A Review on Deep Learning-Based Approaches for Automatic Sonar Target Recognition

Neupane, Dhiraj; Seok, Jongwon

doi:10.3390/electronics9111972

Cited by 102 publications

(62 citation statements)

References 86 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A standard CNN architecture, which is shown in Fig. 4, consists of an input (image), a feature extraction block (convolution, activation unit, pooling layer), followed by one or more fully connected layers, and finally, a classification layer [29]. The main purpose of the convolutional layer is to learn the feature representation of the input image.…”

Section: B Convolutional Neural Networkmentioning

confidence: 99%

“…With the advent and development of DL algorithms, the problems mentioned above have been solved significantly. Deep learning is a subfield of machine learning that can automatically learn raw data features without experts' experience and defines both higher-level and lower-level categories with higher accuracy [29]. A deep learning model consists of a multilayer neural network that extracts and learns features from deep layers of input signals.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Bearing Fault Detection Using Scalogram and Switchable Normalization-Based CNN (SN-CNN)

2021

Self Cite

View full text Add to dashboard Cite

Bearings play a vital role in all rotating machinery, and their failure is one of the significant causes of machine breakdown leading to a profound loss of safety and property. Therefore, the failure of rolling element bearings should be detected early while the machine fault is small. This paper presents the model that detects bearing failures using the continuous wavelet transform and classifies them using a switchable normalization-based convolutional neural network (SN-CNN). State-of-the-art accuracy was achieved with the proposed model using the Case Western Reserve University bearing dataset, which serves as the primary dataset for validating various algorithms for bearing failure detection. Batch normalization techniques were also employed and compared to the proposed model. The spectrogram images were also used as input for further comparison.

show abstract

Section: B Convolutional Neural Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Bearing Fault Detection Using Scalogram and Switchable Normalization-Based CNN (SN-CNN)

2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Side-scan sonar (SSS) can provide high-resolution images [1][2][3], which is extensively used in underwater object detection [4] and maritime search and rescue (SAR) [5]. Until recently, object detection from SSS images has mainly relied on manual visual interpretation [6], and the detection result is thereby influenced by personal quality and experience. Many scholars have studied the automatic target recognition (ATR) from SSS images, such as the machine learning (ML) method and deep learning (DL) method.…”

Section: Introductionmentioning

confidence: 99%

Real-Time Underwater Maritime Object Detection in Side-Scan Sonar Images Based on Transformer-YOLOv5

et al. 2021

View full text Add to dashboard Cite

To overcome the shortcomings of the traditional manual detection of underwater targets in side-scan sonar (SSS) images, a real-time automatic target recognition (ATR) method is proposed in this paper. This method consists of image preprocessing, sampling, ATR by integration of the transformer module and YOLOv5s (that is, TR–YOLOv5s), and target localization. By considering the target-sparse and feature-barren characteristics of SSS images, a novel TR–YOLOv5s network and a down-sampling principle are put forward, and the attention mechanism is introduced in the method to meet the requirements of accuracy and efficiency for underwater target recognition. Experiments verified the proposed method achieved 85.6% mean average precision (mAP) and 87.8% macro-F2 score, and brought 12.5% and 10.6% gains compared with the YOLOv5s network trained from scratch, and had the real-time recognition speed of about 0.068 s per image.

show abstract

“…Recently, deep learning techniques have been developed and widely used in radar target classification fields [ 16 , 17 , 18 , 19 , 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 ]. In particular, the convolutional neural network (CNN) can extract higher-level spatial features from lower-level layers via multiple convolutional layers, avoiding the manual feature extraction procedure of existing machine learning algorithms.…”

Section: Introductionmentioning

confidence: 99%

Classification of Space Objects by Using Deep Learning with Micro-Doppler Signature Images

Jung

Lee

Kim

et al. 2021

Sensors

View full text Add to dashboard Cite

Radar target classification is an important task in the missile defense system. State-of-the-art studies using micro-doppler frequency have been conducted to classify the space object targets. However, existing studies rely highly on feature extraction methods. Therefore, the generalization performance of the classifier is limited and there is room for improvement. Recently, to improve the classification performance, the popular approaches are to build a convolutional neural network (CNN) architecture with the help of transfer learning and use the generative adversarial network (GAN) to increase the training datasets. However, these methods still have drawbacks. First, they use only one feature to train the network. Therefore, the existing methods cannot guarantee that the classifier learns more robust target characteristics. Second, it is difficult to obtain large amounts of data that accurately mimic real-world target features by performing data augmentation via GAN instead of simulation. To mitigate the above problem, we propose a transfer learning-based parallel network with the spectrogram and the cadence velocity diagram (CVD) as the inputs. In addition, we obtain an EM simulation-based dataset. The radar-received signal is simulated according to a variety of dynamics using the concept of shooting and bouncing rays with relative aspect angles rather than the scattering center reconstruction method. Our proposed model is evaluated on our generated dataset. The proposed method achieved about 0.01 to 0.39% higher accuracy than the pre-trained networks with a single input feature.

show abstract

A Review on Deep Learning-Based Approaches for Automatic Sonar Target Recognition

Cited by 102 publications

References 86 publications

Bearing Fault Detection Using Scalogram and Switchable Normalization-Based CNN (SN-CNN)

Bearing Fault Detection Using Scalogram and Switchable Normalization-Based CNN (SN-CNN)

Real-Time Underwater Maritime Object Detection in Side-Scan Sonar Images Based on Transformer-YOLOv5

Classification of Space Objects by Using Deep Learning with Micro-Doppler Signature Images

Contact Info

Product

Resources

About