Obstacle type recognition in visual images via dilated convolutional neural network for unmanned surface vehicles

Recognition of obstacle type based on visual sensors is important for navigation by unmanned surface vehicles (USV), including path planning, obstacle avoidance, and reactive control. Conventional detection techniques may fail to distinguish obstacles that are similar in visual appearance in a cluttered environment. This work proposes a novel obstacle type recognition approach that combines a dilated operator with the deep-level features map of ResNet50 for autonomous navigation. First, visual images are collected and annotated from various different scenarios for USV test navigation. Second, the deep learning model, based on a dilated convolutional neural network, is set and trained. Dilated convolution allows the whole network to learn deep features with increased receptive field and further improves the performance of obstacle type recognition. Third, a series of evaluation parameters are utilised to evaluate the obtained model, such as the mean average precision (mAP), missing rate and detection speed. Finally, some experiments are designed to verify the accuracy of the proposed approach using visual images in a cluttered environment. Experimental results demonstrate that the dilated convolutional neural network obtains better recognition performance than the other methods, with an mAP of 88%.

Methodology for Combining Data Acquired by Unmanned Surface and Aerial Vehicles to Create Digital Bathymetric Models in Shallow and Ultra-Shallow Waters

This paper presents a method for integrating data acquired by unmanned surface vehicles and unmanned aerial vehicles. The aim of this work was to create a uniform bathymetric surface extending to the shoreline. Such a body of water is usually characterized by ultra-shallow depths, which makes measurement impossible even with hydrographic autonomous vessels. Bathymetric data acquired by the photogrammetric method are, however, characterized by large errors with increasing depth. The presented method is based on processing of two data sets using a bathymetric reference surface and selection of points on the basis of generated masks. Numerical bathymetric models created by interpolation methods confirmed the usefulness of the concept adopted.

Unmanned Surface Vehicle (USV) performance test in Bintan Island Waters

An unmanned surface vehicle (USV) is an unmanned vehicle that is operated on the surface of the water for certain purposes, for example, bathymetry measurement, underwater imaging, etc. These unmanned surface vehicles can be used in impassable waters for crewed vessels in dangerous waters. This research measures the movement of the vehicle acceleration and then calculates it as the USV roll and pitch values. The direction of movement and wind speed and the height of the water surface at low tide are also aspects measured in this research. An accelerometer is a sensor that can measure the acceleration of an object, both dynamic and static. Based on the observations, the highest roll value is 6.0° deep while the highest pitch value is 6.5°. The standard deviation value at roll conditions of 2.92 and the standard deviation value at pitch conditions of 1.25. The average frequency of roll conditions is 2.18 and pitch conditions of 1.13. The dominant wind moves from the south to the southwest with a dominant speed ranging from 3.0 to 4.0 m/s. The results of this research indicate that the USV has a good performance so that it is possible to collect data in the water.