Synergistic Use of UAV and USV Data and Petrographic Analyses for the Investigation of Beachrock Formations: A Case Study from Syros Island, Aegean Sea, Greece

Lewicka

et al. 2020

JMSE

The human impact on the ecosystem has been particularly evident in the last century; it transforms the Earth’s surface on an unprecedented scale and brings about irreversible changes. One example is an oceanographic phenomenon known as a tombolo, i.e., a narrow belt connecting the mainland with an island lying near the shore formed as a result of sand and gravel being deposited by sea currents. The phenomenon contributes to an increase in the biogenic substance content in the littoral zone, which leads to increased cyanobacteria blooming in the summer period. Moreover, the debris accumulation in the littoral zone results in the mud formation, which makes the beach landscape less attractive. One of the main features of the tombolo phenomenon is its variability of shape, which includes the form of both the shore and the seabed adjacent to it. Therefore, to describe its size and spatio-temporal variability, it is necessary to apply methods for geodetic (the land) and hydrographic (the sea) measurements that can be carried out in different ways. The aim of the paper is to present the methodology for carrying out measurements of the tombolo oceanographic phenomenon using Unmanned Aerial Vehicles (UAV) and Unmanned Surface Vehicles (USV) on the example of a waterbody adjacent to the Sopot pier. It also presents the results of surveys carried out in November 2019 within this area. The study demonstrated that the integration of two measuring devices whose development began in the second decade of the 20th century, i.e., UAVs and USVs, enables accurate (even up to several centimeters) and reliable determination of the scale and variability of the phenomena occurring in the littoral zone.

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Methodology for Carrying out Measurements of the Tombolo Geomorphic Landform Using Unmanned Aerial and Surface Vehicles near Sopot Pier, Poland

Lewicka

et al. 2020

JMSE

“…UAV images were imported into the Agisoft PhotoScan software. The software combined computer vision techniques and structure from motion (SfM) photogrammetry to achieve direct georeferencing or bundle adjustment with ground control points (GCPs) [75,81,82] or simple similarity transformation over the whole block without GCPs. Alike to classic photogrammetry from air photos or satellite stereopairs, SfM photogrammetry uses overlapping images taken from different points of view.…”

Section: Uav Data Processingmentioning

confidence: 99%

“…The geometry of the whole scene is built as more overlapping images are processed and more mutual objects are detected and related. The requirement for many overlapping photos in order to cover an entire area of interest generated the procedure name of structure from motion photogrammetry or photogrammetry produced from a moving camera [82].…”

Section: Uav Data Processingmentioning

confidence: 99%

Combination of Aerial, Satellite, and UAV Photogrammetry for Mapping the Diachronic Coastline Evolution: The Case of Lefkada Island

Nikolakopoulos

Kyriou

Koukouvelas

et al. 2019

IJGI

Self Cite

Coastline evolution is a proxy of coastal erosion, defined as the wasting of land along the shoreline due to a combination of natural and/or human causes. For countries with a sea border, where a significant proportion of the population lives in coastal areas, shoreline retreat has become a very serious global problem. Remote sensing data and photogrammetry have been used in coastal erosion mapping for many decades. In the current study, multi-date analogue aerial photos, digital aerial photos, and declassified satellite imagery provided by the U.S. Geological Survey (USGS), Pleiades satellite data, and unmanned aerial vehicle images were combined for accurate mapping of the southwestern Lefkada (Ionian Sea, Greece) coastline over the last 73 years. Different photogrammetric techniques were used for the orthorectifation of the remote sensing data, and geographical information systems were used in order to calculate the rates of shoreline change. The results indicated that the southwest shoreline of Lefkada Island is under dynamic equilibrium. This equilibrium is strongly controlled by geological parameters, such as subsidence of the studied shoreline during co-seismic deformation and mass wasting. The maximum accretion rate was calculated at 0.55 m per year, while the respective erosion rate reached −1.53 m per year.

“…USVs are characterized by small size, fast movement, and high flexibility. In recent years, they have been adopted to conduct missions such as marine rescue, environmental monitoring [2], island reef mapping [3], and resource exploration [4]. The safety of USVs is critical when conducting missions, and the roll motion is directly related to the safety and operating performance [5].…”

Section: Introductionmentioning

confidence: 99%

Roll Motion Prediction of Unmanned Surface Vehicle Based on Coupled CNN and LSTM

Zhang

Peng

et al. 2019

Future Internet

The prediction of roll motion in unmanned surface vehicles (USVs) is vital for marine safety and the efficiency of USV operations. However, the USV roll motion at sea is a complex time-varying nonlinear and non-stationary dynamic system, which varies with time-varying environmental disturbances as well as various sailing conditions. The conventional methods have the disadvantages of low accuracy, poor robustness, and insufficient practical application ability. The rise of deep learning provides new opportunities for USV motion modeling and prediction. In this paper, a data-driven neural network model is constructed by combining a convolution neural network (CNN) with long short-term memory (LSTM) for USV roll motion prediction. The CNN is used to extract spatially relevant and local time series features of the USV sensor data. The LSTM layer is exploited to reflect the long-term movement process of the USV and predict roll motion for the next moment. The fully connected layer is utilized to decode the LSTM output and calculate the final prediction results. The effectiveness of the proposed model was proved using USV roll motion prediction experiments based on two case studies from “JingHai-VI” and “JingHai-III” USVS of Shanghai University. Experimental results on a real data set indicated that our proposed model obviously outperformed the state-of-the-art methods.