Deep learning feature extraction for target recognition and classification in underwater sonar images

Zhu, Pingping; Isaacs, Jason C.; Fu, Bo; Ferrari, Silvia

doi:10.1109/cdc.2017.8264055

Cited by 93 publications

(42 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…After initial literature analysis [3][4] [6][8] [16], it was concluded that the deep learning seems to be modern and promising techniques for underwater obstacle recognition. Deep learning is a part of broader family of machine learning methods based on learning data representations [11].…”

Section: Figure 2 Cyberseal Close To the Surface Of Water In The Swimmentioning

confidence: 99%

Using Pretrained AlexNet Deep Learning Neural Network for Recognition of Underwater Objects

Szymak

Gąsiorowski

2020

Naše more

View full text Add to dashboard Cite

Recently, the growing number of Autonomous Underwater Vehicles (AUVs) can be seen. These vehicles are power supplied and controlled from the sources located on their boards. To operate autonomously underwater robots have to be equipped with the diff erent sensors and software for making decision based on the signals from these sensors. The goal of the paper is to show initial research carried out for underwater objects recognition based on video images. Based on several examples included in the literature, the object recognition algorithm proposed in the paper is based on the deep neural network. In the research, the network and training algorithms accessible in the Matlab have been used. The fi nal software will be implemented on board of the Biomimetic Autonomous Underwater Vehicle (BAUV), driven by undulating propulsion imitating oscillating motion of fi ns, e.g. of a fi sh. Sažetak U posljednje vrijeme može se uočiti sve veći broj autonomnih podvodnih plovila (AUV). Ova plovila imaju pogon i kontroliraju ih izvori koji se nalaze na njima. Da bi radili, autonomno podvodni roboti moraju biti opremljeni raznim senzorima i softverom kako bi se donosile odluke na temelju signala primljenih s pomoću senzora. Cilj je ovoga rada prikazati početno istraživanje provedeno na prepoznavanju podvodnih objekata putem videa. Na temelju nekoliko primjera koji se mogu naći u literaturi, algoritam za prepoznavanje objekata koji se predlaže u ovome radu temelji se na dubokim neuronskim mrežama. U istraživanju koristili su se dostupna mreža i algoritmi za obuku u Matlabu. Konačno dobiveni softver primijenit će se na biomimetrijskom autonomnom podvodnom plovilu (BAUV), pogonjenom valovitim pogonom koji imitira oscilirajuće gibanje peraja, npr. ribljih peraja.

show abstract

Section: Figure 2 Cyberseal Close To the Surface Of Water In The Swimmentioning

confidence: 99%

Using Pretrained AlexNet Deep Learning Neural Network for Recognition of Underwater Objects

Szymak

Gąsiorowski

2020

Naše more

View full text Add to dashboard Cite

show abstract

“…The exploration and research of marine resources have become major demands for sustainable national development. Zhu et al [2] proposed an automatic target recognition (ATR) method for a sonar-mounted unmanned underwater vehicle (UUV) with feature extraction through deep learning to achieve target recognition and classification in underwater sonar images, this method provides new ideas for improving the efficiency of image semantic segmentation. Wu et al [3] proposed a novel and practical convolutional neural network architecture for semantic segmentation of high-resolution images of seabed and underwater targets provided by side-scan sonar (SSS), it provides a new way for the semantic segmentation of underwater images with different resolutions.…”

Section: Introductionmentioning

confidence: 99%

Semantic Segmentation of Underwater Images Based on Improved Deeplab

Liu

Fang

2020

JMSE

View full text Add to dashboard Cite

Image semantic segmentation technology has been increasingly applied in many fields, for example, autonomous driving, indoor navigation, virtual reality and augmented reality. However, underwater scenes, where there is a huge amount of marine biological resources and irreplaceable biological gene banks that need to be researched and exploited, are limited. In this paper, image semantic segmentation technology is exploited to study underwater scenes. We extend the current state-of-the-art semantic segmentation network DeepLabv3 + and employ it as the basic framework. First, the unsupervised color correction method (UCM) module is introduced to the encoder structure of the framework to improve the quality of the image. Moreover, two up-sampling layers are added to the decoder structure to retain more target features and object boundary information. The model is trained by fine-tuning and optimizing relevant parameters. Experimental results indicate that the image obtained by our method demonstrates better performance in improving the appearance of the segmented target object and avoiding its pixels from mingling with other class’s pixels, enhancing the segmentation accuracy of the target boundaries and retaining more feature information. Compared with the original method, our method improves the segmentation accuracy by 3%.

show abstract

“…Deep learning has enabled the most advanced performance of many computer vision tasks, including but not limited to target detection, feature extraction, image classification, image de-noising and image reconstruction [1][2][3][4]. It has also led to huge improvements in medical image processing [5][6][7][8] , allowing expert diagnosis of individual diseases.…”

Section: Introductionmentioning

confidence: 99%

A CNN-Based Approach for Lung 3D-CT Registration

Yang

2020

IEEE Access

View full text Add to dashboard Cite

Deep learning techniques have been applied to certain rigid or non-rigid medical image registration due to its potential advantages in meeting the clinical requirements of real-time and accuracy. Based on the deep learning model, this study aims to explore specific network models suitable for lung CT images. The proposed model took unlabeled 3D image pairs as input, and the convolutional neural network (CNN) was utilized and identified as a function with ability of sharing parameters to obtain displacement field. The image pair could be aligned by applying the acquired displacement field to the target image through spatial transformation. The similarity between the aligned image pair combined with the constraints on the displacement field was taken as the objective function to obtain the optimal parameters. Two models with different depths were designed and the consequent registration effects with different optimization methods and convolution kernel sizes were explored. The results proved that the designs with deeper level using Adam optimizer and smaller convolution kernels in obtaining displacement fields had higher accuracy and stronger robustness. The accuracy of the unsupervised model was comparable to state-of-theart methods, while operating orders of magnitude faster. This study proposed a feasible registration method for lung 3D-CT, and its usefulness in aligning CT images has been demonstrated.

show abstract

Deep learning feature extraction for target recognition and classification in underwater sonar images

Cited by 93 publications

References 9 publications

Using Pretrained AlexNet Deep Learning Neural Network for Recognition of Underwater Objects

Using Pretrained AlexNet Deep Learning Neural Network for Recognition of Underwater Objects

Semantic Segmentation of Underwater Images Based on Improved Deeplab

A CNN-Based Approach for Lung 3D-CT Registration

Contact Info

Product

Resources

About