Fuel type mapping using object-based image analysis of DMC and Landsat-8 OLI imagery

<p>Wildfires have been an integral part of the Mediterranean ecosystem. Moreover, the Intergovernmental Panel on Climate Change (IPCC) Fifth Assessment Report emphasizes that the Mediterranean basin is expected to be drier by the end of the 21st century, while future warming will possibly be higher than the global mean. Therefore, outbreaks of wildfires are expected to increase. One of the most important factors for wildfire behavior apart from the meteorological conditions, is fuel types. In this study, a detailed fuel type mapping in a case study area was addressed. To accomplish this goal, an object-based image analysis (OBIA) approach was implemented using the open-source Orfeo toolbox. The freely available Sentinel-2A satellite images were processed in combination with auxiliary European and National scale GIS data. The classification results demonstrate a high-quality Land Cover map with 84% of overall accuracy. The classified land cover polygons were associated with high-resolution tree cover density data derived from Copernicus Land Monitoring Service. This coupling led to the synthesis of the fuel type map. To this end, this approach can fulfill the efficient mapping of fuel types for operational purposes. This research has been co&#8208;financed by the European Regional Development Fund of the European Union and Greek national funds through the Operational Program Competitiveness, Entrepreneurship and Innovation, under the call RESEARCH &#8211;CREATE &#8211;INNOVATE&#160; (project code:T2EDK-01967)</p>

Download Full-text

Object-based image analysis of suburban landscapes using Landsat-8 imagery

International Journal of Digital Earth ◽

10.1080/17538947.2018.1474959 ◽

2018 ◽

Vol 12 (6) ◽

pp. 720-736 ◽

Cited By ~ 2

Author(s):

Ming Shang ◽

Shixin Wang ◽

Yi Zhou ◽

Cong Du ◽

Wenliang Liu

Keyword(s):

Image Analysis ◽

Landsat 8 ◽

Object Based Image Analysis ◽

Object Based

Download Full-text

Fuzzy Object-Based Image Analysis Methods Using Sentinel-2A and Landsat-8 Data to Map and Characterize Soil Surface Residue

Remote Sensing ◽

10.3390/rs11212583 ◽

2019 ◽

Vol 11 (21) ◽

pp. 2583 ◽

Cited By ~ 2

Author(s):

Payam Najafi ◽

Hossein Navid ◽

Bakhtiar Feizizadeh ◽

Iraj Eskandari ◽

Thomas Blaschke

Keyword(s):

Image Analysis ◽

Agricultural Research ◽

Soil Surface ◽

Control Measures ◽

Landsat 8 ◽

Surface Residue ◽

Ground Truth Data ◽

Object Based Image Analysis ◽

Object Based ◽

Sentinel 2A

Soil degradation, defined as the lowering and loss of soil functions, is becoming a serious problem worldwide and threatens agricultural production and terrestrial ecosystems. The surface residue of crops is one of the most effective erosion control measures and it increases the soil moisture content. In some areas of the world, the management of soil surface residue (SSR) is crucial for increasing soil fertility, maintaining high soil carbon levels, and reducing the degradation of soil due to rain and wind erosion. Standard methods of measuring the residue cover are time and labor intensive, but remote sensing can support the monitoring of conservation tillage practices applied to large fields. We investigated the potential of per-pixel and object-based image analysis (OBIA) for detecting and estimating the coverage of SSRs after tillage and planting practices for agricultural research fields in Iran using tillage indices for Landsat-8 and novel indices for Sentinel-2A. For validation, SSR was measured in the field through line transects at the beginning of the agricultural season (prior to autumn crop planting). Per-pixel approaches for Landsat-8 satellite images using normalized difference tillage index (NDTI) and simple tillage index (STI) yielded coefficient of determination (R2) values of 0.727 and 0.722, respectively. We developed comparable novel indices for Sentinel-2A satellite data that yielded R2 values of 0.760 and 0.759 for NDTI and STI, respectively, which means that the Sentinel data better matched the ground truth data. We tested several OBIA methods and achieved very high overall accuracies of up to 0.948 for Sentinel-2A and 0.891 for Landsat-8 with a membership function method. The OBIA methods clearly outperformed per-pixel approaches in estimating SSR and bear the potential to substitute or complement ground-based techniques.

