A novel spectral index to automatically extract road networks from WorldView-2 satellite imagery

Shahi, Kaveh; Shafri, Helmi Zulhaidi Mohd; Taherzadeh, Ebrahim; Mansor, Shattri; Muniandy, Ratnasamy

doi:10.1016/j.ejrs.2014.12.003

Cited by 51 publications

(44 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Built-up Area Index (BAI) BLUE−NIR BLUE+NIR [61] Chlorophyll Green index (CGI) NIR GREEN+RE1 [62] Global Environmental Monitoring Index (GEMI) η − 0.25η 2 − RED−0.125 1−RED η = 2(NIR 2 −RED 2 )+1.5NIR+0.5RED NIR+RED+0.5 [63] Greenness Index (GI) Red-Edge Triangular Vegetation Index (RETVI) 100 (NIR − RE1) − 10 (NIR − GREEN) [74] Soil Adjusted Vegetation Index (SAVI) NIR−RED NIR+RED+0.5 1.5 [75] Blue and RE1 ratio (SRBRE1) BLUE RE1 [64] Blue and RE2 ratio (SRBRE2) BLUE RE2 [76] Blue and RE3 ratio (SRBRE3) BLUE RE3 [67] NIR and Blue ratio (SRNIRB) NIR BLUE [77] NIR and Green ratio (SRNIRG) NIR GREEN [64] NIR and Red ratio (SRNIRR) NIR RED [77] NIR and RE1 ratio (SRNIRRE1) NIR RE1 [62] NIR and RE2 ratio (SRNIRRE2) NIR RE2 [67] NIR and RE3 ratio (SRNIRR3) NIR RE3 [67] Soil Tillage Index (STI) SWIR1 SWIR2 [68] Water Body Index (WBI) BLUE−RED BLUE+RED [78] Figure A1. Aggregated feature importance for the broadleaf stratum derived from the combination of all classification models, based on spectral bands and vegetation indices (please see Figure 4 for more details about the graph and Table A1 for the Vegetation indices description).…”

Section: Name Formula Referencementioning

confidence: 99%

Optimal Input Features for Tree Species Classification in Central Europe Based on Multi-Temporal Sentinel-2 Data

et al. 2019

View full text Add to dashboard Cite

Detailed knowledge about tree species composition is of great importance for forest management. The two identical European Space Agency (ESA) Sentinel-2 (S2) satellites provide data with unprecedented spectral, spatial and temporal resolution. Here, we investigated the potential benefits of using high temporal resolution data for classification of five coniferous and seven broadleaved tree species in a diverse Central European Forest. To run the classification, 18 cloud-free S2 acquisitions were analyzed in a two-step approach. The available scenes were first used to stratify the study area into six broad land-cover classes. Subsequently, additional classification models were created separately for the coniferous and the broadleaved forest strata. To permit a deeper analytical insight in the benefits of multi-temporal datasets for species identification, classification models were developed taking into account all 262,143 possible permutations of the 18 S2 scenes. Each model was fine-tuned using a stepwise recursive feature reduction. The additional use of vegetation indices improved the model performances by around 5 percentage points. Individual mono-temporal tree species accuracies range from 48.1% (January 2017) to 78.6% (June 2017). Compared to the best mono-temporal results, the multi-temporal analysis approach improves the out-of-bag overall accuracy from 72.9% to 85.7% for the broadleaved and from 83.8% to 95.3% for the coniferous tree species, respectively. Remarkably, a combination of six–seven scenes achieves a model quality equally high as the model based on all data; images from April until August proved most important. The classes European Beech and European Larch attain the highest user’s accuracies of 96.3% and 95.9%, respectively. The most important spectral variables to distinguish between tree species are located in the Red (coniferous) and short wave infrared (SWIR) bands (broadleaved), respectively. Overall, the study highlights the high potential of multi-temporal S2 data for species-level classifications in Central European forests.

show abstract

Section: Name Formula Referencementioning

confidence: 99%

Optimal Input Features for Tree Species Classification in Central Europe Based on Multi-Temporal Sentinel-2 Data

et al. 2019

View full text Add to dashboard Cite

show abstract

“…The foreground classes have been chosen within a set of key structuring landscape objects described in Section 2.1.1. The separability analysis, described in Section 2.1.2, has been performed for the spectral bands, for common spectral indices used to enhance the discrimination as well as for new indices based on the less common spectral bands available from Sentinel-2 (Table 2 [ [39][40][41][42][43][44][45][46][47][48][49][50][51][52][53][54][55][56][57][58]). For this purpose, pure spectral signatures of objects have been extracted from the images at well known locations (see Section 3).…”

