Object-Based Predictive Modeling (OBPM) for Archaeology: Finding Control Places in Mountainous Environments

This contribution examines the potential of object-based image analysis (OBIA) for archaeological predictive modeling starting from elevation data, by testing a ruleset for the location of “control places” on two test areas in the Alpine environment (northern Italy). The ruleset was developed on the western Asiago Plateau (Vicenza Province, Veneto) and subsequently re-applied (semi)automatically in the Isarco Valley (South Tirol). Firstly, we considered the physiographic, climatic, and morphological characteristics of the selected areas and we applied 3 DTM processing techniques: Slope, local dominance, and solar radiation. Subsequently, we employed an object-based approach to classification. Solar radiation, local dominance, and slope were visualized as a three-layer RGB image that was segmented with the multiresolution algorithm. The classification was implemented with a ruleset that selected only image–objects with high local dominance and solar radiation, but low slope, which were considered more suitable parameters for human occupation. The classification returned five areas on the Asiago Plateau that were remotely and ground controlled, confirming anthropic exploitation covering a time span from protohistory (2nd-1st millennium BC) to the First World War. Subsequently, the same model was applied to the Isarco Valley to verify the replicability of the method. The procedure resulted in 36 potential control places which find good correspondence with the archaeological sites discovered in the area. Previously unknown contexts were further controlled using very high-resolution (VHR) aerial images and digital terrain model (DTM) data, which often suggested a possible (pre-proto)historic human frequentation. The outcomes of the analysis proved the feasibility of the approach, which can be exported and applied to similar mountainous landscapes for site predictivity analysis.

Download Full-text

Archaeological Surveying of Subarctic and Arctic Landscapes: Comparing the Performance of Airborne Laser Scanning and Remote Sensing Image Data

Sustainability ◽

10.3390/su13041917 ◽

2021 ◽

Vol 13 (4) ◽

pp. 1917

Author(s):

Alma Elizabeth Thuestad ◽

Ole Risbøl ◽

Jan Ingolf Kleppe ◽

Stine Barlindhaug ◽

Elin Rose Myrvoll

Keyword(s):

Remote Sensing ◽

Laser Scanning ◽

Digital Terrain Model ◽

Image Data ◽

Remote Sensing Image ◽

Airborne Laser Scanning ◽

Aerial Images ◽

Detection Rates ◽

Airborne Laser ◽

Pros And Cons

What can remote sensing contribute to archaeological surveying in subarctic and arctic landscapes? The pros and cons of remote sensing data vary as do areas of utilization and methodological approaches. We assessed the applicability of remote sensing for archaeological surveying of northern landscapes using airborne laser scanning (LiDAR) and satellite and aerial images to map archaeological features as a basis for (a) assessing the pros and cons of the different approaches and (b) assessing the potential detection rate of remote sensing. Interpretation of images and a LiDAR-based bare-earth digital terrain model (DTM) was based on visual analyses aided by processing and visualizing techniques. 368 features were identified in the aerial images, 437 in the satellite images and 1186 in the DTM. LiDAR yielded the better result, especially for hunting pits. Image data proved suitable for dwellings and settlement sites. Feature characteristics proved a key factor for detectability, both in LiDAR and image data. This study has shown that LiDAR and remote sensing image data are highly applicable for archaeological surveying in northern landscapes. It showed that a multi-sensor approach contributes to high detection rates. Our results have improved the inventory of archaeological sites in a non-destructive and minimally invasive manner.

Download Full-text

Classification of Very-High-Spatial-Resolution Aerial Images Based on Multiscale Features with Limited Semantic Information

Remote Sensing ◽

10.3390/rs13030364 ◽

2021 ◽

Vol 13 (3) ◽

pp. 364

Author(s):

Han Gao ◽

Jinhui Guo ◽

Peng Guo ◽

Xiuwan Chen

Keyword(s):

Deep Learning ◽

Land Cover ◽

Spatial Resolution ◽

Large Scale ◽

High Spatial Resolution ◽

Training Data ◽

Aerial Images ◽

Rural Landscapes ◽

Feature Representations ◽

Object Based

Recently, deep learning has become the most innovative trend for a variety of high-spatial-resolution remote sensing imaging applications. However, large-scale land cover classification via traditional convolutional neural networks (CNNs) with sliding windows is computationally expensive and produces coarse results. Additionally, although such supervised learning approaches have performed well, collecting and annotating datasets for every task are extremely laborious, especially for those fully supervised cases where the pixel-level ground-truth labels are dense. In this work, we propose a new object-oriented deep learning framework that leverages residual networks with different depths to learn adjacent feature representations by embedding a multibranch architecture in the deep learning pipeline. The idea is to exploit limited training data at different neighboring scales to make a tradeoff between weak semantics and strong feature representations for operational land cover mapping tasks. We draw from established geographic object-based image analysis (GEOBIA) as an auxiliary module to reduce the computational burden of spatial reasoning and optimize the classification boundaries. We evaluated the proposed approach on two subdecimeter-resolution datasets involving both urban and rural landscapes. It presented better classification accuracy (88.9%) compared to traditional object-based deep learning methods and achieves an excellent inference time (11.3 s/ha).

