Difference between revisions of "Archaeology"

From
Jump to: navigation, search
m
m
 
(One intermediate revision by the same user not shown)
Line 23: Line 23:
 
* [[Python#Satellite Imagery |Satellite Imagery]] with Python
 
* [[Python#Satellite Imagery |Satellite Imagery]] with Python
 
* [[Time]] ... [[Time#Positioning, Navigation and Timing (PNT)|PNT]] ... [[Time#Global Positioning System (GPS)|GPS]] ... [[Causation vs. Correlation#Retrocausality| Retrocausality]] ... [[Quantum#Delayed Choice Quantum Eraser|Delayed Choice Quantum Eraser]] ... [[Quantum]]
 
* [[Time]] ... [[Time#Positioning, Navigation and Timing (PNT)|PNT]] ... [[Time#Global Positioning System (GPS)|GPS]] ... [[Causation vs. Correlation#Retrocausality| Retrocausality]] ... [[Quantum#Delayed Choice Quantum Eraser|Delayed Choice Quantum Eraser]] ... [[Quantum]]
* [[History of Artificial Intelligence (AI)]] ... [[Creatives]]
 
 
* [https://singularityhub.com/2020/05/07/the-new-indiana-jones-ai-heres-how-its-overhauling-archaeology/ The New Indiana Jones? AI. Here’s How It’s Overhauling Archaeology | Peter Rejcek - Singularity Hub]
 
* [https://singularityhub.com/2020/05/07/the-new-indiana-jones-ai-heres-how-its-overhauling-archaeology/ The New Indiana Jones? AI. Here’s How It’s Overhauling Archaeology | Peter Rejcek - Singularity Hub]
 
** [https://www.tandfonline.com/doi/abs/10.1080/0734578X.2018.1482186?journalCode=ysea20 Automated mound detection using lidar and object-based image analysis in Beaufort County, South Carolina | Davis, Sanger, & Lipo]  
 
** [https://www.tandfonline.com/doi/abs/10.1080/0734578X.2018.1482186?journalCode=ysea20 Automated mound detection using lidar and object-based image analysis in Beaufort County, South Carolina | Davis, Sanger, & Lipo]  
Line 42: Line 41:
 
<youtube>UaVxJ8i-pBU</youtube>
 
<youtube>UaVxJ8i-pBU</youtube>
 
<b>Automated Detection of Archaeology in the New Forest using Deep Learning with Remote Sensor Data
 
<b>Automated Detection of Archaeology in the New Forest using Deep Learning with Remote Sensor Data
</b><br>As a result of the New Forest Knowledge project, many new sites were discovered. This was partly due to the undertaken LiDAR survey which was followed by an intensive manual process to interpret the results. The research presented in this paper looks at methods to automate this process especially for round barrow detection using deep learning. Traditionally, automated methods require manual feature engineering to extract the visual appearance of a site on remote sensing data. Whereas this approach is difficult, expensive and bound to detect a single type of site, recent developments have moved towards automated feature learning of which deep learning is the most notable. In our approach, we use known site locations together with LiDAR data and aerial images to train Convolutional Neural Networks (CNNs). This network is typically constructed of many layers with each representing a different filter (e.g. to detect lines or edges). When this network is trained, each new site location that is fed to the network will update the weights of features to better represent the appearance of sites in the remote sensing data. For this learning process, an accurate dataset is required with a lot of examples and therefore the New Forest is a very suitable case study, especially thanks to the extensive research of the New Forest Knowledge project. In this paper, our latest results will be presented together with a future perspective on how we can scale our approach to a country wide detection method when computing power becomes even more efficient.  Iris Kramer , Electronics and Computer Science, University of Southampton, UK  Jonathon Hare, Electronics and Computer Science, University of Southampton, UK  Isabel Sargent, Ordnance Survey, UK  Adam Prugel-Bennett, Electronics and Computer Science, University of Southampton, UK
+
</b><br>As a result of the New Forest Knowledge project, many new sites were discovered. This was partly due to the undertaken LiDAR survey which was followed by an intensive manual process to interpret the results. The research presented in this paper looks at methods to automate this process especially for round barrow detection using deep learning. Traditionally, automated methods require manual feature engineering to extract the visual appearance of a site on remote sensing data. Whereas this approach is difficult, expensive and bound to detect a single type of site, recent developments have moved towards automated feature learning of which deep learning is the most notable. In our approach, we use known site locations together with LiDAR data and aerial images to train Convolutional Neural Networks (CNNs). This network is typically constructed of many layers with each representing a different filter (e.g. to detect lines or edges). When this network is trained, each new site location that is fed to the network will update the weights of features to better represent the appearance of sites in the remote sensing data. For this learning process, an accurate dataset is required with a lot of examples and therefore the New Forest is a very suitable case study, especially thanks to the extensive research of the New Forest Knowledge project. In this paper, our latest results will be presented together with a future [[perspective]] on how we can scale our approach to a country wide detection method when computing power becomes even more efficient.  Iris Kramer , Electronics and Computer Science, University of Southampton, UK  Jonathon Hare, Electronics and Computer Science, University of Southampton, UK  Isabel Sargent, Ordnance Survey, UK  Adam Prugel-Bennett, Electronics and Computer Science, University of Southampton, UK
 
