Multi-AUV Target Recognition Method Based on GAN-meta Learning

The presence of adverse factors such as turbid water quality and target occlusion prevented the acquisition of valid target characterization data. Due to the variable shape of the target, the accuracy of recognition for untrained new targets is low. In view of the above problems, this paper proposes a Multi-AUV target recognition method based on GAN-meta learning. VGG-19 network is used for feature extraction of target images, and the WGAN network is used to make up for missing target information. Based on the meta-learning theory, the parameters of the feature extraction process are trained by using stochastic gradient descent to improve the algorithm's ability to recognize new targets. Ensure that the GAN-meta learning model has a strong generalization ability. Simulation experiments are conducted on four underwater targets (underwater reconnaissance equipment, submarine, frogman, and torpedo) in the SUN dataset, and the results demonstrate that the proposed model achieves better performance.

[1]  Lei Cao,et al.  Learning to Learn: Hierarchical Meta-Critic Networks , 2019, IEEE Access.

[2]  Junliang Huang,et al.  Hybrid Brain/Muscle Signals Powered Wearable Walking Exoskeleton Enhancing Motor Ability in Climbing Stairs Activity , 2019, IEEE Transactions on Medical Robotics and Bionics.

[3]  Zengfu Wang,et al.  Real-Time Traffic Sign Recognition Based on Efficient CNNs in the Wild , 2019, IEEE Transactions on Intelligent Transportation Systems.

[4]  Linlin Zhu,et al.  Deeply Supervised Face Completion With Multi-Context Generative Adversarial Network , 2019, IEEE Signal Processing Letters.

[5]  Zhenghua Liu,et al.  Learning to Guide: Guidance Law Based on Deep Meta-Learning and Model Predictive Path Integral Control , 2019, IEEE Access.

[6]  Yu Kang,et al.  Adaptive Neural Control of a Kinematically Redundant Exoskeleton Robot Using Brain–Machine Interfaces , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[7]  Rui Chai,et al.  Research on improved algorithm of object detection based on feature pyramid , 2018, Multimedia Tools and Applications.

[8]  Huiyu Zhou,et al.  Vehicle Detection in Aerial Images Based on Lightweight Deep Convolutional Network and Generative Adversarial Network , 2019, IEEE Access.

[9]  Guorong Li,et al.  Localization-Aware Meta Tracker Guided With Adversarial Features , 2019, IEEE Access.

[10]  Feng Liu,et al.  Extended Global–Local Representation Learning for Video Person Re-Identification , 2019, IEEE Access.

[11]  Chen Wang,et al.  Object Detection and Instance Segmentation in Remote Sensing Imagery Based on Precise Mask R-CNN , 2019, IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium.

[12]  Yue Zhang,et al.  Meta-SSD: Towards Fast Adaptation for Few-Shot Object Detection With Meta-Learning , 2019, IEEE Access.

[13]  Hyuk-Jae Lee,et al.  Resolution-Preserving Generative Adversarial Networks for Image Enhancement , 2019, IEEE Access.

[14]  Zhe-Ming Lu,et al.  Automatic metrics learning with low‐noise embedding for zero‐shot learning , 2019, Electronics Letters.

[15]  Lei Cao,et al.  Meta-Learning via Weighted Gradient Update , 2019, IEEE Access.

[16]  Hanjun Jiang,et al.  Dynamic loss for one-stage object detectors in computer vision , 2018 .

[17]  Xuanqin Mou,et al.  Low-Dose CT Image Denoising Using a Generative Adversarial Network With Wasserstein Distance and Perceptual Loss , 2017, IEEE Transactions on Medical Imaging.

[18]  Liang Lin,et al.  Blending-Target Domain Adaptation by Adversarial Meta-Adaptation Networks , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Wenjun Zeng,et al.  Learning to Update for Object Tracking With Recurrent Meta-Learner , 2018, IEEE Transactions on Image Processing.

[20]  Guangming Shi,et al.  Motor-Imagery-Based Teleoperation of a Dual-Arm Robot Performing Manipulation Tasks , 2019, IEEE Transactions on Cognitive and Developmental Systems.

[21]  Yuanyuan Zhao,et al.  Autonomous Underwater Vehicle Navigation , 2010, IEEE Journal of Oceanic Engineering.

[22]  Scott T. Acton,et al.  SDL: Saliency-Based Dictionary Learning Framework for Image Similarity , 2018, IEEE Transactions on Image Processing.

[23]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Fuchun Sun,et al.  Lifelong Learning for Scene Recognition in Remote Sensing Images , 2019, IEEE Geoscience and Remote Sensing Letters.

[25]  Jinhua Yu,et al.  A Universal Intensity Standardization Method Based on a Many-to-One Weak-Paired Cycle Generative Adversarial Network for Magnetic Resonance Images , 2019, IEEE Transactions on Medical Imaging.

[26]  Jianqing Zhu,et al.  Improved Action-Decision Network for Visual Tracking With Meta-Learning , 2019, IEEE Access.