Object-based image segmentation in photogrammetry for cartographic use

2021 ◽  
Author(s):  
Béla Kovács ◽  
Márton Pál ◽  
Fanni Vörös
Keyword(s):  
Land Cover ◽  
Large Scale ◽  
Autonomous Vehicle ◽  
Unsupervised Classification ◽  
Large Set ◽  
Bare Rock ◽  
Object Based ◽  
Social Fund ◽  
Elevation Data ◽  
Control Technologies

<p>The use of aerial photography in topography has started in the first decades of the 20<sup>th</sup> century. Remote sensed data have become indispensable for cartographers and GIS staff when doing large-scale mapping: especially topographic, orienteering and thematic maps. The use of UAVs (unmanned aerial vehicles) for this purpose has also become widespread for some years. Various drones and sensors (RGB, multispectral and hyperspectral) with many specifications are used to capture and process the physical properties of an examined area. In parallel with the development of the hardware, new software solutions are emerging to visualize and analyse photogrammetric material: a large set of algorithms with different approaches are available for image processing.</p><p>Our study focuses on the large-scale topographic mapping of vegetation and land cover. Most traditional analogue and digital maps use these layers either for background or highlighted thematic purposes. We propose to use the theory of OBIA – Object-based Image Analysis to differentiate cover types. This method involves pixels to be grouped into larger polygon units based on either spectral or other variables (e.g. elevation, aspect, curvature in case of DEMs). The neighbours of initial seed points are examined whether they should be added to the region according to the similarity of their attributes. Using OBIA, different land cover types (trees, grass, soils, bare rock surfaces) can be distinguished either with supervised or unsupervised classification – depending on the purposes of the analyst. Our base data were high-resolution RGB and multispectral images (with 5 bands).</p><p>Following this methodology, not only elevation data (e.g. shaded relief or vector contour lines) can be derived from UAV imagery but vector land cover data are available for cartographers and GIS analysts. As the number of distinct land cover groups is free to choose, even quite complex thematic layers can be produced. These layers can serve as subjects of further analyses or for cartographic visualization.</p><p> </p><p>BK is supported by Application Domain Specific Highly Reliable IT Solutions” project  has been implemented with the support provided from the National Research, Development and Innovation Fund of Hungary, financed under the Thematic Excellence Programme TKP2020-NKA-06 (National Challenges Subprogramme) funding scheme.</p><p>MP and FV are supported by EFOP-3.6.3-VEKOP-16-2017-00001: Talent Management in Autonomous Vehicle Control Technologies – The Project is financed by the Hungarian Government and co-financed by the European Social Fund.</p>

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

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).

scholarly journals Land Cover Classification of Nine Perennial Crops Using Sentinel-1 and -2 Data

2019 ◽  
Vol 12 (1) ◽  
pp. 96 ◽  
Author(s):  
James Brinkhoff ◽  
Justin Vardanega ◽  
Andrew J. Robson
Keyword(s):  
Land Cover ◽  
Large Scale ◽  
Satellite Image ◽  
Resource Planning ◽  
Support Vector ◽  
Perennial Crop ◽  
Perennial Crops ◽  
Object Based ◽  
Rbf Kernel

Land cover mapping of intensive cropping areas facilitates an enhanced regional response to biosecurity threats and to natural disasters such as drought and flooding. Such maps also provide information for natural resource planning and analysis of the temporal and spatial trends in crop distribution and gross production. In this work, 10 meter resolution land cover maps were generated over a 6200 km2 area of the Riverina region in New South Wales (NSW), Australia, with a focus on locating the most important perennial crops in the region. The maps discriminated between 12 classes, including nine perennial crop classes. A satellite image time series (SITS) of freely available Sentinel-1 synthetic aperture radar (SAR) and Sentinel-2 multispectral imagery was used. A segmentation technique grouped spectrally similar adjacent pixels together, to enable object-based image analysis (OBIA). K-means unsupervised clustering was used to filter training points and classify some map areas, which improved supervised classification of the remaining areas. The support vector machine (SVM) supervised classifier with radial basis function (RBF) kernel gave the best results among several algorithms trialled. The accuracies of maps generated using several combinations of the multispectral and radar bands were compared to assess the relative value of each combination. An object-based post classification refinement step was developed, enabling optimization of the tradeoff between producers’ accuracy and users’ accuracy. Accuracy was assessed against randomly sampled segments, and the final map achieved an overall count-based accuracy of 84.8% and area-weighted accuracy of 90.9%. Producers’ accuracies for the perennial crop classes ranged from 78 to 100%, and users’ accuracies ranged from 63 to 100%. This work develops methods to generate detailed and large-scale maps that accurately discriminate between many perennial crops and can be updated frequently.