Download Full-text

A comparison of pixel-based decision tree and object-based Support Vector Machine methods for land-cover classification based on aerial images and airborne lidar data

International Journal of Remote Sensing ◽

10.1080/01431161.2017.1371864 ◽

2017 ◽

Vol 38 (23) ◽

pp. 7176-7195 ◽

Cited By ~ 12

Author(s):

Qiong Wu ◽

Ruofei Zhong ◽

Wenji Zhao ◽

Han Fu ◽

Kai Song

Keyword(s):

Support Vector Machine ◽

Land Cover ◽

Decision Tree ◽

Land Cover Classification ◽

Airborne Lidar ◽

Aerial Images ◽

Support Vector ◽

Lidar Data ◽

Object Based ◽

Airborne Lidar Data

Download Full-text

Localização de nascentes ameaçadas em áreas urbanas: Uma estratégia preventiva de conservação ambiental com auxílio de Modelo Digital do Terreno (MDT)

Revista Brasileira de Geografia Física ◽

10.26848/rbgf.v14.4.p2186-2203 ◽

2021 ◽

Vol 14 (4) ◽

pp. 2186-2203

Author(s):

Bárbara Fernanda da Cunha Tasca ◽

Fernanda Vieira Xavier ◽

Auberto José Barros Siqueira

Keyword(s):

Land Surface ◽

Numerical Models ◽

Urban Expansion ◽

Digital Terrain Model ◽

Human Occupation ◽

Public Authorities ◽

First Order ◽

Terrain Model ◽

Drainage Channels ◽

High Level

Identifying urban headwaters and delimitating their Permanent Preservation Areas (PPA) before its inevitable degradation by the human occupation is essential to guarantee the long-term sustainability of the cities. However, the scarcity of tools for facilitating this purpose prevents public authorities from speeding up their control actions. As headwaters frequently occur near the beginning of first-order drainage channels, it is assumed that their location can be obtained by using numerical models of the land surface. Thus, this study aimed to evaluate and demonstrate the applicability of a Digital Terrain Model (MDT) as an auxiliary tool in the prospecting process in spring fields in the urban area of Cuiabá, MT, Brazil. The methodology consisted of extracting the drainage channels from the modeled area, making it possible to indicate locations for prospecting corresponding to the head regions of the first order channels. The results show that 62,8% of the occurrence of the headwaters were in a 300m radii from the first-order start points. However, it was not possible to issue a conclusive evaluation in 28,6% of the places due to the high level of anthropization. Nevertheless, only in 8,6% of them did not present any water emergence in the surroundings, indicating the effectiveness of this method in guiding the prospection of headwaters in field. We concluded that our procedures are worthful for cities that have detailed altimetric surveys, being especially useful in urban expansion areas, where the preventive character of headwaters conservation is essential.

Download Full-text

Photogrammetric surveying forests and woodlands with UAVs: techniques for automatic removal of vegetation and digital terrain model production for hydrological applications

Journal of Unmanned Vehicle Systems ◽

10.1139/juvs-2016-0023 ◽

2019 ◽

Vol 7 (1) ◽

pp. 1-20

Author(s):

Fotis Giagkas ◽

Petros Patias ◽

Charalampos Georgiadis

Keyword(s):

Vegetation Type ◽

Digital Terrain Model ◽

Point Clouds ◽

Aerial Images ◽

Surface Model ◽

Terrain Model ◽

Vegetation Height ◽

Digital Terrain ◽

Dense Point ◽

Height Model

The purpose of this study is the photogrammetric survey of a forested area using unmanned aerial vehicles (UAV), and the estimation of the digital terrain model (DTM) of the area, based on the photogrammetrically produced digital surface model (DSM). Furthermore, through the classification of the height difference between a DSM and a DTM, a vegetation height model is estimated, and a vegetation type map is produced. Finally, the generated DTM was used in a hydrological analysis study to determine its suitability compared to the usage of the DSM. The selected study area was the forest of Seih-Sou (Thessaloniki). The DTM extraction methodology applies classification and filtering of point clouds, and aims to produce a surface model including only terrain points (DTM). The method yielded a DTM that functioned satisfactorily as a basis for the hydrological analysis. Also, by classifying the DSM–DTM difference, a vegetation height model was generated. For the photogrammetric survey, 495 aerial images were used, taken by a UAV from a height of ∼200 m. A total of 44 ground control points were measured with an accuracy of 5 cm. The accuracy of the aerial triangulation was approximately 13 cm. The produced dense point cloud, counted 146 593 725 points.

