The oceans in the Earth's in one of the last border lines on the World, with
only a fraction of their depths having been explored. Advancements in
technology have led to the development of Autonomous Underwater Vehicles (AUVs)
that can operate independently and perform complex tasks underwater. These
vehicles have revolutionized underwater exploration, allowing us to study and
understand our oceans like never before. In addition to AUVs, image processing
techniques have also been developed that can help us to better understand the
seabed and its features. In this comprehensive survey, we will explore the
latest advancements in AUV technology and seabed image processing techniques.
We'll discuss how these advancements are changing the way we explore and
understand our oceans, and their potential impact on the future of marine
science. Join us on this journey to discover the exciting world of underwater
exploration and the technologies that are driving it forward.

通过对自主水下车辆技术和海床图像处理技术的最新进展的全面调查，我们将探索这些进展如何改变我们探索和理解海洋的方式，以及它们对海洋科学未来的潜在影响。加入我们一起发现激动人心的水下探索世界以及推动其发展的技术。

革新自主式水下航行器（AUV）与海底图像处理技术的水下探测

Revolutionizing Underwater Exploration of Autonomous Underwater Vehicles  (AUVs) and Seabed Image Processing Techniques

The oceans are a source of an impressive mixture of complex data that could
be used to uncover relationships yet to be discovered. Such data comes from the
oceans and their surface, such as Automatic Identification System (AIS)
messages used for tracking vessels' trajectories. AIS messages are transmitted
over radio or satellite at ideally periodic time intervals but vary irregularly
over time. As such, this paper aims to model the AIS message transmission
behavior through neural networks for forecasting upcoming AIS messages' content
from multiple vessels, particularly in a simultaneous approach despite
messages' temporal irregularities as outliers. We present a set of experiments
comprising multiple algorithms for forecasting tasks with horizon sizes of
varying lengths. Deep learning models (e.g., neural networks) revealed
themselves to adequately preserve vessels' spatial awareness regardless of
temporal irregularity. We show how convolutional layers, feed-forward networks,
and recurrent neural networks can improve such tasks by working together.
Experimenting with short, medium, and large-sized sequences of messages, our
model achieved 36/37/38% of the Relative Percentage Difference - the lower, the
better, whereas we observed 92/45/96% on the Elman's RNN, 51/52/40% on the GRU,
and 129/98/61% on the LSTM. These results support our model as a driver for
improving the prediction of vessel routes when analyzing multiple vessels of
diverging types simultaneously under temporally noise data.

本文针对海洋数据中存在时间奇异性的问题，使用神经网络建模，预测多艘船舶的 AIS 消息内容，以改善航线预测。在多个算法实验中，卷积层、前馈网络和递归神经网络的组合模型表现最佳。结果表明该模型有效地提高了航线预测的准确度。