A Multi Scale Feature Extraction Approach to Improve Land Use Land Cover Classification Accuracy using IRS LISS IV Imagery

2016 ◽  
Vol 1 (1) ◽  
pp. 3-17 ◽  
Author(s):  
Kuntal Ganguly ◽  
Mohit Modi ◽  
Manoj Raj Saxena ◽  
Ravali Bharadwaj ◽  
Divya Vijayan V. ◽  
...  
Keyword(s):  
Land Use ◽  
Feature Extraction ◽  
Land Cover ◽  
Large Scale ◽  
Land Use Land Cover ◽  
Scale Feature ◽  
Multi Scale ◽  
Knowledge Based ◽  
Object Based ◽  
Processing Techniques

The study presents an approach to map Land Use / Land Cover Change (LULCC) at large scale and processing techniques that permit higher accuracy. IRS RESOURCESAT-2 LISS-IV images of Nellore district of Andhra Pradesh were used to apply the classification technique. In multi-scale feature extraction approach LULCC takes two forms i.e. conversion from one category of LULCC to another and modification of condition within a category. Thus, major LULCC classes were extracted using object based approach and uncertain classes were identified using onscreen knowledge based method. The results showed in 2009, the accuracy of cropland, water body and built-up segments were 99.3%, 94.79% and 89.72%, respectively, whereas, in 2013 the accuracies were 94.31%, 88.26% and 81.20%, respectively. Hence, this classification approach can be useful in different landscape structure over the time, which can be quantified and assessed to achieve a better understanding of the land cover.

Adsorption Isotherm Predictions for Multiple Molecules in MOFs Using the Same Deep Learning Model

2019 ◽  
Author(s):  
Ryther Anderson ◽  
Achay Biong ◽  
Diego Gómez-Gualdrón
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Molecular Simulation ◽  
Large Scale ◽  
Learning Model ◽  
Operating Conditions ◽  
Small Subset ◽  
Screening Methods ◽  
Large Set ◽  
Metal Organic

<div>Tailoring the structure and chemistry of metal-organic frameworks (MOFs) enables the manipulation of their adsorption properties to suit specific energy and environmental applications. As there are millions of possible MOFs (with tens of thousands already synthesized), molecular simulation, such as grand canonical Monte Carlo (GCMC), has frequently been used to rapidly evaluate the adsorption performance of a large set of MOFs. This allows subsequent experiments to focus only on a small subset of the most promising MOFs. In many instances, however, even molecular simulation becomes prohibitively time consuming, underscoring the need for alternative screening methods, such as machine learning, to precede molecular simulation efforts. In this study, as a proof of concept, we trained a neural network as the first example of a machine learning model capable of predicting full adsorption isotherms of different molecules not included in the training of the model. To achieve this, we trained our neural network only on alchemical species, represented only by their geometry and force field parameters, and used this neural network to predict the loadings of real adsorbates. We focused on predicting room temperature adsorption of small (one- and two-atom) molecules relevant to chemical separations. Namely, argon, krypton, xenon, methane, ethane, and nitrogen. However, we also observed surprisingly promising predictions for more complex molecules, whose properties are outside the range spanned by the alchemical adsorbates. Prediction accuracies suitable for large-scale screening were achieved using simple MOF (e.g. geometric properties and chemical moieties), and adsorbate (e.g. forcefield parameters and geometry) descriptors. Our results illustrate a new philosophy of training that opens the path towards development of machine learning models that can predict the adsorption loading of any new adsorbate at any new operating conditions in any new MOF.</div>

scholarly journals A Novel Unsupervised Classification Method for Sandy Land Using Fully Polarimetric SAR Data

2021 ◽  
Vol 13 (3) ◽  
pp. 355
Author(s):  
Weixian Tan ◽  
Borong Sun ◽  
Chenyu Xiao ◽  
Pingping Huang ◽  
Wei Xu ◽  
...  
Keyword(s):  
Spectral Clustering ◽  
Large Scale ◽  
Clustering Algorithm ◽  
Feature Vector ◽  
Unsupervised Classification ◽  
Classification Method ◽  
Sandy Land ◽  
Classification Methods ◽  
The Many ◽  
Representative Points

Classification based on polarimetric synthetic aperture radar (PolSAR) images is an emerging technology, and recent years have seen the introduction of various classification methods that have been proven to be effective to identify typical features of many terrain types. Among the many regions of the study, the Hunshandake Sandy Land in Inner Mongolia, China stands out for its vast area of sandy land, variety of ground objects, and intricate structure, with more irregular characteristics than conventional land cover. Accounting for the particular surface features of the Hunshandake Sandy Land, an unsupervised classification method based on new decomposition and large-scale spectral clustering with superpixels (ND-LSC) is proposed in this study. Firstly, the polarization scattering parameters are extracted through a new decomposition, rather than other decomposition approaches, which gives rise to more accurate feature vector estimate. Secondly, a large-scale spectral clustering is applied as appropriate to meet the massive land and complex terrain. More specifically, this involves a beginning sub-step of superpixels generation via the Adaptive Simple Linear Iterative Clustering (ASLIC) algorithm when the feature vector combined with the spatial coordinate information are employed as input, and subsequently a sub-step of representative points selection as well as bipartite graph formation, followed by the spectral clustering algorithm to complete the classification task. Finally, testing and analysis are conducted on the RADARSAT-2 fully PolSAR dataset acquired over the Hunshandake Sandy Land in 2016. Both qualitative and quantitative experiments compared with several classification methods are conducted to show that proposed method can significantly improve performance on classification.

