While 8-band multispectral (MUL-PanSharpen) and grayscale (PAN) images are included, in this post we will focus on 3-band imagery (RGB-PanSharpen). The high-resolution 30 cm resolution DigitalGlobe WorldView3 imagery in the SpaceNet Dataset is delivered in 16-bit format. Python code is included in the APLS github repository for the interested reader. We will discuss the variance in road structure in subsequent posts. We demonstrate methods for converting 16-bit imagery to standard RGB formats, and for extracting raster masks from the SpaceNet GeoJSON labels. In this post, we focus on issues #1 and #2. Since the goal of the challenge is to reproduce these centerline labels, the variance in road structure presents a challenge. The SpaceNet road network was created in such a fashion that only centerlines are labeled, regardless of roadway size. All roads are not created equal, as lane widths, number of lanes, and road surface all vary widely between differing geographic locales.Vector labels are rarely compatible with machine learning architectures, particularly in the computer vision realm.(We recommend QGIS to view raw SpaceNet data.) Few programs are designed to display 16-bit imagery, necessitating conversion.The SpaceNet imagery is distributed as 16-bit imagery, and the road network is distributed as a line-string vector GeoJSON format, which poses a few challenges: Remote sensing data is often formatted in a bespoke manner, which greatly complicates this process. One of the primary challenges of working with and eventually classifying remote sensing datasets is creating training data for ingestion into machine learning workflows. In previous posts we detailed the evaluation metric for this challenge, and more recently we described the SpaceNet Roads Dataset in this post we detail the steps to get started working with the roads dataset, with attendant code hosted on the APLS github page. Such automated processes may help improve a vast array of problems, from the mundane (traffic) to the extreme (mass evacuation). The SpaceNet Road Detection and Routing Challenge aims to automatically extract road networks directly from high-resolution satellite imagery.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |