Airborne SAR Autofocus Based on Blurry Imagery Classification

Chen, Jianlai; Yu, Hanwen; Xu, Gang; Zhang, Junchao; Liang, Buge; Yang, Dongkai

doi:10.3390/rs13193872

Cited by 9 publications

(6 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where W (1) and W (2) represent the weight parameters of the two fully connected layers respectively. Based on the three above modules, a CL training procedure can be established.…”

Section: A Pre-training the Network With Contrastive Learningmentioning

confidence: 99%

“…S YNTHETIC aperture radar (SAR) is an advanced remote sensor used to provide high-resolution images, which has many potential applications in military and civilian fields [1]- [5]. Nowadays, numerous high-resolution SAR images are available due to extensive satellite exploration activities, making automatic SAR image interpretation an urgent necessity.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Self-Supervised Feature Representation for SAR Image Target Classification Using Contrastive Learning

Pei,

Su,

et al. 2023

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

Self Cite

View full text Add to dashboard Cite

Nowadays, the developed deep neural networks (DNN) have been widely applied to synthetic aperture radar (SAR) image interpretation, such as target classification and recognition, which can automatically learn high-level semantic features in data-driven and task-driven manners. For the supervised learning methods, abundant labeled samples are required to avoid the over-fitting of designed networks, which is usually difficult for SAR image applications. To address these issues, a novel two-stage algorithm based on contrastive learning (CL) is proposed for SAR image target classification. In the pretraining stage, to extract self-supervised representations (SSRs) from an unlabeled train set, a convolutional neural network (CNN)-based encoder is first pre-trained using a contrasting strategy. This encoder can convert SAR images into a discriminative embedding space. Meanwhile, the optimal encoder can be determined using a linear evaluation protocol, which can indirectly confirm the transferability of pre-learned SSRs to downstream tasks. Therefore, in the fine-tuning stage, a SAR target classifier can be adequately trained using a few labeled SSRs in a supervised manner, which benefits from the powerful pre-trained encoder. Numerical experiments are carried out on the shared MSTAR dataset to demonstrate that the model based on the proposed self-supervised feature learning algorithm is superior to the conventional supervised methods under labeled data constraints. In addition, knowledge transfer experiments are also conducted on the openSARship dataset, showing that the encoder pre-trained from the MSTAR dataset can support the classifier training with high efficiency and precision. These results demonstrate the excellent training convergence and classification performance of the proposed algorithm.

show abstract

“…where W (1) and W (2) represent the weight parameters of the two fully connected layers respectively. Based on the three above modules, a CL training procedure can be established.…”

Section: A Pre-training the Network With Contrastive Learningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Self-Supervised Feature Representation for SAR Image Target Classification Using Contrastive Learning

Pei,

Su,

et al. 2023

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

Self Cite

View full text Add to dashboard Cite

show abstract

“…Aiming at the variable SAR motion trajectory, the motion compensation method [11]- [15] uses the real-time recorded platform position and motion information to calculate the motion error and realize the compensation. Another autofocus method [16]- [20] is to use the radar echo data to evaluate the motion error.…”

Section: Introductionmentioning

confidence: 99%

A Modified Algorithm for Highly Squinted Missile-Borne SAR Imaging With Large Acceleration

Zheng,

Guan,

Jiang

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The acceleration imaging algorithm of missile-borne SAR deals with acceleration and high squint angle using an equivalent range model. However, the original missile-borne SAR acceleration imaging algorithm will be ineffective because the phase error compensation for the center point of the scene is no longer applicable to all point targets in the presence of increased acceleration. To address this problem, this paper makes improvements to the missile-borne SAR acceleration imaging algorithm and adds compensation measures for slant distance approximation error. The corresponding imaging algorithms are designed and the space-variant errors of the range and azimuth are compensated respectively. Simulation experiments verify the accuracy and effectiveness of the proposed algorithm.INDEX TERMS synthetic aperture radar (SAR), missile-borne SAR, high squint, large acceleration, spacevariant error compensation.

show abstract

“…Some of these applications rely on chirp signal transmission as in the case of sonar [24], while others model the received signal after Doppler spread as chirp signals, e.g., in synthetic aperture radars (SARs) [26], and heart sound signals [27]. In the literature, various techniques have been developed for the estimation of chirp parameters, including the airborne SAR [28] and the Doppler frequency rate [29].…”

Section: Introductionmentioning

confidence: 99%

Characterization and Selection of WiFi Channel State Information Features for Human Activity Detection in a Smart Public Transportation System

Alizadeh,

Savaria,

Nerguizian

2024

IEEE Open J. Intell. Transp. Syst.

View full text Add to dashboard Cite

Robust methods are needed to detect how people are moving in smart public transportation systems. This paper proposes and characterizes effective means to accurately detect passengers. We analyze a public WiFi-based activity recognition (WiAR) dataset to extract human activity features from Channel State Information (CSI) data. To do so, CSI power changes caused by nearby human activity are analyzed. Our method first extracts multi-dimensional features using a Short-Time Fourier Transform (STFT) of CSI data to capture the relevant signal features. Since the environment of a transportation system changes dynamically and non-deterministically, we propose analyzing these changes with a heuristic algorithm that leverages a decision tree to automate a decision-making solution for feature selection. Principal Component Analysis (PCA) is performed before the decision tree algorithm. Reported results are compared with those obtained from the existing methods. Based on these results, we explore the effectiveness of various features such as the chirp rate, delta band power, spectral flux, and frequency of movement. This allows identifying and recommending the most effective features for the explored detection task according to observed variability, information gain, and correlation between features. The reported classification results show that using only the chirp rate generated from CSI information as a feature, we achieve precision = 83%, True Positive (T P ) = 94%, True Negative (T N ) = 91% and F1-score = 87%. Considering delta band power as an additional feature adds more information and allows getting higher performance with precision = 100%, T P = 97%, T N = 95% and F1-score = 95%.

show abstract

Airborne SAR Autofocus Based on Blurry Imagery Classification

Cited by 9 publications

References 33 publications

Self-Supervised Feature Representation for SAR Image Target Classification Using Contrastive Learning

Self-Supervised Feature Representation for SAR Image Target Classification Using Contrastive Learning

A Modified Algorithm for Highly Squinted Missile-Borne SAR Imaging With Large Acceleration

Characterization and Selection of WiFi Channel State Information Features for Human Activity Detection in a Smart Public Transportation System

Contact Info

Product

Resources

About