Fractures in UAV Imagery for Segmentation

Citation Author(s):
Vitor Lamy Mesiano
Savastano
Petrobras
Davi Bortolotti
Batista
Submitted by:
Davi Batista
Last updated:
Mon, 10/25/2021 - 09:46
DOI:
10.21227/5939-y446
Data Format:
License:
0
0 ratings - Please login to submit your rating.

Abstract 

The dataset contains UAV imagery and fracture interpretation of rock outcrops acquired in Praia das Conchas, Cabo Frio, Rio de Janeiro, Brazil. Along with georeferenced .geotiff images, the dataset contains filtered 500 x 500 .png tiles containing only scenes with fracture data, along with .png binary masks for semantic segmentation and original georeferenced shapefile annotations. This data can be useful for segmentation and extraction of geological structures from UAV imagery, for evaluating computer vision methodologies or machine learning techniques.

Instructions: 

The geotiff folder contains all georeferenced 500x500 tile images with all data, including all-black images, scenes of sea and vegetation. The images folder contain 500x500 .PNG images with rock outcrops containing geological structures. In the masks folder, there are .PNG binary masks for the previous images, with pixels values representing two classe: 0 for background and 1 for fractures. The shapefile folder contains the same data as mentioned masks, though as georeferenced and vectorized annotation originally interpreted by the geoscientist, to be used in GIS software.

Comments

Soy profesor de Visión por Computador, por lo que este DATASET me será de mucha utilidad para mis practicas de clase

Submitted by ANTONIA MACEDO CRUZ on Thu, 11/04/2021 - 15:43

do some work on UAV.

Submitted by CHAO LI on Tue, 11/09/2021 - 01:44