Visual search tool for satellite imagery

Posted to Apps  |  Tags: ,  |  Nathan Yau

Terrapattern is a fun prototype that lets you search satellite imagery simply by clicking on a map. For example, you can click on a tennis court, and through machine learning, the application looks for similar areas.

Terrapattern uses a deep convolutional neural network (DCNN), based on the ResNet (“Residual Network”) architecture developed by Kaiming He et al. We trained a 34-layer DCNN using hundreds of thousands of satellite images labeled in OpenStreetMap, teaching the neural network to predict the category of a place from a satellite photo. In the process, our network learned which high-level visual features (and combinations of those features) are important for the classification of satellite imagery.

Give it a try.

Favorites

Think Like a Statistician – Without the Math

I call myself a statistician, because, well, I’m a statistics graduate student. However, the most important things I’ve learned are less formal, but have proven extremely useful when working/playing with data.

Who is Older and Younger than You

Here’s a chart to show you how long you have until you start to feel your age.

Shifting Incomes for American Jobs

For various occupations, the difference between the person who makes the most and the one who makes the least can be significant.

Years You Have Left to Live, Probably

The individual data points of life are much less predictable than the average. Here’s a simulation that shows you how much time is left on the clock.