The Effect of Training Dataset Size on SAR Automatic Target Recognition Using Deep Learning

Kuang, Weidong; Dong, Wenjie; Dong, Liang

doi:10.1109/iceiec54567.2022.9835077

Cited by 3 publications

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In many areas, the sufficient datasets might not be available or cannot be generated in the simulation, what indicates the need for collecting and labelling a new dataset. The data must be labelled in the large amount to prevent the overfitting [ 8 ]. The inability to collect the adequately diversified set of the images might be overcome by the artificial data augmentation [ 9 , 10 ].…”

Section: Introductionmentioning

confidence: 99%

Influence of Insufficient Dataset Augmentation on IoU and Detection Threshold in CNN Training for Object Detection on Aerial Images

Bożko

Ambroziak

2022

Sensors

View full text Add to dashboard Cite

The objects and events detection tasks are being performed progressively often by robotic systems like unmanned aerial vehicles (UAV) or unmanned surface vehicles (USV). Autonomous operations and intelligent sensing are becoming standard in numerous scenarios such as supervision or even search and rescue (SAR) missions. The low cost of autonomous vehicles, vision sensors and portable computers allows the incorporation of the deep learning, mainly convolutional neural networks (CNN) in these solutions. Many systems meant for custom purposes rely on insufficient training datasets, what may cause a decrease of effectiveness. Moreover, the system’s accuracy is usually dependent on the returned bounding boxes highlighting the supposed targets. In desktop applications, precise localisation might not be particularly relevant; however, in real situations, with low visibility and non-optimal camera orientation, it becomes crucial. One of the solutions for dataset enhancement is its augmentation. The presented work is an attempt to evaluate the influence of the training images augmentation on the detection parameters important for the effectiveness of neural networks in the context of object detection. In this research, network appraisal relies on the detection confidence and bounding box prediction accuracy (IoU). All the applied image modifications were simple pattern and colour alterations. The obtained results imply that there is a measurable impact of the augmentation process on the localisation accuracy. It was concluded that a positive or negative influence is related to the complexity and variability of the objects classes.

show abstract

Section: Introductionmentioning

confidence: 99%

Influence of Insufficient Dataset Augmentation on IoU and Detection Threshold in CNN Training for Object Detection on Aerial Images

Bożko

Ambroziak

2022

Sensors

View full text Add to dashboard Cite

show abstract

Advancing industrial building energy measurement and verification (M&V) with deep learning: Evaluating data size and feature selection impact

Sukarti,

Sulaima,

Kadir

et al. 2024

Energy and Buildings

View full text Add to dashboard Cite

A Comprehensive Survey on SAR ATR in Deep-Learning Era

Li¹,

Yu²,

Lei³

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Due to the advantages of Synthetic Aperture Radar (SAR), the study of Automatic Target Recognition (ATR) has become a hot topic. Deep learning, especially in the case of a Convolutional Neural Network (CNN), works in an end-to-end way and has powerful feature-extracting abilities. Thus, researchers in SAR ATR also seek solutions from deep learning. We review the related algorithms with regard to SAR ATR in this paper. We firstly introduce the commonly used datasets and the evaluation metrics. Then, we introduce the algorithms before deep learning. They are template-matching-, machine-learning- and model-based methods. After that, we introduce mainly the SAR ATR methods in the deep-learning era (after 2017); those methods are the core of the paper. The non-CNNs and CNNs, that is, those used in SAR ATR, are summarized at the beginning. We found that researchers tend to design specialized CNN for SAR ATR. Then, the methods to solve the problem raised by limited samples are reviewed. They are data augmentation, Generative Adversarial Networks (GAN), electromagnetic simulation, transfer learning, few-shot learning, semi-supervised learning, metric leaning and domain knowledge. After that, the imbalance problem, real-time recognition, polarimetric SAR, complex data and adversarial attack are also reviewed. The principles and problems of them are also introduced. Finally, the future directions are conducted. In this part, we point out that the dataset, CNN architecture designing, knowledge-driven, real-time recognition, explainable and adversarial attack should be considered in the future. This paper gives readers a quick overview of the current state of the field.

show abstract

The Effect of Training Dataset Size on SAR Automatic Target Recognition Using Deep Learning

Cited by 3 publications

References 5 publications

Influence of Insufficient Dataset Augmentation on IoU and Detection Threshold in CNN Training for Object Detection on Aerial Images

Influence of Insufficient Dataset Augmentation on IoU and Detection Threshold in CNN Training for Object Detection on Aerial Images

Advancing industrial building energy measurement and verification (M&V) with deep learning: Evaluating data size and feature selection impact

A Comprehensive Survey on SAR ATR in Deep-Learning Era

Contact Info

Product

Resources

About