Mapping Archeological Signs From Airborne Lidar Data Using Deep Neural Networks: Primary Results

Küçükdemirci, Melda; Landeschi, Giacomo; Dell’Unto, Nicolò; Ohlsson, Mattias

doi:10.4000/archeosciences.10179

Cited by 3 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is now fairly well known in the literature that the investigation of the human past requires an interdisciplinary approach in which remote sensing data represent an irreplaceable investigative tool in the search for traces of the past, sometimes explaining the signs of the present. The anomalies, the colour, the patterns visible from a remote sensing scene are all the result of the interaction between natural phenomena and human activities whose ultimate outcome is the landscape (Küçükdemirci et al, 2021). In this regard, it is now widely accepted that certain types of buried archaeological deposits can be identified due to their inherent ability to produce different proxy indicators visible on the ground, even though physical and micro topographical changes that can be intercepted from an aerial view (Crawford 1929;Dassie 1978;Wilson 1982;Optiz and Cowley 2013).…”

Section: Methodsmentioning

confidence: 99%

Uavimals: The "Open" Remote Sensing System for Surface Archaeological Investigations

Vacatello,

Roccella,

Vannini

2023

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Today, there is an increasing use of airborne sensors in archaeology, especially to investigate the surface of more or less vast territories quickly and accurately. In particular, airborne laser scanning technologies from small remotely piloted aircraft are rapidly developing towards increasingly high-performance solutions for the investigation of archaeological evidence hidden by vegetation or more or less substantial soil deposits. The proposed contribution intends to insert itself within this field of archaeological research by presenting "UAVIMALS" (Unmanned Aerial Vehicle Integrated with Micro Airborne Laser Scanner), an aerial remote sensing system of "soil marks", designed for surface archaeological investigations and the result of an Early Career Grant from the National Geographic Society. The system, consisting of a customised drone based on an open architecture and software for vehicle control and data processing, integrates a solid-state laser sensor, commonly engineered for obstacle avoidance, but here exploited to process accurate DTM (Digital Terrain Model) of small land surfaces with a significant reduction in cost and acquisition time. The system, whose engineering was contributed by the BioRobotics Institute of the S. Anna University of Pisa, was tested within the archaeological context of Leopoli - Cencelle (Tarquinia, Italy). A mediaeval city that has been researched for about 25 years by the Chair of Christian and Medieval Archaeology at the 'Sapienza' University of Rome. Experimentation missions carried out on the site, which is still only partially investigated, have been successful in bringing to light some urban areas that had not yet been investigated.

show abstract

Section: Methodsmentioning

confidence: 99%

Uavimals: The "Open" Remote Sensing System for Surface Archaeological Investigations

Vacatello,

Roccella,

Vannini

2023

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…As it is also highlighted in Gallwey et al (2019), segmentation tasks for medical and biomedical image analysis share similar challenges with LIDAR data. Thus, recently similar segmentation approaches started to be adapted to extract the archaeological features from LIDAR data (Bundzel et al, 2020; Gallwey et al, 2019; Guyot et al, 2021; Kazimi et al, 2019; Küçükdemirci et al, 2021).…”

Section: Methodsmentioning

confidence: 99%

“…As it is seen in the studies above, this approach is more commonly applied on LIDAR‐derived datasets, especially those related to archaeological research, mainly due to the limitation of a large number of annotated datasets which is still obstacle in this field. Thus, it is necessary to find a way of developing different network architectures with a limited quantity of annotated datasets and to create an original labelled data catalogue for archaeological remote sensing (Bundzel et al, 2020; Gallwey et al, 2019; Küçükdemirci et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Investigating ancient agricultural field systems in Sweden from airborne LIDAR data by using convolutional neural network

Küçükdemirci

Landeschi

Ohlsson

et al. 2022

Archaeological Prospection

Self Cite

View full text Add to dashboard Cite

Today, the advances in airborne LIDAR technology provide high-resolution datasets that allow specialists to detect archaeological features hidden under wooded areas more efficiently. Still, the complexity and large scale of these datasets require automated analysis. In this respect, artificial intelligence (AI)-based analysis has recently created an alternative approach for interpreting remote sensing data. In this study, a convolutional neural network (CNN) is proposed to detect clearance cairns, which are visible in today's landscape and act as important markers of past agricultural activities. For this aim, the U-shape network architecture is adapted, trained from scratch with an original labelled dataset and tested in various field sites, focusing on southern Sweden. Although it is challenging to tune the hyperparameters and decide on the proper network architecture to obtain reliable prediction, long-running experimental tests with this model produced promising results, with training and validation metrics of 0.8406 Dice-coefficient, 0.7469 Val-dice coefficient, and 0.7350 IuO and 0.6034 Val-IoU values, once trained with the best parameters. Thus, the proposed CNN model in this study made data interpretation quicker and guided scholars to focus on the location of the target objects, opening a new frontier for future landscape analysis and archaeological research.

show abstract

“…It has experimented with geospatial data/images (satellite, aerial, lidar), texts, categorical tableau data, point clouds, and other datasets. For instance, one can consider some indicative examples such as the work that has been done on bone classification [1], remote sensing archaeology [2][3][4][5][6][7][8][9][10][11][12], geophysical prospection [13][14][15][16][17], detection of objects in paintings [18], classification of pottery [19], and the 3D reconstruction of heritage buildings [20]. The main reason behind this growing trend, which has been noticed in the last five years in all scientific domains, underlies the nuisance generated when dealing with multivariate analysis of high-volume datasets, which are challenging to process and interpret.…”

Section: Introductionmentioning

confidence: 99%

GPR Data Processing and Interpretation Based on Artificial Intelligence Approaches: Future Perspectives for Archaeological Prospection

Küçükdemirci

Sarris

2022

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Ground penetrating radar (GPR) is a well-established technique used in archaeological prospection and it requires a number of specialized routines for signal and image processing to enhance the data acquired and lead towards a better interpretation of them. Computer-aided techniques have advanced the interpretation of GPR data, dealing with a wide range of operations aiming towards locating, imaging, and diagnosis/interpretation. This article will discuss the novel and recent applications of machine learning (ML) and deep learning (DL) techniques, under the artificial intelligence umbrella, for processing GPR measurements within archaeological contexts, and their potential, limitations, and possible future prospects.

show abstract

Mapping Archeological Signs From Airborne Lidar Data Using Deep Neural Networks: Primary Results

Abstract: Highlights:• Complexity of large-scale Airborne LIDAR data: its processing, and interpretation emerges the necessity of automated analysis with novel techniques.• Detection and documentation of archaeological ruins, hidden in the forests of the Swedish landscape.

Cited by 3 publications

References 7 publications

Uavimals: The "Open" Remote Sensing System for Surface Archaeological Investigations

Uavimals: The "Open" Remote Sensing System for Surface Archaeological Investigations

Investigating ancient agricultural field systems in Sweden from airborne LIDAR data by using convolutional neural network

GPR Data Processing and Interpretation Based on Artificial Intelligence Approaches: Future Perspectives for Archaeological Prospection

Contact Info

Product

Resources

About