Structural Prior Driven Regularized Deep Learning for Sonar Image Classification

Gerg, Isaac D.; Monga, Vishal

doi:10.1109/tgrs.2020.3045649

Cited by 29 publications

(23 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, with the aid of groupwise convolution, the width of the network is boosted, further enhancing the semantic information of the feature maps. Te classifcation accuracy of the network model can be greatly improved by the network model [26,27]. Terefore, this paper chose the ResNet101 residual network model as the benchmark model, and in the next step, attentional mechanisms will be incorporated into the ResNet101 model to further improve the classifcation accuracy.…”

Section: Feature Extraction Network Based Onmentioning

confidence: 99%

An Image Classification Method Based on Adaptive Attention Mechanism and Feature Extraction Network

Luo

2023

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The convolution neural network (CNN) not only has high fault tolerance but also has high computing capacity. The image classification performance of CNN has an important relationship with its network depth. The network depth is deeper, and the fitting ability of CNN is stronger. However, a further increase in the depth of CNN will not improve the accuracy of the network but will produce higher training errors, which will reduce the image classification performance of CNN. In order to solve the above problems, this paper proposes a feature extraction network, AA-ResNet with an adaptive attention mechanism. The residual module of the adaptive attention mechanism is embedded for image classification. It consists of a feature extraction network guided by the pattern, a generator trained in advance, and a complementary network. The feature extraction network guided by the pattern is used to extract different levels of features to describe different aspects of an image. The design of the model effectively uses the image information of the whole level and the local level, and the feature representation ability is enhanced. The whole model is trained as a loss function, which is about a multitask problem and has a specially designed classification, which helps to reduce overfitting and make the model focus on easily confused categories. The experimental results show that the method in this paper performs well in image classification for the relatively simple Cifar-10 dataset, the moderately difficult Caltech-101 dataset, and the Caltech-256 dataset with large differences in object size and location. The fitting speed and accuracy are high.

show abstract

Section: Feature Extraction Network Based Onmentioning

confidence: 99%

An Image Classification Method Based on Adaptive Attention Mechanism and Feature Extraction Network

Luo

2023

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…The naval mine is a strategic military instrument that contains explosive material and contributes both to offensive actions, which consist of eliminating surface ships or submarines, and to defensive actions, being used to protect the naval borders of a country. In addition, due to their suitable cost performance and since they are considered war tools that manage to prevent opponents from freely engaging in activity in mine areas for a long time [ 2 ], sea mines are popular for use both in combat and for area protection purposes. Thus, depending on the location, the mines can be floating or drifting on the surface of the water, anchored or bottomed, while, considering their type, they can be considered as follows: contact, induce, moored, ground, drifting, oscillating, creeping, mobile, homing, rising or bouquet mines.…”

Section: Introductionmentioning

confidence: 99%

“…The mine countermeasure decisions must consider adopting actions that imply mine-hunting or sweeping operations [ 2 ]. The demining or genius combat diver is a type of military man specialized in searching for and destroying sea mines, using diving as the main procedure.…”

Section: Introductionmentioning

confidence: 99%

“…In a recent study [ 2 ], DL was shown to improve performance in the domain of synthetic aperture sonar (SAS) image classification. Within the study [ 2 ], two structural priors were enforced via regularization terms in the learning of the network: structural similarity priors—enhanced imagery aids human interpretation and is semantically similar to the original imagery; and structural scene context priors—learned features that ideally encapsulate target centering information.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Sea Mine Detection Framework Using YOLO, SSD and EfficientDet Deep Learning Models

Munteanu

Diana

Zamfir

et al. 2022

Sensors

View full text Add to dashboard Cite

In the context of new geopolitical tensions due to the current armed conflicts, safety in terms of navigation has been threatened due to the large number of sea mines placed, in particular, within the sea conflict areas. Additionally, since a large number of mines have recently been reported to have drifted into the territories of the Black Sea countries such as Romania, Bulgaria Georgia and Turkey, which have intense commercial and tourism activities in their coastal areas, the safety of those economic activities is threatened by possible accidents that may occur due to the above-mentioned situation. The use of deep learning in a military operation is widespread, especially for combating drones and other killer robots. Therefore, the present research addresses the detection of floating and underwater sea mines using images recorded from cameras (taken from drones, submarines, ships and boats). Due to the low number of sea mine images, the current research used both an augmentation technique and synthetic image generation (by overlapping images with different types of mines over water backgrounds), and two datasets were built (for floating mines and for underwater mines). Three deep learning models, respectively, YOLOv5, SSD and EfficientDet (YOLOv5 and SSD for floating mines and YOLOv5 and EfficientDet for underwater mines), were trained and compared. In the context of using three algorithm models, YOLO, SSD and EfficientDet, the new generated system revealed high accuracy in object recognition, namely the detection of floating and anchored mines. Moreover, tests carried out on portable computing equipment, such as Raspberry Pi, illustrated the possibility of including such an application for real-time scenarios, with the time of 2 s per frame being improved if devices use high-performance cameras.

show abstract

“…, [9] and classification [2], [4], [5], [6], and far too little attention has been paid to orientation estimation. In fact, the precise orientation information of rotated targets can not only be used in pose estimation tasks but also in improving rotated target recognition [10].…”

mentioning

confidence: 99%

Orientation Estimation of Rotated Sonar Image Targets via the Wavelet Subimage Energy Ratio

Zhang

Tang

Zhong

et al. 2022

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

View full text Add to dashboard Cite

Precise orientation information facilitates target recognition of sonar images. Traditional orientation estimation methods, including the Hough transform method, have poor antinoise abilities, so they cannot achieve high estimation precision for sonar images, which usually have low signal-to-noise ratios. The convolutional neural network (CNN) regression method is sensitive to image affine transformations and requires extensive computation, so it cannot achieve strong robustness or high speed. To achieve high-precision, high-speed, and robust orientation estimation of sonar image targets, we present a novel orientation estimation method via the wavelet subimage energy ratio (WSER). The WSER varies with the rotation angles of images and has the highest value when the long axes of targets are vertical. It is translational and scale invariant and does not need supervised training. Therefore, we propose estimating orientations of sonar image targets by finding the max of the WSER to achieve high precision, high speed, and strong robustness to the translation and scale transformations of images. The results of experiments on a self-made sonar image dataset show that the mean absolute error (MAE) of the proposed method is 7.9°, while the MAEs of the CNN regression method and traditional methods are 10.1 and 22.9°, respectively. In addition, the proposed method is six times faster than the CNN regression method. The proposed orientation estimation method has also been applied to align the orientation of sonar images and CNN can achieve state-of-the-art performance for rotated target recognition using the aligned images. Data and codes are publicly available.

show abstract

Structural Prior Driven Regularized Deep Learning for Sonar Image Classification

Cited by 29 publications

References 47 publications

An Image Classification Method Based on Adaptive Attention Mechanism and Feature Extraction Network

An Image Classification Method Based on Adaptive Attention Mechanism and Feature Extraction Network

Sea Mine Detection Framework Using YOLO, SSD and EfficientDet Deep Learning Models

Orientation Estimation of Rotated Sonar Image Targets via the Wavelet Subimage Energy Ratio

Contact Info

Product

Resources

About