Follow this tag to curate your own personalized Activity Stream and email alerts.
To train the model, he identified known locations of tree canopy using lidar data and NAIP imagery over California. Using that as ground truth, the model was trained to classify which pixels contain trees in the corresponding satellite images. The result is a machine-learning model that has learned to identify trees just using four-band high-resolution (~1 meter) satellite or aerial imagery—no lidar required! — Medium
Former New York Times cartographer Tim Wallace describes how his current firm, Santa Fe-based Descartes Labs, has built a machine learning model to identify tree canopy from satellite imagery thus making accurate mapping of trees and urban forests far more accessible to cities worldwide. San... View full entry
Proving that some market somewhere will find a value for anything, a company called Orbital Insight is now tracking "the shadows cast by half-finished Chinese buildings" as a possible indicator for where the country's economy might be headed. — bldgblog.blogspot.com
Google's satellite imaging allows us to virtually tour remote or inaccessible locales the world over, and with recently improved resolutions and initiatives from the Google Cultural Institute, our gaze can go farther and more intimately into places we may never physically visit. Google's interest... View full entry
Two months ago, after much lobbying by the biggest satellite company in North America, DigitalGlobe, the US government relaxed restrictions to allow for commercially available satellite imagery up to 25 cm resolution—twice as detailed as the previous limit of 50 cm [...] The extra sharp images from Worldview-3 will greatly increase the maps' level of detail to the point where it can make out 10-inch objects, which means Google will soon be able to see “manholes and mailboxes” [...] — Motherboard
DigitalGlobe launched the first commercial satellite yesterday. Google, Microsoft, and several US government agencies are customers of DigitalGlobe. Such sharp images would be able to make out human faces, which, coupled with facial recognition software, could start to sound like a sci-fi... View full entry
In this image, vegetation is displayed in red, and flooded areas are black and dark blue. Brighter blue shows sediment-laden water, and gray areas are houses, buildings and roads. The image covers an area of 35.2 by 66.3 miles (56.7 by 106.9 kilometers) and is located at 14.5 degrees north latitude, 100.5 degrees east longitude. — http://www.jpl.nasa.gov
Detached from the content depicted, the full-resolution image itself is too amazing to not circulate... View full entry
