Automatyzacja w procesie detekcji obiektów archeologicznych z danych ALS

Bakuła, K.; Ostrowski, W.; Zapłata, Rafał

doi:10.14746/fpp.2014.19.09

Cited by 6 publications

(5 citation statements)

References 2 publications

(2 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The interest in DCNNs (Deep Convolutional Neural Networks) for the recognition of archaeological structures is gradually increasing among the archaeological community. Research with ALS data using deep learning methods has involved spatially simple objects, e.g., burial mounds [1][2][3]20,21], charcoal piles [1,3,21,22], post-mining pits [23] as well as roundhouses and huts [2]; attempts to identify more spatially complex structures such as polygonal megalithic tombs [24] were also undertaken. Deep learning methods have also been implemented for the detection of multi-element objects with complex, irregular relief such as Celtic field systems [1,20].…”

Section: Deep Learning and Als Data In Archaeologymentioning

confidence: 99%

“…Conventional ALS data acquisition and processing is usually performed according to the following procedures: (1) acquisition of data, (2) classification of the point cloud, (3) generation of a DTM (Digital Terrain Model) followed by transformation into a visualisation (4). The preferred method of ALS data transformation to increase the visibility of the detected objects is LRM (Local Relief Model) [1][2][3]20,22,23]. This technique is used to extract small changes in terrain relief and is based on subtracting the mean values from the input DTM [26].…”

Section: Deep Learning and Als Data In Archaeologymentioning

confidence: 99%

See 1 more Smart Citation

Semantic Segmentation (U-Net) of Archaeological Features in Airborne Laser Scanning—Example of the Białowieża Forest

Banasiak¹,

Berezowski²,

Zapłata

et al. 2022

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Airborne Laser Scanning (ALS) technology can be used to identify features of terrain relief in forested areas, possibly leading to the discovery of previously unknown archaeological monuments. Spatial interpretation of numerous objects with various shapes and sizes is a difficult challenge for archaeologists. Mapping structures with multiple elements whose area can exceed dozens of hectares, such as ancient agricultural field systems, is very time-consuming. These archaeological sites are composed of a large number of embanked fields, which together form a recognizable spatial pattern. Image classification and segmentation, as well as object recognition, are the most important tasks for deep learning neural networks (DLNN) and therefore they can be used for automatic recognition of archaeological monuments. In this study, a U-Net neural network was implemented to perform semantic segmentation of the ALS-derived data including (1) archaeological, (2) natural and (3) modern features in the Polish part of the Białowieża Forest. The performance of the U-Net segmentation model was evaluated by measuring the pixel-wise similarity between ground truth and predicted segmentation masks. After 83 epochs, The Dice-Sorensen coefficient (F1 score) and the Intersect Over Union (IoU) metrics were 0.58 and 0.5, respectively. The IoU metric reached a value of 0.41, 0.62 and 0.62 for the ancient field system banks, ancient field system plots and burial mounds, respectively. The results of the U-Net deep learning model proved very useful in semantic segmentation of images derived from ALS data.

show abstract

Section: Deep Learning and Als Data In Archaeologymentioning

confidence: 99%

Section: Deep Learning and Als Data In Archaeologymentioning

confidence: 99%

Semantic Segmentation (U-Net) of Archaeological Features in Airborne Laser Scanning—Example of the Białowieża Forest

Banasiak¹,

Berezowski²,

Zapłata

et al. 2022

Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…As demonstrated by the studies of remnants of charcoal burning and tar distilling carried out using DEM, traces of charcoal piles are common finds in Polish forests [ 37 ]. This is confirmed by historical, cultural and environmental studies [ 22 , 36 , 38 , 39 , 40 , 41 , 42 ].…”

Section: Study Resultsmentioning

confidence: 99%

Anthropogenic Landforms Derived from LiDAR Data in the Woodlands near Kotlarnia (Koźle Basin, Poland)

Waga

Szypuła

Fajer³

2022

Sensors

View full text Add to dashboard Cite

Unlike farmland or urban areas, forests have long been regarded as environments that favour the preservation of valuable geological and historical sites. However, due to invasive forestry methods, the implementation of large investment projects and the development of mining, they are increasingly no longer safe spaces for the relics of human activities recorded in landforms. Data collection, including using LiDAR technology, presents an opportunity to preserve knowledge about these landforms. Through the analysis of shaded images of a 37-hectare woodland area near Kotlarnia, landforms of various ages documenting 21 different human activities were identified, including remnants of reforestation activities, the expansion and modification of hydraulic structures and road infrastructure, charcoal burning and tar distilling, exploitation of mineral resources and military activities. The results of the remote sensing work were verified in the field.

show abstract

“…Automated methods could provide additional cognitive value. Methods such as machine learning or neural networks are already in use [80][81][82][83][84] and will be explored in the future. Since we have already verified the results in the field, we may have reference materials for automated solutions evaluation.…”

Section: Discussionmentioning

confidence: 99%

ALS-Based Detection of Past Human Activities in the Białowieża Forest—New Evidence of Unknown Remains of Past Agricultural Systems

et al. 2020

Self Cite

View full text Add to dashboard Cite

The Białowieża Forest (BF), a unique ecosystem of historical significance in central Europe, has a long history of assumed human settlement, with at least 200 known archaeological sites (until 2016). This study uncovers new evidence of the cultural heritage of this unique forest area using Airborne Laser Scanning (ALS) technology combined with traditional archaeological field assessment methods to verify the ALS data interpretations and to provide additional evidence about the function and origin of the newly detected archaeological sites. The results of this study include (1) a scientific approach for an improved identification of archaeological resources in forest areas; (2) new evidence about the history of the human use of the BF based on ALS data, covering the entire Polish part of the BF; and (3) an improved remote sensing infrastructure, supporting existing GIS (Geographic Information System) systems for the BF, a famous UNESCO Heritage site. Our study identified numerous locations with evidence of past human agricultural activities known in the literature as “field systems”, “lynchets” and “Celtic fields”. The initial identification included more than 300 km of possible field boundaries and plough headlands, many of which we have verified on the ground. Various past human activities creating those boundaries have existed since the (pre-) Roman Period up to the 13th century AD. The results of this study demonstrate that past human activities in the Polish part of the Białowieża Forest had been more prevalent than previously believed. As a practical result of the described activities, a geodatabase was created; this has practical applications for the system of monument protection in Poland, as well as for local communities and the BF’s management and conservation. The more widely achieved results are in line with the implementation of the concept of a cultural heritage inventory in forested and protected areas—the actions taken specify (built globally) the forms of protection and management of cultural and environmental goods.

show abstract

Automatyzacja w procesie detekcji obiektów archeologicznych z danych ALS

Cited by 6 publications

References 2 publications

Semantic Segmentation (U-Net) of Archaeological Features in Airborne Laser Scanning—Example of the Białowieża Forest

Semantic Segmentation (U-Net) of Archaeological Features in Airborne Laser Scanning—Example of the Białowieża Forest

Anthropogenic Landforms Derived from LiDAR Data in the Woodlands near Kotlarnia (Koźle Basin, Poland)

ALS-Based Detection of Past Human Activities in the Białowieża Forest—New Evidence of Unknown Remains of Past Agricultural Systems

Contact Info

Product

Resources

About