Man-Made Object Recognition from Underwater Optical Images Using Deep Learning and Transfer Learning

Yu, Xian; Xing, Xiangrui; Zheng, Han; Fu, Xueyang; Huang, Yue; Ding, Xinghao

doi:10.1109/icassp.2018.8461549

Cited by 13 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…AlexNet and ResNet are both classic networks and are widely used in image classification. We adopted AlexNet 24 and ResNet-50 25 as the base networks. On the one hand, for the convenience of comparison with other mainstream methods; on the other hand, these two network structures can obtain better results in image feature extraction.…”

Section: Compared Approaches and Results Analysismentioning

confidence: 99%

Deep adversarial domain adaptation network

Chen

et al. 2020

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

The advantage of adversarial domain adaptation is that it uses the idea of adversarial adaptation to confuse the feature distribution of two domains and solve the problem of domain transfer in transfer learning. However, although the discriminator completely confuses the two domains, adversarial domain adaptation still cannot guarantee the consistent feature distribution of the two domains, which may further deteriorate the recognition accuracy. Therefore, in this article, we propose a deep adversarial domain adaptation network, which optimises the feature distribution of the two confused domains by adding multi-kernel maximum mean discrepancy to the feature layer and designing a new loss function to ensure good recognition accuracy. In the last part, some simulation results based on the Office-31 and Underwater data sets show that the deep adversarial domain adaptation network can optimise the feature distribution and promote positive transfer, thus improving the classification accuracy.

show abstract

Section: Compared Approaches and Results Analysismentioning

confidence: 99%

Deep adversarial domain adaptation network

Chen

et al. 2020

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

show abstract

“…Based on this theory, Xiamen University integrated deep learning and transfer learning to recognize underwater manmade targets. 26 This method is superior to traditional methods in underwater manmade target recognition tasks. It is suitable for long-term research and development.…”

Section: Few-shot Target Recognitionmentioning

confidence: 97%

“…25 Through the training of multiple datasets, the algorithm can accurately recognize targets in different underwater environments and provide new ideas for subsequent research on multidata information fusion. Yu et al 26 built a model composed of five convolutional layers and three fully connected layers based on convolutional neural network (CNN) deep learning theory. In the training procedure, both labeled in-air images and unlabeled underwater images are used to train the model.…”

Section: Underwater Manmade Target Recognition Technologymentioning

confidence: 99%

Underwater target recognition methods based on the framework of deep learning: A survey

Teng

Zhao

2020

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

The accuracy of underwater target recognition by autonomous underwater vehicle (AUV) is a powerful guarantee for underwater detection, rescue, and security. Recently, deep learning has made significant improvements in digital image processing for target recognition and classification, which makes the underwater target recognition study becoming a hot research field. This article systematically describes the application of deep learning in underwater image analysis in the past few years and briefly expounds the basic principles of various underwater target recognition methods. Meanwhile, the applicable conditions, pros and cons of various methods are pointed out. The technical problems of AUV underwater dangerous target recognition methods are analyzed, and corresponding solutions are given. At the same time, we prospect the future development trend of AUV underwater target recognition.

show abstract

“…The object tracking is achieved by support vector regression (SVR) followed by the kernel extreme learning machine (KELM) model. Yu et al (2018) proposed a combination of deep learning and transfer learning techniques to recognize man-made objects from underwater optical images. You only look once (YOLO) is a new state-of-the-art, real-time object detection system.…”

Section: Deep Learning Based Object Trackingmentioning

confidence: 99%

Passive Visual Underwater Surveillance: A Survey

Subudhi

Kapoor

Rout

et al. 2023

Preprint

View full text Add to dashboard Cite

The objective of this article is to provide a detailed review of the state-of-the-art underwater surveillance process and the new trends of the same. Underwater surveillance has recently getting lots of attention because of its potential applications including the security of the coastal border, effective fish farming, deep-sea exploration, preservation of rare aquatic animals, etc. In the case of underwater, the light that is sensed by the camera got degraded due to many underwater phenomena such as haze, low illumination, scattering, absorption, diffraction, and refraction. The actual color of the object, as well as the scene, gets degraded as the light can not travel deep underwater. In a situation, where the scene of view is not clear, it is very difficult to detect the moving objects present in the scene. Further, the identification of the object of concern and tracking of that becomes more challenging. In this survey, we categorize underwater surveillance as a combination of the three blocks: enhancement, object detection, and object tracking. We categorize all these three blocks based on the underwater complexity and motion models considered. In this article, we tried to enumerate the most detailed descriptions of each category. We also discuss the future directions of research in the area of underwater surveillance.

show abstract

Man-Made Object Recognition from Underwater Optical Images Using Deep Learning and Transfer Learning

Cited by 13 publications

References 13 publications

Deep adversarial domain adaptation network

Deep adversarial domain adaptation network

Underwater target recognition methods based on the framework of deep learning: A survey

Passive Visual Underwater Surveillance: A Survey

Contact Info

Product

Resources

About