Identifying vegetation in arid regions using object-based image analysis with RGB-only aerial imagery

Micha Silver, Arti Tiwari, Arnon Karnieli

Research output: Contribution to journalArticlepeer-review

6 Scopus citations

Abstract

Vegetation state is usually assessed by calculating vegetation indices (VIs) derived from remote sensing systems where the near infrared (NIR) band is used to enhance the vegetation signal. However VIs are pixel-based and require both visible and NIR bands. Yet, most archived photographs were obtained with cameras that record only the three visible bands. Attempts to construct VIs with the visible bands alone have shown only limited success, especially in drylands. The current study identifies vegetation patches in the hyperarid Israeli desert using only the visible bands from aerial photographs by adapting an alternative geospatial object-based image analysis (GEOBIA) routine, together with recent improvements in preprocessing. The preprocessing step selects a balanced threshold value for image segmentation using unsupervised parameter optimization. Then the images undergo two processes: segmentation and classification. After tallying modeled vegetation patches that overlap true tree locations, both true positive and false positive rates are obtained from the classification and receiver operating characteristic (ROC) curves are plotted. The results show successful identification of vegetation patches in multiple zones from each study area, with area under the ROC curve values between 0.72 and 0.83.

Original languageEnglish
Article number2308
JournalRemote Sensing
Volume11
Issue number19
DOIs
StatePublished - 1 Oct 2019

Keywords

  • Arid regions
  • Classification
  • Gray-level co-occurrence matrix
  • Object-based image analysis
  • Optimization
  • Segmentation
  • Texture
  • Threshold
  • Vegetation

Fingerprint

Dive into the research topics of 'Identifying vegetation in arid regions using object-based image analysis with RGB-only aerial imagery'. Together they form a unique fingerprint.

Cite this