Autonomous Visual Perception for Unmanned Surface Vehicle Navigation in an Unknown Environment.

Wenqiang Zhan,Yuanqiao Wen,Xin Liu,Supu Xiu,Changshi Xiao,Chunhui Zhou,Xiong Zou,Haiwen Yuan,Yimeng Zhang,Qiliang Li

doi:10.3390/s19102216

Abstract

Robust detection and recognition of water surfaces are critical for autonomous navigation of unmanned surface vehicles (USVs), since any none-water region is likely an obstacle posing a potential danger to the sailing vehicle. A novel water region visual detection method is proposed in this paper. First, the input image pixels are clustered into different regions and each pixel is assigned a label tag and a confidence value by adaptive multistage segmentation algorithm. Then the resulting label map and associated confidence map are fed into a convolutional neural network (CNN) as training samples to train the network online. Finally, the online trained CNN is used to segment the input image again but with greater precision and stronger robustness. Compared with other deep-learning image segmentation algorithms, the proposed method has two advantages. Firstly, it dispenses with the need of manual labeling training samples which is a costly and painful task. Secondly, it allows real-time online training for CNN, making the network adaptive to the navigational environment. Another contribution of this work relates to the training process of neuro network. An effective network training method is designed to learn from the imperfect training data. We present the experiments in the lake with a various scene and demonstrate that our proposed method could be applied to recognize the water region in the unknown navigation environment automatically.

Highlights

The past decade of research in marine and field robotics gave rise to the development of a new class of small-sized unmanned surface vehicles (USVs)
In [13], a hierarchical horizon detection algorithm was proposed by using Canny edge detector and Hough transform to find major edges in the image, and the precise curvature of the horizon was captured by fine-level adjustment
We propose a novel online learning approach to recognize the water region for the USV in the unknown navigation environment

Summary

Introduction

By itself camera is data-rich, how to extract useful information from millions or billions of raw pixels remains to be a challenging problem. One of those specific to USVs is water region segmentation, i.e., assigning each pixels a meaningful label such as water, sky, shore, or other vehicles in view, even a coarse water-none-water labeling is very helpful to the auto-navigation task of USV. In [13], a hierarchical horizon detection algorithm was proposed by using Canny edge detector and Hough transform to find major edges in the image, and the precise curvature of the horizon was captured by fine-level adjustment. Wang et al [16] sampled maximum or minimum gradient value points along each vertical line in the gradient image, and used RANSAC to fit the horizon line

Methods

Results

Conclusion