Archaeologic Machine Learning for Shipwreck Detection Using Lidar and Sonar

Character, Leila; Ortíz, Agustín; Beach, Timothy; Luzzadder–Beach, Sheryl

doi:10.3390/rs13091759

Cited by 30 publications

(18 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e signal processing block provides several ways to process raw waveforms: (1) Parametric filtering: First, we perform Fourier transform on the signal, do spectrum analysis, remove high-frequency and low-frequency interference waves, and analyze the real and effective frequency band signal by selecting an appropriate filtering range; (2) Differential signal: When the reflection is not obvious, differential processing is performed on the signal to amplify the degree of waveform distortion; (3) Integral signal: We integrate the signal to properly reduce aftershocks; (4) Reflection extraction: Based on the estimation of the phase difference of the same signal at different sampling times, selecting an appropriate reflection coefficient can clearly show the phase mutation of the waveform [16]. e labeling module realizes manual labeling of karst caves, fissures, abnormal location shapes, or interfaces.…”

Section: Signal Analysis Software Pbcamentioning

confidence: 99%

Application of Internet of Things Technology in the Construction of Bored Pile Foundation in a High Altitude Environment

Liu¹,

Wang²,

Guo³

et al. 2022

Journal of Control Science and Engineering

View full text Add to dashboard Cite

In order to solve the problem that the current geophysical method is difficult to locate in the mud of bored piles, the problem of effective exploration of karst caves at the bottom of piles, the author puts forward the application of Internet of Things technology and sonar technology in the construction of bored pile foundation in a high altitude environment. Combined with the propagation characteristics of sonar stress waves, a sonar detection method for karst caves at the bottom of bored piles is proposed, and a sonar detector for karst caves at the bottom of piles (JL-SONAR) and signal analysis software (PBCA) are developed. The JL-SONAR detector realizes the emission and acquisition of onsite sonar signals, and the PBCA software completes the analysis and arrangement of the detection data. This technology makes full use of the mud conditions of bored piles, the development of karst caves within 10 m of the pile bottom can be tracked and detected in the process of hole formation, which has the advantages of low cost, high speed, and high precision. Experimental results show that Project A has been drilled in multiple directions at the bottom of the pile, the rock cores on the west side of the pile bottom are mostly fragmented, the rock quality index RQD is 15–30, and the quality of the foundation rock at the pile bottom is extremely poor, which verify the results of sonar detection. No slurry leakage occurred in Project B after drilling, and the cores were mostly short columns. The rock quality index RQD was 75 to 90, and the quality of the foundation rock at the bottom of the pile was good, which verifies the results of sonar detection. Conclusion. The research results provide a new solution for karst cave exploration in karst areas, especially in liquid environments.

show abstract

Section: Signal Analysis Software Pbcamentioning

confidence: 99%

Application of Internet of Things Technology in the Construction of Bored Pile Foundation in a High Altitude Environment

Liu¹,

Wang²,

Guo³

et al. 2022

Journal of Control Science and Engineering

View full text Add to dashboard Cite

show abstract

“…The network structure included three convolution layers and two full connection layers, and the results were superior to those of random guessing, SVM with a linear kernel, radial basis function, and SVM with an RBF kernel. A character-based target detection model with YOLOv3, laser and sonar data were used to detect shipwrecks on the seabed [32], achieving an F 1 value (explained later in the study) of 0.92 and a precision of 0.90, proving that YOLOv3 is reliable for underwater archaeological exploration. Berganzo-Besga et al used the supervised classification method of the random forest model to perform binary classification of soil based on Sentinel-2 imagery, combined with the multi-scale relief model (MSRM), detected tumuli over an area of near 30,000 km 2 using YOLOv3 deep learning [33].…”

Section: Introductionmentioning

confidence: 91%

Automatic Mapping of Karez in Turpan Basin Based on Google Earth Images and the YOLOv5 Model

