CycleGAN-based realistic image dataset generation for forward-looking sonar

Liu, Dingyu; Wang, Yusheng; Ji, Yonghoon; Yamashita, Atsushi; Asama, Hajime

doi:10.1080/01691864.2021.1873845

Cited by 27 publications

(9 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the network was trained in a supervised manner, where ground truth labels were required. Although labels can be acquired by generative adversarial network (GAN) and a simulator, it is necessary to model a similar scene in the simulator [20]. Considering the difficulty of acquiring ground truth labels, self-supervised learning methods have also been proposed.…”

Section: A Acoustic Camera 3d Reconstructionmentioning

confidence: 99%

Learning Pseudo Front Depth for 2D Forward-Looking Sonar-based Multi-view Stereo

Wang

Asama

et al. 2022

2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Self Cite

View full text Add to dashboard Cite

2D forward-looking sonar is a crucial sensor for underwater robotic perception. A well-known problem in this field is estimating missing information in the elevation direction during sonar imaging. There are demands to estimate 3D information per image for 3D mapping and robot navigation during fly-through missions. Recent learning-based methods have demonstrated their strengths, but there are still drawbacks. Supervised learning methods have achieved highquality results but may require further efforts to acquire 3D ground-truth labels. The existing self-supervised method requires pretraining using synthetic images with 3D supervision. This study aims to realize stable self-supervised learning of elevation angle estimation without pretraining using synthetic images. Failures during self-supervised learning may be caused by motion degeneracy problems. We first analyze the motion field of 2D forward-looking sonar, which is related to the main supervision signal. We utilize a modern learning framework and prove that if the training dataset is built with effective motions, the network can be trained in a self-supervised manner without the knowledge of synthetic data. Both simulation and real experiments validate the proposed method.

show abstract

Section: A Acoustic Camera 3d Reconstructionmentioning

confidence: 99%

Learning Pseudo Front Depth for 2D Forward-Looking Sonar-based Multi-view Stereo

Wang

Asama

et al. 2022

2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Self Cite

View full text Add to dashboard Cite

show abstract

“…One is generated by simulation data, such as the Multi-target Noise interference Sonar Dataset (MNSD) and Single-target Reverberation interference Sonar Dataset (SRSD) [36], while the MNSD is generated by three-dimensional imaging sonar data simulation experiment and the SRSD is a single-class bionic dataset with seabed reverberation interference. Liu et al [37] utilizes an acoustic image simulator to generate a forward-looking sonar dataset and CycleGAN is used to enhance the dataset.…”

Section: Sonar Datasetsmentioning

confidence: 99%

Attentive SOLO for Sonar Target Segmentation

Huang¹,

Zuo²,

Bei³

et al. 2022

Electronics

View full text Add to dashboard Cite

Imaging sonar systems play an important role in underwater target detection and location. Due to the influence of reverberation noise on imaging sonar systems, the task of sonar target segmentation is a challenging problem. In order to segment different types of targets in sonar images accurately, we proposed the gated fusion-pyramid segmentation attention (GF-PSA) module. Specifically, inspired by gated full fusion, we improved the pyramid segmentation attention (PSA) module by using gated fusion to reduce the noise interference during feature fusion and improve segmentation accuracy. Then, we improved the SOLOv2 (Segmenting Objects by Locations v2) algorithm with the proposed GF-PSA and named the improved algorithm Attentive SOLO. In addition, we constructed a sonar target segmentation dataset, named STSD, which contains 4000 real sonar images, covering eight object categories with a total of 7077 target annotations. The experimental results show that the segmentation accuracy of Attentive SOLO on STSD is as high as 74.1%, which is 3.7% higher than that of SOLOv2.

show abstract

“…Another paradigm is coupling guide image synthesis and image-to-image translation to generate sonar images. This is a two-stage paradigm that generates guide images firstly, such as the semantic image [9] or optical rendering image [10]- [12], then translates them into realistic sonar images. Thanks to the power of Generative Adversarial Networks (GANs) [13], it is able to generate far more realistic sonar images than the first paradigm.…”

Section: Introductionmentioning

confidence: 99%

Self-perceptual generative adversarial network for synthetic aperture sonar image generation

et al. 2023

Fourteenth International Conference on Graphics and Image Processing (ICGIP 2022)

View full text Add to dashboard Cite

Due to the shortage of Synthetic Aperture Sonar (SAS) image datasets, the development of many underwater tasks is hindered. To tackle this problem, coupling optical rendering and image-to-image translation is a novel and feasible way. However, because of the big gap between simulated optical images and real SAS images, the performances of existing works are not desired and have plenty of room for improvement. In this paper, we introduce a Self-Perceptual Generative Adversarial Network (SPerGAN) which can controllably generate SAS images with high fidelity. It utilizes a kind of self-perceptual loss to generate high-quality and diverse SAS images. Moreover, we introduce a novel evaluation method of SAS images that accords closely with human cognition. To evaluate the performance of our method, we first compare it against recent outstanding image-to-image translation methods on qualitative and quantitative aspects. Then we make ablation studies to explore the effects of different cycle consistency losses and hyper-parameters. The results show that our method can generate diverse and realistic SAS images.

show abstract

CycleGAN-based realistic image dataset generation for forward-looking sonar

Cited by 27 publications

References 32 publications

Learning Pseudo Front Depth for 2D Forward-Looking Sonar-based Multi-view Stereo

Learning Pseudo Front Depth for 2D Forward-Looking Sonar-based Multi-view Stereo

Attentive SOLO for Sonar Target Segmentation

Self-perceptual generative adversarial network for synthetic aperture sonar image generation

Contact Info

Product

Resources

About