A Generative Model of Underwater Images for Active Landmark Detection and Docking
A Generative Model of Underwater Images for Active Landmark Detection and Docking
复制标题
DOI：
10.1109/iros40897.2019.8968146
复制
发表时间：
2019-11
期刊：
影响因子：
--
通讯作者：
Shuang Liu;M. Ozay;Hongli Xu;Yang Lin;Takayuki Okatani
中科院分区：
文献类型：
--
作者：
Shuang Liu;M. Ozay;Hongli Xu;Yang Lin;Takayuki Okatani
水下主动地标（UALs）被广泛用于水下机器人任务中的短距离水下导航。由于水下光照、水质和摄像机视角变化的大范围变化，UAL的检测具有挑战性。此外，检测精度的提高依赖于用于训练检测模型的图像的统计多样性。我们提出了一个生成对抗网络，称为坦克到场GAN（T2FGAN），学习水下图像的生成模型，并使用学习的模型进行数据增强，以提高检测精度。为此，首先使用在坦克中捕获的UAL的图像来训练T2FGAN。然后，T2FGAN的学习模型用于根据不同的水质，光照，姿态和地标配置（WIPC）生成UAL的图像。在实验分析中，我们首先探索统计特性的图像的UAL由T2FGAN在各种WIPC主动地标检测。然后，我们使用生成的图像用于训练检测算法。实验结果表明，利用生成的图像训练检测算法可以提高检测精度。在现场实验中，水下对接任务成功地在一个湖泊中使用T2FGAN生成的数据集训练的检测模型。
Underwater active landmarks (UALs) are widely used for short-range underwater navigation in underwater robotics tasks. Detection of UALs is challenging due to large variance of underwater illumination, water quality and change of camera viewpoint. Moreover, improvement of detection accuracy relies upon statistical diversity of images used to train detection models. We propose a generative adversarial network, called Tank-to-field GAN (T2FGAN), to learn generative models of underwater images, and use the learned models for data augmentation to improve detection accuracy. To this end, first a T2FGAN is trained using images of UALs captured in a tank. Then, the learned model of the T2FGAN is used to generate images of UALs according to different water quality, illumination, pose and landmark configurations (WIPCs). In experimental analyses, we first explore statistical properties of images of UALs generated by T2FGAN under various WIPCs for active landmark detection. Then, we use the generated images for training detection algorithms. Experimental results show that training detection algorithms using the generated images can improve detection accuracy. In field experiments, underwater docking tasks are successfully performed in a lake by employing detection models trained on datasets generated by T2FGAN.