scholarly journals Pixel- vs. Object-Based Landsat 8 Data Classification in Google Earth Engine Using Random Forest: The Case Study of Maiella National Park

2021 ◽  
Vol 13 (12) ◽  
pp. 2299
Author(s):  
Andrea Tassi ◽  
Daniela Gigante ◽  
Giuseppe Modica ◽  
Luciano Di Martino ◽  
Marco Vizzari
Keyword(s):  
Land Cover ◽  
National Park ◽  
Time Window ◽  
Central Italy ◽  
Google Earth ◽  
Data Cube ◽  
Landsat 8 ◽  
Change Analysis ◽  
Object Based ◽  
Google Earth Engine

With the general objective of producing a 2018–2020 Land Use/Land Cover (LULC) map of the Maiella National Park (central Italy), useful for a future long-term LULC change analysis, this research aimed to develop a Landsat 8 (L8) data composition and classification process using Google Earth Engine (GEE). In this process, we compared two pixel-based (PB) and two object-based (OB) approaches, assessing the advantages of integrating the textural information in the PB approach. Moreover, we tested the possibility of using the L8 panchromatic band to improve the segmentation step and the object’s textural analysis of the OB approach and produce a 15-m resolution LULC map. After selecting the best time window of the year to compose the base data cube, we applied a cloud-filtering and a topography-correction process on the 32 available L8 surface reflectance images. On this basis, we calculated five spectral indices, some of them on an interannual basis, to account for vegetation seasonality. We added an elevation, an aspect, a slope layer, and the 2018 CORINE Land Cover classification layer to improve the available information. We applied the Gray-Level Co-Occurrence Matrix (GLCM) algorithm to calculate the image’s textural information and, in the OB approaches, the Simple Non-Iterative Clustering (SNIC) algorithm for the image segmentation step. We performed an initial RF optimization process finding the optimal number of decision trees through out-of-bag error analysis. We randomly distributed 1200 ground truth points and used 70% to train the RF classifier and 30% for the validation phase. This subdivision was randomly and recursively redefined to evaluate the performance of the tested approaches more robustly. The OB approaches performed better than the PB ones when using the 15 m L8 panchromatic band, while the addition of textural information did not improve the PB approach. Using the panchromatic band within an OB approach, we produced a detailed, 15-m resolution LULC map of the study area.

SateLoc: A Virtual Fingerprinting Approach to Outdoor LoRa Localization Using Satellite Images

2021 ◽  
Vol 17 (4) ◽  
pp. 1-28
Author(s):  
Yuxiang Lin ◽  
Wei Dong ◽  
Yi Gao ◽  
Tao Gu
Keyword(s):  
Land Cover ◽  
Large Scale ◽  
Satellite Images ◽  
Low Cost ◽  
Tracking Error ◽  
Location Based Services ◽  
Distance Constraint ◽  
Combination Strategy ◽  
Land Cover Types ◽  
High Resolution Satellite Images

With the increasing relevance of the Internet of Things and large-scale location-based services, LoRa localization has been attractive due to its low-cost, low-power, and long-range properties. However, existing localization approaches based on received signal strength indicators are either easily affected by signal fading of different land-cover types or labor intensive. In this work, we propose SateLoc, a LoRa localization system that utilizes satellite images to generate virtual fingerprints. Specifically, SateLoc first uses high-resolution satellite images to identify land-cover types. With the path loss parameters of each land-cover type, SateLoc can automatically generate a virtual fingerprinting map for each gateway. We then propose a novel multi-gateway combination strategy, which is weighted by the environmental interference of each gateway, to produce a joint likelihood distribution for localization and tracking. We implement SateLoc with commercial LoRa devices without any hardware modification, and evaluate its performance in a 227,500-m urban area. Experimental results show that SateLoc achieves a median localization error of 43.5 m, improving more than 50% compared to state-of-the-art model-based approaches. Moreover, SateLoc can achieve a median tracking error of 37.9 m with the distance constraint of adjacent estimated locations. More importantly, compared to fingerprinting-based approaches, SateLoc does not require the labor-intensive fingerprint acquisition process.

Sign in / Sign up

Export Citation Format

Share Document