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

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

doi:10.3390/s19102216

Cited by 38 publications

(22 citation statements)

References 26 publications

(29 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance of the different algorithms is compared via Figure 15f,k, whose WSLs are somewhat curved. As shown in Figure 20, the four columns correspond to different methods respectively, which are respectively SLF [10] method, EDS [9] method, SPS [14] method and OL [17] method. The first column uses straight line fitting combined with the RANSAC method (SLF) [10].…”

Section: Comparison With Other Methodsmentioning

confidence: 99%

“…Similarly, for images with bad illumination, the superpixel segmentation method (SPS) [14] cannot distinguish whether the shadow is shore or water area, so what is obtained in Figure 20g is not a satisfactory result. The results obtained by online learning method (OL) [17] are shown in Figure 20d,h. The method first uses lidar and vision to judge the input image pixels, and then the image pixels are fed into a convolutional neural network (CNN) to train the network online, and finally, the online trained CNN Figure 20.…”

Section: Comparison With Other Methodsmentioning

confidence: 99%

“…The results obtained by online learning method (OL) [17] are shown in Figure 20d,h. The method first uses lidar and vision to judge the input image pixels, and then the image pixels are fed into a convolutional neural network (CNN) to train the network online, and finally, the online trained CNN is used to segment the input image.…”

Section: Comparison With Other Methodsmentioning

confidence: 99%

See 2 more Smart Citations

A Novel Water-Shore-Line Detection Method for USV Autonomous Navigation

Zou

Xiao

Zhan

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

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...

show abstract

Section: Comparison With Other Methodsmentioning

confidence: 99%

Section: Comparison With Other Methodsmentioning

confidence: 99%

Section: Comparison With Other Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Water-Shore-Line Detection Method for USV Autonomous Navigation

Zou

Xiao

Zhan

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Moreover, with the development of Deep Learning, it has also been applied in water region segmentation. For example, Zhan et al [13] proposed an online learning approach to recognize the water region for the USV in the unknown navigation environment using a convolutional neural network (CNN). Han et al [14] innovatively used the Fully Connected Convolutional Network (FCN) to achieve water hazards detection on the road.…”

Section: Introductionmentioning

confidence: 99%

Segmentation of River Scenes Based on Water Surface Reflection Mechanism

Lin

Zhu

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

Segmentation of a river scene is a representative case of complex image segmentation. Different from road segmentation, river scenes often have unstructured boundaries and contain complex light and shadow on the water’s surface. According to the imaging mechanism of water pixels, this paper designed a water description feature based on a multi-block local binary pattern (MB-LBP) and Hue variance in HSI color space to detect the water region in the image. The improved Local Binary Pattern (LBP) feature was used to recognize the water region and the local texture descriptor in HSI color space using Hue variance was used to detect the shadow area of the river surface. Tested on two data sets including simple and complex river scenes, the proposed method has better segmentation performance and consumes less time than those of two other widely used methods.

show abstract

“…Most of the researchers directly focus on water line detection and water target detection [5,6]. There are a few pieces of research reports on the water region detection directly [7]. For the detection of water line, most existing researches make use of the traditional vision algorithms based on the edge features and line detection algorithms, assuming that the water line is a straight line for the undistorted image and a circle for the omnidirectional image [8,9].…”

Section: Introductionmentioning

confidence: 99%

Adaptive Semantic Segmentation for Unmanned Surface Vehicle Navigation

et al. 2020

Self Cite

View full text Add to dashboard Cite

The intelligentization of unmanned surface vehicles (USVs) has recently attracted intensive interest. Visual perception of the water scenes is critical for the autonomous navigation of USVs. In this paper, an adaptive semantic segmentation method is proposed to recognize the water scenes. A semantic segmentation network model is designed to classify each pixel of an image into water, land or sky. The segmentation result is refined by the conditional random field (CRF) method. It is further improved accordingly by referring to the superpixel map. A weight map is generated based on the prediction confidence. The network trains itself with the refined pseudo label and the weight map. A set of experiments were designed to evaluate the proposed method. The experimental results show that the proposed method exhibits excellent performance with few-shot learning and is quite adaptable to a new environment, very efficient for limited manual labeled data utilization.

show abstract

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

Cited by 38 publications

References 26 publications

A Novel Water-Shore-Line Detection Method for USV Autonomous Navigation

A Novel Water-Shore-Line Detection Method for USV Autonomous Navigation

Segmentation of River Scenes Based on Water Surface Reflection Mechanism

Adaptive Semantic Segmentation for Unmanned Surface Vehicle Navigation

Contact Info

Product

Resources

About