Skip to main content

Wondering why some cities improve more than others? MIT Media Lab knows

In 2013, researchers at the Massachusetts Institute of Technology (MIT) Media Lab created a computer vision system that could read photos of urban areas and gauge how safe people would find them. Now, using the same system, the team is working with colleagues at Harvard University to identify what causes urban areas to succeed or fail. Tested with five American cities, this system quantifies the physical improvement or deterioration of neighborhoods.

According to a paper published in the Proceedings of the National Acadamy of Sciences, researchers used the system to analyze over a million pairs of photos taken seven years apart. These results were then used to test popular theories about the causes of urban revitalization.

Recommended Videos

Contrary to popular belief, raw income levels and housing prices do not predict change in a neighborhood. Instead, the study found it had more to do with other factors. The researchers found that the density of highly educated residents, proximity to central business districts or other physically attractive neighborhoods, and the initial safety score assigned by the computer vision system all lead to improvements in the physical condition.

Courtesy of the MIT researchers. Image used with permission by copyright holder

Another theory that was tested is that neighborhoods are mostly revitalized when their buildings have deteriorated enough for replacement. The researchers at MIT and Harvard found little correlation between the age of a neighborhood’s buildings and the degree of physical improvement.

In order to properly train the machine-learning system used, human volunteers had to rate the relative safety of urban areas shown in hundreds of thousands of image pairs. Then, for the new study, the same system compared images associated with the same geographic coordinates seven years apart in Google’s Street View. However, images had to be preprocessed to ensure the system’s decisions were reliable. For example. green spaces are one of the ways people assess safety. If one image was captured in summer, and the other in winter, the machine-learning system might incorrectly think the neighborhood has lost green space.

To test the system’s outcome, researchers then presented 15,000 random pairs of images from the data set to human reviewers. When asked to assess the relative safety of the areas shown, the reviewers matched the computer 72 percent of the time. Additionally, in the remaining percentage, most of the disagreements were of pairs with little change in safety scores.

By better understanding what caused these areas to improve or decline, other urban areas can learn and adapt to provide safer and more practical solutions for its residents. This is another way that cities can become smarter beyond adding sensors.

Garrett Hulfish
Garrett is the kind of guy who tells you about all the tech you haven't heard of yet. He also knows too much about other…
The Yale Assure Lock 2 has only grown better with age
the yale assure lock 2 has only grown better with age plus

The Yale Assure Lock 2 has long held a spot on our roundup of the best smart locks. Offering a sleek design, robust companion app, and a multitude of customization options, it's a premium choice that's an easy recommendation for most shoppers. And while some smart locks begin to show their age over the years, the Yale Assure Lock 2 has only grown more enticing.

Part of this is due to its impressive durability — the one installed on my front door has seen more than a few Colorado storms yet remains in pristine condition — but the other reason is Yale's commitment to expanding the number of models in the Assure Lock 2 lineup. I recently had a chance to test out a second, newer version of the Assure Lock 2 that works with Apple Home Keys, and it cemented my belief that it's one of the best smart locks money can buy.

Read more
Hue gives users eight new free spring-focused themes
A TV with ambient backlighting from Philips Hue.

The latest Philip Hue app update, version 5.39, is now available from download from both the iOS and Android stores. This update introduces brand-new scenes, each of which has a distinctive springtime-theme. All of the themes are available now in the Hue scene gallery, and you should be able to find them after you update your app.

The eight scenes are Nature's colors, Precious, Narcissa, Baby's breath, Crocus, Blossom, Spring lake, and Spring blossom. Various shades of pink, yellow, and green dominate the scenes, but the most impressive of all is the Nature's colors option.

Read more
This Arlo security camera is 50% off today — down to $50
The Arlo Essential 2nd Gen security camera, installed outdoors.

Protect your entire home with the Arlo Essential 2nd Gen security camera -- you'll be able to afford multiples of this smart home device while Arlo's 50% discount is active. From the 2K model's original price of $100, you'll only have to pay $50, so covering every corner of your house will be easier on the wallet. You'll have to complete your purchases as soon as possible though, as we're not sure how much time is remaining for you to pocket the savings of $50 each for every unit of this security camera.

Why you should buy the Arlo Essential 2nd Gen security camera

Read more