Deep Gabor Neural Network for Automatic Detection of Mine-Like Objects in Sonar Imagery

Le, Hoang Thanh; Phung, Son Lam; Chapple, Philip B.; Bouzerdoum, A.; Ritz, Christian; Tran, Le Chung

doi:10.1109/access.2020.2995390

Cited by 27 publications

(11 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering object detection, state-of-the-art architectures are divided into two types: one-stage and two-stage. Two examples of one-stage approaches are SSD (Single-Shot multibox Detector) and You Only Look Once (YOLO), which use a CNN to obtain predictionbounding boxes along probabilities for objects' classes [91].…”

Section: Deep Learningmentioning

confidence: 99%

A Survey of Seafloor Characterization and Mapping Techniques

Loureiro,

Dias,

Almeida

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

The deep seabed is composed of heterogeneous ecosystems, containing diverse habitats for marine life. Consequently, understanding the geological and ecological characteristics of the seabed’s features is a key step for many applications. The majority of approaches commonly use optical and acoustic sensors to address these tasks; however, each sensor has limitations associated with the underwater environment. This paper presents a survey of the main techniques and trends related to seabed characterization, highlighting approaches in three tasks: classification, detection, and segmentation. The bibliography is categorized into four approaches: statistics-based, classical machine learning, deep learning, and object-based image analysis. The differences between the techniques are presented, and the main challenges for deep sea research and potential directions of study are outlined.

show abstract

Section: Deep Learningmentioning

confidence: 99%

A Survey of Seafloor Characterization and Mapping Techniques

Loureiro,

Dias,

Almeida

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…While their system showed promising results, it was limited in terms of its ability to handle real-world data with missing values and required significant pre-processing. Thanh Le et al [3] proposed a Deep Gabor Neural Network (DGNN) for automatic detection of mine-like objects in sonar imagery. Their system showed good performance but was limited in terms of scalability for large datasets.…”

Section: Existing Systemmentioning

confidence: 99%

Sonar Rock vs Mine Prediction Using Xgboost and Randomized Search Cv

2023

IRJMETS

View full text Add to dashboard Cite

Sonar technology is widely used for underwater object detection, and its application in identifying mines has been extensively studied. However, distinguishing between rocks and mines is a challenge as they are static objects and have similar characteristics. In this study, we propose the use of the XGBoost algorithm for sonar rock vs mine prediction. The dataset used in this study is the Sonar dataset provided by Gorman, R. P., and Sejnowski, T J. Our model analyses the data obtained from sonar waves and makes predictions based on this data. We constructed a decision-making model using XGBoost, which achieved a classification accuracy of 88%. To further enhance the performance of the model, we used the Randomized Search CV algorithm, which randomly selects a set of hyperparameters and evaluates the performance of the model using cross-validation. This has boosted the accuracy to 95.23%. Our findings suggest that XGBoost can be a valuable tool for sonarbased rock vs mine prediction in underwater environments.

show abstract

“…Another study [ 23 ] effectively combined both semantically weak and strong features to handle mine-like objects at multiple scales. Thus, within the study, a parameterized Gabor layer, which improved the generalization capability and computational efficiency, was used for feature extraction.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…Another recent study [ 23 ] developed a Gabor-based deep neural network architecture to detect MLOs. The steerable Gabor filtering modules were embedded within the cascaded layers to enhance the images’ scale and orientation, and the proposed Gabor neural network (GNN) was designed as a feature pyramid network with a small number of trainable weights and trained utilizing sonar images with labelled MLOs [ 23 ]. The automatic detection of mine-like objects using sonar images was also investigated by other authors [ 34 ] who used Gabor CNN, R-CNN, Fast R-CNN, Faster R-CNN, Tiny YOLOv3, YOLOv3 and SSD300 methods.…”

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

Deep Gabor Neural Network for Automatic Detection of Mine-Like Objects in Sonar Imagery

Cited by 27 publications

References 36 publications

A Survey of Seafloor Characterization and Mapping Techniques

A Survey of Seafloor Characterization and Mapping Techniques

Sonar Rock vs Mine Prediction Using Xgboost and Randomized Search Cv

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

Contact Info

Product

Resources

About