInSAR

2021 ◽  
Vol 13 (4) ◽  
pp. 618
Author(s):  
Zexin Lv ◽  
Fangfang Li ◽  
Xiaolan Qiu ◽  
Chibiao Ding
Keyword(s):  
Motion Compensation ◽  
Residual Error ◽  
Synthetic Aperture ◽  
Interferometric Synthetic Aperture Radar ◽  
Practical Application ◽  
Aerial Vehicle ◽  
Application Potential ◽  
Large Motion ◽  
Simulation Results ◽  
Interferometric Sar

Polarimetric Interferometric Synthetic Aperture Radar (PolInSAR) can improve interferometric coherence and phase quality, which has good application potential. With the development of the Mini-SAR system, Unmanned Aerial Vehicle borne (UAV-borne) PolInSAR systems became a reality. However, UAV-borne PolInSAR is easily affected by air currents and other factors, which may cause large motion errors and polarization distortion inevitably exists. However, there are few pieces of research which are about motion compensation residual error (MCRE) and polarization distortion effects on PolInSAR. Though the effects of MCRE on Interferometric SAR (InSAR) and polarization distortion on PolInSAR were studied, respectively, these two parts are independently modeled and analyzed. In this paper, a model that simultaneously considers the effects of these two kinds of errors is proposed, and simulation results are given to validate the model. Then, a quantitative analysis based on a real Quadcopter UAV PolInSAR system is performed according to the model, which is valuable for system design and practical application of the UAV-borne PolInSAR system.

Motion Compensation in Synthetic Aperture Sonar Imaging

1995 ◽  
pp. 745-754 ◽  
Author(s):  
John M. Silkaitis ◽  
Bretton L. Douglas ◽  
Hua Lee
Keyword(s):  
Motion Compensation ◽  
Synthetic Aperture ◽  
Synthetic Aperture Sonar ◽  
Sonar Imaging

scholarly journals A DIVERSIFIED DEEP BELIEF NETWORK FOR HYPERSPECTRAL IMAGE CLASSIFICATION

2016 ◽  
Vol XLI-B7 ◽  
pp. 443-449
Author(s):  
P. Zhong ◽  
Z. Q. Gong ◽  
C. Schönlieb
Keyword(s):  
Image Classification ◽  
Real World ◽  
Hyperspectral Image ◽  
Classification Performance ◽  
Fine Tuning ◽  
Hyperspectral Image Classification ◽  
Latent Factors ◽  
Deep Model ◽  
Training Samples ◽  
Limited Training Samples

In recent years, researches in remote sensing demonstrated that deep architectures with multiple layers can potentially extract abstract and invariant features for better hyperspectral image classification. Since the usual real-world hyperspectral image classification task cannot provide enough training samples for a supervised deep model, such as convolutional neural networks (CNNs), this work turns to investigate the deep belief networks (DBNs), which allow unsupervised training. The DBN trained over limited training samples usually has many “dead” (never responding) or “potential over-tolerant” (always responding) latent factors (neurons), which decrease the DBN’s description ability and thus finally decrease the hyperspectral image classification performance. This work proposes a new diversified DBN through introducing a diversity promoting prior over the latent factors during the DBN pre-training and fine-tuning procedures. The diversity promoting prior in the training procedures will encourage the latent factors to be uncorrelated, such that each latent factor focuses on modelling unique information, and all factors will be summed up to capture a large proportion of information and thus increase description ability and classification performance of the diversified DBNs. The proposed method was evaluated over the well-known real-world hyperspectral image dataset. The experiments demonstrate that the diversified DBNs can obtain much better results than original DBNs and comparable or even better performances compared with other recent hyperspectral image classification methods.

scholarly journals Determination and correction of aberrations in full field OCT using phase gradient autofocus by maximizing the likelihood function

2020 ◽  
Author(s):  
Vasily Matkivsky ◽  
Alexander Moiseev ◽  
Pavel Shilyagin ◽  
Alexander Rodionov ◽  
Hendrik Spahr ◽  
...  
Keyword(s):  
High Frequency ◽  
Likelihood Function ◽  
Synthetic Aperture ◽  
Numerical Estimation ◽  
Optical Aberrations ◽  
Phase Gradient ◽  
Full Field ◽  
Fundus Imaging ◽  
Spatial Frequencies ◽  
Estimation And Correction

A method for numerical estimation and correction of aberrations of the eye in fundus imaging with optical coherence tomography (OCT) is presented. Aberrations are determined statistically by using the estimate based on likelihood function maximization. The method can be considered as an extension of the phase gradient autofocusing algorithm in synthetic aperture radar imaging to 2D optical aberrations correction. The efficiency of the proposed method has been demonstrated in OCT fundus imaging with 6λ aberrations. After correction, single photoreceptors were resolved. It is also shown that wavefront distortions with high spatial frequencies can be determined and corrected.Graphical Abstract for Table of Contents[Text. This work is dedicated to development a method for numerical estimation and correction of aberrations of the eye in fundus imaging with OCT. Aberration evaluation is performed statistically by using estimate based on likelihood function maximization. The efficiency of the proposed method has been demonstrated in OCT fundus imaging with 6λ aberrations. It has been shown that spatial high-frequency wavefront distortions can be determined]

scholarly journals Attention-Based Residual Network with Scattering Transform Features for Hyperspectral Unmixing with Limited Training Samples

2020 ◽  
Vol 12 (3) ◽  
pp. 400 ◽  
Author(s):  
Zeng ◽  
Ritz ◽  
Zhao ◽  
Lan
Keyword(s):  
Neural Network ◽  
Additive Noise ◽  
Hyperspectral Data ◽  
Training Data ◽  
K Nearest Neighbors ◽  
Practical Applications ◽  
Hyperspectral Unmixing ◽  
Scattering Transform ◽  
Training Samples ◽  
Limited Training Samples

This paper proposes a framework for unmixing of hyperspectral data that is based on utilizing the scattering transform to extract deep features that are then used within a neural network. Previous research has shown that using the scattering transform combined with a traditional K-nearest neighbors classifier (STFHU) is able to achieve more accurate unmixing results compared to a convolutional neural network (CNN) applied directly to the hyperspectral images. This paper further explores hyperspectral unmixing in limited training data scenarios, which are likely to occur in practical applications where the access to large amounts of labeled training data is not possible. Here, it is proposed to combine the scattering transform with the attention-based residual neural network (ResNet). Experimental results on three HSI datasets demonstrate that this approach provides at least 40% higher unmixing accuracy compared to the previous STFHU and CNN algorithms when using limited training data, ranging from 5% to 30%, are available. The use of the scattering transform for deriving features within the ResNet unmixing system also leads more than 25% improvement when unmixing hyperspectral data contaminated by additive noise.

Sign in / Sign up

Export Citation Format

Share Document