It’s easier than ever to view maps of anywhere you want to go – by car. On foot is another matter. Most cities and towns in the United States don’t have sidewalk maps, and pedestrians are usually left to fend for themselves: Can you walk from your hotel to restaurants on the other side of the interstate? Is there a shortcut from downtown to the sports arena? And how do you get to the bus station anyway?
Now, MIT researchers, along with colleagues from several other universities, have developed an open-source tool that uses aerial imagery and image recognition to create complete maps of sidewalks and driveways. The tool can help planners, policymakers and civilians who want to expand their pedestrian infrastructure.
“In the areas of urban planning and urban policy, this is a huge gap,” says Andries Sivtsuk, associate professor at MIT and co-author of a new paper detailing the tool’s capabilities. “Most American city governments know very little about their sidewalk networks. There’s no data on them. The private sector hasn’t taken the job of mapping them. It just seemed like a really important technology to develop, especially in an open-source field in the way it can be used by places.” other.”
The tool, called TILE2NET, was developed using some US regions as primary data sources, but it can be refined and adapted for use anywhere.
“We thought we needed a method that could be scalable and used in different cities,” says Maryam Hosseini, a postdoctoral researcher in MIT’s City Model Lab in the Department of Urban Studies and Planning (DUSP). the tool.
The paper, “Mapping the Walk: A Scalable Computer Vision for Generewalk Network Datasets from Aerial Imagery,” appears online in the journal Computers, environment and urban systems. The book is Hosseini. Sevtsuk, who is the Charles and Ann Spaulding Associate Professor of Urban Science and Planning at DUSP and head of the City Model Lab at MIT; Fabio Miranda, Assistant Professor of Computer Science at the University of Illinois at Chicago; Roberto M. Cesar, Professor of Computer Science at the University of São Paulo; and Claudio T-Silva, Professor of Computer Science and Engineering at New York University (NYU) Tandon School of Engineering, and Professor of Data Science at NYU’s Center for Data Science.
Significant research for the project was done at New York University while Hosseini was a student there, and he worked with Silva as co-consultant.
There are multiple ways to try mapping sidewalks and other pedestrian paths in cities and towns. Planners can make maps by hand, which are accurate but time consuming; Or they can use methods and make assumptions about the extent of the sidewalks, which lowers the accuracy; Or they could attempt pedestrian tracking, which may be limited in showing the full reach of walking nets.
Instead, the research team used computerized image recognition techniques to build a tool that visually recognizes sidewalks, crosswalks, and crosswalks. To do this, the researchers first used 20,000 aerial photos from Boston, Cambridge, New York City and Washington — places where comprehensive pedestrian maps already exist. By training the image recognition model on such clearly defined objects and using parts of those cities as a starting point, they were able to see how well TILE2NET would work elsewhere in those cities.
In the end, the tool worked well, recognizing 90 percent or more of all sidewalks and crosswalks in Boston and Cambridge, for example. After visual training on those cities, the tool can be applied to other metro areas; People elsewhere can now plug in their aerial photos at TILE2NET, too.
“We wanted to make it easy for cities in different parts of the world to do something like this without having to do the heavy lifting.” [the tool]Hosseini says. Collaboratively we’ll make it better and better, hopefully, as we move forward. “
The need for such a tool is great, says Sivtsuk, whose research focuses on pedestrian and non-motorized movement in cities, and who has developed multiple types of pedestrian mapping tools in his career. He points out that most cities have largely patchy networks of sidewalks and pedestrian walkways. However, it is difficult to scale these networks efficiently without mapping them.
“Imagine we have the same gaps in the networks of cars that pedestrians have in their networks,” says Sivtsuk. “You drive into an intersection and then the road ends. Or you can’t take a right turn because there is no road. That’s what [pedestrians] It confronts us constantly, and we don’t realize how important continuity is [pedestrian] networks. “
In the bigger picture, Sivtsuk notes, continued climate change means cities will have to expand their infrastructure for pedestrians and cyclists, among other measures; Transport remains a significant source of carbon dioxide emissions.
“When cities talk about reducing carbon emissions, there is no other way to make a big impact than to tackle transportation,” says Sivtsuk. “The whole world of urban data for public transport, pedestrians and bicycles is really behind [vehicle data] in quality. Analyzing how cities would function without a car requires this kind of data.”
On the bright side, Sivtsuk suggests, adding pedestrian and bicycle infrastructure “is being done more aggressively than it has been in many decades in the past. In the 20th century it was the other way around, we were taking away sidewalks to make room for vehicular routes. We’re now seeing the opposite trend “To make the best use of pedestrian infrastructure, it’s important that cities have their own network data. Now you can really tell how someone can get to a bus stop.”