Guo

Luo

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

As a large-scale irrigation and water conservancy project in ancient times, karez are common in Central Asia and arid regions with a history of thousands of years. Turpan, which is located in the Xinjiang Uyghur Autonomous Region, has the most extensive and concentrated distribution of karez shafts in China. There are tens of thousands of shafts, some of which are in use and are living cultural heritage. According to radiocarbon (14C) dating, some karezs are over 600 years old. The karez is of great significance to the research on geology, hydrology, oasis, climate change, and development history of karez in Turpan. With the development of the population, arable land, industrialization, and urbanization, karez systems are facing the risk of abandonment. Detailed karez distribution mapping or dynamic monitoring data are important for their management or analysis; although there are related methods, due to Turpan’s large desert and “Gobi” environments, field surveys are time- and energy-consuming, and some areas are difficult to access. Precise shaft locations and distribution maps are scarce and often lack georeferencing. The distribution and preservation of karez have not yet been fully grasped. In this study, we evaluated the effectiveness of You Only Look Once version 5 (YOLOv5) in automatically detecting karez in high-resolution images of the Turpan region. We propose post-processing steps to reduce the false karez identified by YOLOv5. Our results demonstrate the feasibility of using YOLOv5 and post-processing techniques to detect karez automatically, and the detected results are sufficient to capture the linear alignment of karez. Target detection based on YOLOv5 and post-processing can greatly improve automatic shaft identification and is therefore useful for the fine mapping of karez. We also applied this method in Shanshan County (for which no detailed mapping data on karez has been obtained before) and successfully detected some karez that had not been archived before. The number of shafts in Turpan is 82,493. Through DBSCAN clustering, it was identified which karez line belonged to which shaft; the number of sections of karez that have been used is 5057, which have a total length of 2387.2 km. The karez line obtained was overlaid with the crop-land data, and the positional relationship between the karez line and the crop land was analyzed. The cultivated area is basically surrounded by karez. Our method can potentially be applied to construct an inventory for all karez shafts globally.

show abstract

“…Second, satellite image recognition is not new. For example, scholars at the University of Texas at Austin have been using machine learning and remote sensing imagery to discover undersea shipwrecks successfully [26]. However, finding submarine wrecks does not require algorithms to describe the location and size of the wreck very precisely, as opposed to identifying small boats and their physical characteristics.…”

Section: Bringing Deep Learning To Small Ship Detection In Satellite ...mentioning

confidence: 99%

BoatNet: Automated Small Boat Composition Detection using Deep Learning on Satellite Imagery

Jialeng

Fuente

Smith

2022

Preprint

View full text Add to dashboard Cite

Tracking and measuring national carbon footprints is one of the keys to achieving the ambitious goals set by countries. According to statistics, more than 10\% of global transportation carbon emissions result from shipping. However, accurate tracking of the emissions of the small boat segment is not well established. Past research has begun to look into the role played by small boat fleets in terms of Greenhouse Gases (GHG), but this either relies on high-level techno-activity assumptions or the installation of GPS sensors to understand how this vessel class behaves. This research is undertaken mainly in relation to fishing and recreational boats. With the advent of open-access satellite imagery and its ever-increasing resolution, it can support innovative methodologies that could eventually lead to the quantification of GHG emissions. This work used deep learning algorithms to detect small boats in three cities in the Gulf of California in Mexico. The work produced a methodology named BoatNet that can detect, measure and classify small boats even under low-resolution and blurry satellite images, achieving an accuracy of 93.9% with a precision of 74.0%. Future work should focus on attributing a boat activity to fuel consumption and operational profile to estimate small boat GHG emissions in any given region. The data curated and produced in this study is freely available at https://github.com/theiresearch/BoatNet.

show abstract

Archaeologic Machine Learning for Shipwreck Detection Using Lidar and Sonar

Cited by 30 publications

References 24 publications

Application of Internet of Things Technology in the Construction of Bored Pile Foundation in a High Altitude Environment

Application of Internet of Things Technology in the Construction of Bored Pile Foundation in a High Altitude Environment

Automatic Mapping of Karez in Turpan Basin Based on Google Earth Images and the YOLOv5 Model

BoatNet: Automated Small Boat Composition Detection using Deep Learning on Satellite Imagery

Contact Info

Product

Resources

About