Section: Spectral Resolution For Spatial Object Detectionmentioning

confidence: 99%

Sentinel-2’s Potential for Sub-Pixel Landscape Feature Detection

et al. 2016

View full text Add to dashboard Cite

Land cover and land use maps derived from satellite remote sensing imagery are critical to support biodiversity and conservation, especially over large areas. With its 10 m to 20 m spatial resolution, Sentinel-2 is a promising sensor for the detection of a variety of landscape features of ecological relevance. However, many components of the ecological network are still smaller than the 10 m pixel, i.e., they are sub-pixel targets that stretch the sensor’s resolution to its limit. This paper proposes a framework to empirically estimate the minimum object size for an accurate detection of a set of structuring landscape foreground/background pairs. The developed method combines a spectral separability analysis and an empirical point spread function estimation for Sentinel-2. The same approach was also applied to Landsat-8 and SPOT-5 (Take 5), which can be considered as similar in terms of spectral definition and spatial resolution, respectively. Results show that Sentinel-2 performs consistently on both aspects. A large number of indices have been tested along with the individual spectral bands and target discrimination was possible in all but one case. Overall, results for Sentinel-2 highlight the critical importance of a good compromise between the spatial and spectral resolution. For instance, the Sentinel-2 roads detection limit was of 3 m and small water bodies are separable with a diameter larger than 11 m. In addition, the analysis of spectral mixtures draws attention to the uneven sensitivity of a variety of spectral indices. The proposed framework could be implemented to assess the fitness for purpose of future sensors within a large range of applications.

show abstract

“…In addition, commercial data from sensors such as from SPOT 6/7, Rapid Eye and Worldview are increasingly becoming affordable, with the capability for user-defined tasking plans, which are useful for repeated and on-demand image acquisitions at a specific area of interest such as disaster-stricken areas. These sensors are instrumental in deriving and maintaining most geospatial baseline datasets, such as road and railway networks [33,34], forest inventory [35,36], wetland delineation [37,38], digital elevation models [39][40][41], river and stream networks [42], building structures [43], agricultural field boundaries [44,45], and powerlines [46]. Innovative agreements such as the Single License-Multi-User Agreement (SLMA) for negotiating cheaper high-resolution data for multiple countries need to be explored in Africa.…”

Section: Earth Observation Data For Capacity Buildingmentioning

confidence: 99%

The Role of African Emerging Space Agencies in Earth Observation Capacity Building for Facilitating the Implementation and Monitoring of the African Development Agenda: The Case of African Earth Observation Program

Kganyago

Mhangara

2019

IJGI

View full text Add to dashboard Cite

AU-Agenda 2063 was adopted at the 24th Ordinary Session of the African Heads of State and Government in 2015 as the blueprint for the future development of the continent. Built upon the continent’s past experiences, challenges, and successes, AU-Agenda 2063 comprehensively describes the strategic path for Africa’s future development in the next 50 years. Thus, the monitoring of its implementation in various African states is critical for ensuring sustainable development and track progress. However, the higher cost of collecting data for accurately and reliably monitoring the implementation of Agenda 2063 may hinder the progress towards achieving these goals. Satellite Earth observation provides ample data, and thus has provided opportunities for the development of novel products and services with the potential to support implementation, monitoring and reporting for AU-Agenda 2063 development imperatives. However, it has been limitedly exploited in Africa, as evidenced by lower research outputs and investments. This calls for increased capacity building in the use of available EO data and products for various users including decision makers to advance national, regional and continental priorities. The use of such data products is often hampered by the capability to understand the products and thus their value for addressing socio-economic challenges. This paper discusses the potential of Earth observation capacity building for supporting the implementation, monitoring of, and reporting towards achieving AU-Agenda 2063 development imperatives. Specifically, this paper identifies existing capacity building resources, including the role of open and free Earth observation data, open-source software, and product dissemination platforms that can be leveraged for supporting national development, service delivery and the achievement of AU-Agenda 2063 targets. Furthermore, the paper recognizes the importance of bilateral and multilateral partnerships in leveraging existing know-how, technology and other resources for advancing strategic goals of African emerging space agencies and promoting sustainable development, with examples from South African National Space Agency (SANSA). Then, the challenges and opportunities for capacity building and the wide adoption of EO in Africa are discussed in the context of AU-Agenda 2063. The paper thus concludes that EO capacity building is essential to address the skills and data gaps and increase the use of EO-based solutions for decision making in various sectors, critical for achieving AU-A2063.

show abstract

A novel spectral index to automatically extract road networks from WorldView-2 satellite imagery

Cited by 51 publications

References 30 publications

Optimal Input Features for Tree Species Classification in Central Europe Based on Multi-Temporal Sentinel-2 Data

Optimal Input Features for Tree Species Classification in Central Europe Based on Multi-Temporal Sentinel-2 Data

Sentinel-2’s Potential for Sub-Pixel Landscape Feature Detection

The Role of African Emerging Space Agencies in Earth Observation Capacity Building for Facilitating the Implementation and Monitoring of the African Development Agenda: The Case of African Earth Observation Program

Contact Info

Product

Resources

About