Download Full-text

Comparisons on Calculating Methods of Total Daily Global Solar Radiation in Urban Area Based on Panoramic Images

E3S Web of Conferences ◽

10.1051/e3sconf/201913605010 ◽

2019 ◽

Vol 136 ◽

pp. 05010

Author(s):

Moyan Zhang ◽

Yan Liu ◽

Ruixin Chen ◽

Xiangfei Guo ◽

Weiqing Yuan ◽

...

Keyword(s):

Solar Radiation ◽

Urban Area ◽

Morphological Characteristics ◽

Global Solar Radiation ◽

View Factor ◽

Sky View Factor ◽

Panoramic Images ◽

Rayman Model ◽

Morphology Characteristics ◽

Tree View

In this paper, the total daily global solar radiation is tested at 18 locations with different morphological characteristics in Xi’an University of Architecture and Technology. PTgui is used to convert the panoramic pictures from Baidu Street Map to fisheye images. Sky view factor (SVF) and tree view factor (TVF) are calculated by Rayman model with fisheye images. SVF is used to calculate the total daily global solar radiation at the 18 locations with two different methods and TVF is used to classify the locations. The calculations and testing results are compared and combined the morphological characteristics. Then it is found that using suitable methods on different locations is necessary to obtain more accurate results whether the TVF (tree view factor) is more than 0.3 or less. To obtain solar radiation at different locations in the urban area, the calculating methods should be carefully chosen based on the morphology characteristics of the location.

Download Full-text

Power Line Extraction From Aerial Images Using Object-Based Markov Random Field With Anisotropic Weighted Penalty

IEEE Access ◽

10.1109/access.2019.2939025 ◽

2019 ◽

Vol 7 ◽

pp. 125333-125356 ◽

Cited By ~ 3

Author(s):

Le Zhao ◽

Xianpei Wang ◽

Hongtai Yao ◽

Meng Tian ◽

Zini Jian

Keyword(s):

Random Field ◽

Markov Random Field ◽

Power Line ◽

Aerial Images ◽

Line Extraction ◽

Markov Random ◽

Object Based

Download Full-text

On the ensemble of multiscale object-based classifiers for aerial images: a comparative study

Multimedia Tools and Applications ◽

10.1007/s11042-018-6023-4 ◽

2018 ◽

Vol 77 (19) ◽

pp. 24565-24592 ◽

Cited By ~ 1

Author(s):

Agnaldo Aparecido Esmael ◽

Jefersson Alex dos Santos ◽

Ricardo da Silva Torres

Keyword(s):

Comparative Study ◽

Aerial Images ◽

Object Based

Download Full-text

Analysis of Mountain Relief for the Causes of Snow Avalanches

Journal of Geology Geography and Geoecology ◽

10.15421/112071 ◽

2020 ◽

Vol 29 (4) ◽

pp. 789-795

Author(s):

Roman M. Rudyi ◽

Yuriy O. Kyselov ◽

Halyna T. Domashenko ◽

Olena Y. Kravets ◽

Kateryna D. Husar

Keyword(s):

Solar Radiation ◽

Digital Terrain Model ◽

Mountain Range ◽

Mountain Area ◽

Terrain Model ◽

Gis Technologies ◽

Digital Terrain ◽

Solar Radiation Incident ◽

Long Time ◽

Fundamental Research

The descent of avalanches is quite a usual phenomenon for the Ukrainian Carpathians, as well as for the conditions of mountain terrain in general. The Gorgany range of the Carpathian mountains is a typical avalanche-prone territory. Avalanches cause significant damage to forestry and may lead to casualties. Therefore, descent of avalanches has for a long time been a subject of fundamental research in geomorphology, meteorology, topography, photogrammetry and GIS technologies. Using photogrammetric mapping, we analyzed the causes of the descent of one of the largest avalanches in the Ukrainian Carpathians for the past 15 years. The avalanche fell from Poliensky mountain in the Gorgany mountain range in 2006, causing destruction of a great amount of forest. The main causes of avalanches were divided into two groups, the first including more or less stable factors caused by impact of terrain and somewhat less by solar radiation and the second group comprising meteorological factors, such as prolonged snowstorms and snowfall, that is, different fluctuations in weather. The main attention was paid to the first group of factors. For this purpose, a digital terrain model (DTM) of the study area was developed, visualizing the terrain, demonstrating the studied slope of the mountain along which the avalanche slid. According to the digital model, we developed maps of the steepness andexposition of the slope. Also we calculated the coefficient for solar radiation incident on the slope and which depends on the height of the Sun above the horizon and the coordinates of the slope. Using these data, the illuminance map of the Poliensky mountain area was developed. Studies conducted using GIS technologies led to the conclusion that the determining factors that triggered the powerful avalanche from Poliensky mountain were the great steepness and length of the slope, as well as the absence of forest at the top of the mountain, i.e. at the beginning of the avalanche track.

Download Full-text