For the navigation of an unmanned surface vehicle (USV), detection and recognition of the water-shore-line (WSL) is an important part of its intellectualization. Current research on this issue mainly focuses on the straight WSL obtained by straight line fitting. However, the WSL in the image acquired by boat-borne vision is not always in a straight line, especially in an inland river waterway. In this paper, a novel three-step approach for WSL detection is therefore proposed to solve this problem through the information of an image sequence. Firstly, the initial line segment pool is built by the line segment detector (LSD) algorithm. Then, the coarse-to-fine strategy is used to obtain the onshore line segment pool, including the rough selection of water area instability and the fine selection of the epipolar constraint between image frames, both of which are demonstrated in detail in the text. Finally, the complete shore area is generated by an onshore line segment pool of multi-frame images, and the lower boundary of the area is the desired WSL. In order to verify the accuracy and robustness of the proposed method, field experiments were carried out in the inland river scene. Compared with other detection algorithms based on image processing, the results demonstrate that this method is more adaptable, and can detect not only the straight WSL, but also the curved WSL.Sensors 2020, 20, 1682 2 of 20 tracking. Coupled with the development of computer vision technology, the camera has become an indispensable sensor device for USV because of its low cost, rich information and high resolution [3].The water-shore-line (WSL) is one of the most prominent symbols of optical images captured by boat-borne vision in an inland river scene. First of all, due to the height limitation of USV, obstacles in the field of vision always appear near WSL, so accurate WSL detection is very beneficial for target detection and recognition. Secondly, WSL detection can not only obtain the motion state and surrounding environment information of the USV, but also estimate the location information of the USV from the shore [4].WSL detection is similar to sea-sky-line [4][5][6][7], water-sky-line [8-10] and skyline detection [11], which is a connection line with a larger gradient value in the image. Compared with WSL detection, there are many studies on sea-sky-line detection, mainly including image processing methods such as straight line fitting [4][5][6][7], wavelet transform [12], region growth [13], threshold segmentation [9,14] and other methods [15].An Bowen et al. [4] first applied the OTSU algorithm to complete image binarization, then extracted the line segments with the Hough transform, and finally used the line segment fitting to obtain the sea-sky-line. Liang et al. [6] used texture features to narrow the sea-sky-line area, then got candidate points in the area and applied the improved line segment fitting method to obtain the line segment parameters. Ma et al. [7] analyzed the adverse effects of waves, clouds and glaring reflecti...