Download Full-text

Efficient paddy field mapping using Landsat-8 imagery and object-based image analysis based on advanced fractel net evolution approach

GIScience & Remote Sensing ◽

10.1080/15481603.2016.1273438 ◽

2016 ◽

Vol 54 (3) ◽

pp. 354-380 ◽

Cited By ~ 16

Author(s):

Tengfei Su

Keyword(s):

Image Analysis ◽

Paddy Field ◽

Landsat 8 ◽

Field Mapping ◽

Object Based Image Analysis ◽

Object Based ◽

Evolution Approach

Download Full-text

MAPPING BURNT AREAS USING THE SEMI-AUTOMATIC OBJECT-BASED IMAGE ANALYSIS METHOD

International Journal of Remote Sensing and Earth Sciences (IJReSES) ◽

10.30536/j.ijreses.2020.v17.a3281 ◽

2020 ◽

Vol 17 (1) ◽

pp. 57

Author(s):

Hana Listi Fitriana ◽

Suwarsono Suwarsono ◽

Eko Kusratmoko ◽

Supriatna Supriatna

Keyword(s):

Image Analysis ◽

Geographical Area ◽

Remote Sensing Data ◽

Environmental Damage ◽

Landsat 8 ◽

Fast Method ◽

Object Based Image Analysis ◽

Object Based ◽

Burnt Areas ◽

The Impact

Forest and land fires in Indonesia take place almost every year, particularly in the dry season and in Sumatra and Kalimantan. Such fires damage the ecosystem, and lower the quality of life of the community, especially in health, social and economic terms. To establish the location of forest and land fires, it is necessary to identify and analyse burnt areas. Information on these is necessary to determine the environmental damage caused, the impact on the environment, the carbon emissions produced, and the rehabilitation process needed. Identification methods of burnt land was made both visually and digitally by utilising satellite remote sensing data technology. Such data were chosen because they can identify objects quickly and precisely. Landsat 8 image data have many advantages: they can be easily obtained, the archives are long and they are visible to thermal wavelengths. By using a combination of visible, infrared and thermal channels through the semi-automatic object-based image analysis (OBIA) approach, the study aims to identify burnt areas in the geographical area of Indonesia. The research concludes that the semi-automatic OBIA approach based on the red, infrared and thermal spectral bands is a reliable and fast method for identifying burnt areas in regions of Sumatra and Kalimantan.

Download Full-text

Leveraging Machine Learning to Extend Ontology-Driven Geographic Object-Based Image Analysis (O-GEOBIA): A Case Study in Forest-Type Mapping

Remote Sensing ◽

10.3390/rs11050503 ◽

2019 ◽

Vol 11 (5) ◽

pp. 503 ◽

Cited By ~ 5

Author(s):

Sachit Rajbhandari ◽

Jagannath Aryal ◽

Jon Osborn ◽

Arko Lucieer ◽

Robert Musk

Keyword(s):

Machine Learning ◽

Image Analysis ◽

Classification Accuracy ◽

Forest Type ◽

Rule Based ◽

Object Based Image Analysis ◽

Type Mapping ◽

Object Based ◽

Geographic Object

Ontology-driven Geographic Object-Based Image Analysis (O-GEOBIA) contributes to the identification of meaningful objects. In fusing data from multiple sensors, the number of feature variables is increased and object identification becomes a challenging task. We propose a methodological contribution that extends feature variable characterisation. This method is illustrated with a case study in forest-type mapping in Tasmania, Australia. Satellite images, airborne LiDAR (Light Detection and Ranging) and expert photo-interpretation data are fused for feature extraction and classification. Two machine learning algorithms, Random Forest and Boruta, are used to identify important and relevant feature variables. A variogram is used to describe textural and spatial features. Different variogram features are used as input for rule-based classifications. The rule-based classifications employ (i) spectral features, (ii) vegetation indices, (iii) LiDAR, and (iv) variogram features, and resulted in overall classification accuracies of 77.06%, 78.90%, 73.39% and 77.06% respectively. Following data fusion, the use of combined feature variables resulted in a higher classification accuracy (81.65%). Using relevant features extracted from the Boruta algorithm, the classification accuracy is further improved (82.57%). The results demonstrate that the use of relevant variogram features together with spectral and LiDAR features resulted in improved classification accuracy.

Download Full-text