URBAN VEGETATION DETECTION BASED ON THE LAND-COVER CLASSIFICATION OF PLANETSCOPE, RAPIDEYE AND WORLDVIEW-2 SATELLITE IMAGERY

One of the problems that are encountered today is the migration from rural to urban areas. Cities are becoming overpopulated and consequently overbuilt. Due to the high demand for new residential and commercial buildings, in the last few decades, green zones such as parks are often becoming built. In the cities, there is increasingly less room left to nature. Urban vegetation has a large impact on the quality of life in cities. The aim of this research is the detection of urban vegetation by three independent multispectral (MS), and high spatial resolution satellite imagery. Satellite imagery with various spatial resolution and spectral characteristics are used in this research. The study area is the capital city of Croatia, Zagreb. For this research MS imagery from PlanetScope (PS), Rapideye (RE) and WorldView-2 (WV2) satellites were obtained within project “Geospatial Monitoring of green infrastructure by means of terrestrial, airborne and satellite imagery” (GEMINI). PS 3.7-m spatial resolution imagery has 4 bands (blue, green, red and near-infrared), RE 5-m spatial resolution imagery has 5 bands (blue, green, red, red edge and near-infrared) and WV2 2-m spatial resolution imagery has 8 bands (coastal, blue, green, yellow, red, red edge, near-Infrared 1 and near-infrared 2). Above mentioned satellite imagery with different spatial resolution and spectral characteristics were used to obtain three independent land-cover classifications of the city of Zagreb. Based on the land-cover classification entire study area was divided into 5 classes (water, bare soil, built-up, forest and low vegetation). Supervised classification was made with a random forest (RF) classifier based on manually collected training polygons. Accuracy assessment of the different resolution land-cover classifications was calculated based on the reference polygons. The main goal of this research is the accuracy comparison of the land-cover classifications conducted on three different satellite imagery sources. According to expectations highest overall accuracy and user’s accuracies for each class has WV2 satellite imagery, then PS, and lowest accuracy has RE satellite imagery. This is important for the further research on project GEMINI especially for detection and monitoring of urban vegetation as one of the most important factors of life quality in cities.

[1]  Mario Chica-Olmo,et al.  An assessment of the effectiveness of a random forest classifier for land-cover classification , 2012 .

[2]  M. Gašparović,et al.  The effect of fusing Sentinel-2 bands on land-cover classification , 2018 .

[3]  René Roland Colditz,et al.  An Evaluation of Different Training Sample Allocation Schemes for Discrete and Continuous Land Cover Classification Using Decision Tree-Based Algorithms , 2015, Remote. Sens..

[4]  Robert C. Weih,et al.  OBJECT-BASED CLASSIFICATION VS . PIXEL-BASED CLASSIFICATION : COMPARITIVE IMPORTANCE OF MULTI-RESOLUTION IMAGERY , 2010 .

[5]  Mateo Gašparović,et al.  Analiza urbanizacije grada Splita , 2017 .

[6]  Mariana Belgiu,et al.  Random forest in remote sensing: A review of applications and future directions , 2016 .

[7]  Clement Atzberger,et al.  Tree Species Classification with Random Forest Using Very High Spatial Resolution 8-Band WorldView-2 Satellite Data , 2012, Remote. Sens..

[8]  Stephen J. Ventura,et al.  Fuzzy and isodata classification of landform elements from digital terrain data in Pleasant Valley, Wisconsin , 1997 .

[9]  Giles M. Foody,et al.  Status of land cover classification accuracy assessment , 2002 .

[10]  Qihao Weng,et al.  A survey of image classification methods and techniques for improving classification performance , 2007 .

[11]  J. Orestes Cerdeira,et al.  Contextual classification of remotely sensed images with integer linear programming , 2006, CompIMAGE.

[12]  Sharda Nagorao Dhoke,et al.  Satellite Image Classification Methods and Techniques: A Review , 2018 .

[13]  A. Viera,et al.  Understanding interobserver agreement: the kappa statistic. , 2005, Family medicine.