Shadow verification–based waterline detection for unmanned surface vehicles deployed in complicated natural environment

Yangjie Wei,Yuqing He

doi:10.1177/1729881418818732

Abstract

Boundary separation of operational regions would be helpful for unmanned surface vehicles deployed in dynamic outdoor environments. However, the feasibility and accuracy of current obstacle avoidance methods based on conventional optical images are comparatively poor for unmanned surface vehicle applications, with complicated natural illumination as one of the main sources of error. In this article, a new optical waterline detection method is proposed by combining shadow verification and global optimization (energy minimization). The method is then validated using an actual unmanned surface vehicle operating in outdoor environments. First, the basic principles of intrinsic image are introduced and then employed to evaluate the threshold for background segmentation so that the influence of complicated intensity distribution on the original image is reduced. The properties of different types of shadows are compared, and the basic principles of shadow verification are used to classify the different object regions. Subsequently, the intensity contrast between the shadow and non-shadow regions is used to measure the waterline position based on the relationship between the illumination and the shadow formation. Furthermore, the waterline detection problem is transformed into a problem involving the optimization of energy (minimization) described using differential equations. Finally, experiments are conducted with a series of practical images captured by the unmanned surface vehicle. The experimental results demonstrate the feasibility and robustness of the proposed method.

Highlights

Boundary detection of the sailing region for unmanned surface vehicles (USVs) would facilitate automatic navigation and obstacle avoidance
In our operation test experiments, the video images captured from a forward facing camera onboard an actual USV system operating on an outdoor water surface, shown in Figure 6, and the VS250DH camera is from the MicroVision Company (Redmond, Washington, USA)
We proposed an optical waterline detection method by combining shadow verification and energy minimization

Summary

Introduction

Boundary detection of the sailing region for unmanned surface vehicles (USVs) would facilitate automatic navigation and obstacle avoidance. The basic principles of coastline detection based on images captured using a synthetic aperture radar (SAR), which is typically mounted on an aircraft or spacecraft,[5,6,7,8,9] are explained for the waterline detection of USVs, because the waterline and the coastline exhibit similar characteristics in terms of the shape, position, and intensity. These methods are widely used in marine geology because the field of view of the SAR system is considerable, and images can be captured day or night, even in stormy weather and through clouds. The segmentation threshold can be automatically chosen through the trough detection method from the histogram curve, as shown in Figure 3, in which there is a triangle on the curve

Results

Discussion

Conclusion