|}
 
|}
 
|<!-- M -->
 
|<!-- M -->

Latest revision as of 15:58, 28 April 2024

Youtube search... ...Google search


Automated Detection of Archaeology in the New Forest using Deep Learning with Remote Sensor Data
As a result of the New Forest Knowledge project, many new sites were discovered. This was partly due to the undertaken LiDAR survey which was followed by an intensive manual process to interpret the results. The research presented in this paper looks at methods to automate this process especially for round barrow detection using deep learning. Traditionally, automated methods require manual feature engineering to extract the visual appearance of a site on remote sensing data. Whereas this approach is difficult, expensive and bound to detect a single type of site, recent developments have moved towards automated feature learning of which deep learning is the most notable. In our approach, we use known site locations together with LiDAR data and aerial images to train Convolutional Neural Networks (CNNs). This network is typically constructed of many layers with each representing a different filter (e.g. to detect lines or edges). When this network is trained, each new site location that is fed to the network will update the weights of features to better represent the appearance of sites in the remote sensing data. For this learning process, an accurate dataset is required with a lot of examples and therefore the New Forest is a very suitable case study, especially thanks to the extensive research of the New Forest Knowledge project. In this paper, our latest results will be presented together with a future perspective on how we can scale our approach to a country wide detection method when computing power becomes even more efficient. Iris Kramer , Electronics and Computer Science, University of Southampton, UK Jonathon Hare, Electronics and Computer Science, University of Southampton, UK Isabel Sargent, Ordnance Survey, UK Adam Prugel-Bennett, Electronics and Computer Science, University of Southampton, UK

How deep learning helps archaeologists rediscover the past
Tech Republic Practical applications of deep learning algorithms enhances the fields of archaeology and history.

Artifacts

Youtube search... ...Google search


FROM CAVE PAINTING TO EMOJIS: human visual expressions and how A.I. can measure it
VISUA Alessandro Prest, CTO & Co-Founder of LogoGrab, brings us through a journey of human visual expression evolution at eMerge Americas, WIT.

Machine-Learning AI Translates Cuneiform - Earthly Headlines
Jindo Cuneiform, the oldest surviving form of writing in existence, was the writing system in place of the ancient Sumerians, Akkadians, and Assyrians. Museums, labs, and even private collectors are sitting on a large database of these writings, yet only a handful of them have been translated. The Jindo takes a look at the development of machine-learning algorithms that are utilized by scientists seeking to translate the remainder of these tablets. Also discussed are the implications of such algorithmic tools on the whole of academia, and the possible discoveries that are to be made in doing so.