MSGID: 1:317/3 6413ecf9   
   PID: hpt/lnx 1.9.0-cur 2019-01-08   
   TID: hpt/lnx 1.9.0-cur 2019-01-08   
    Where the sidewalk ends    
      
     Date:   
         March 16, 2023   
     Source:   
         Massachusetts Institute of Technology   
     Summary:   
         Most cities don't map their own pedestrian networks. Now,   
         researchers have built the first open-source tool to let planners   
         do just that.   
      
         Researchers have built TILE2NET, an open-source tool that uses   
         aerial imagery and image-recognition to create complete maps of   
         sidewalks and crosswalks. The tool can help planners, policymakers,   
         and urbanists who want to expand pedestrian infrastructure.   
      
      
         Facebook Twitter Pinterest LinkedIN Email   
   FULL STORY   
   ==========================================================================   
   It's easier than ever to view maps of any place you'd like to go --   
   by car, that is. By foot is another matter. Most cities and towns in   
   the U.S. do not have sidewalk maps, and pedestrians are usually left to   
   fend for themselves: Can you walk from your hotel to the restaurants on   
   the other side of the highway? Is there a shortcut from downtown to the   
   sports arena? And how do you get to that bus stop, anyway?   
      
   ==========================================================================   
   Now MIT researchers, along with colleagues from multiple other   
   universities, have developed an open-source tool that uses aerial   
   imagery and image- recognition to create complete maps of sidewalks and   
   crosswalks. The tool can help planners, policymakers, and urbanists who   
   want to expand pedestrian infrastructure.   
      
   "In the urban planning and urban policy fields, this is a huge gap," says   
   Andres Sevtsuk, an associate professor at MIT and a co-author of a new   
   paper detailing the tool's capabilities. "Most U.S. city governments know   
   very little about their sidewalk networks. There is no data on it. The   
   private sector hasn't taken on the task of mapping it. It seemed like   
   a really important technology to develop, especially in an open-source   
   way that can be used by other places."  The tool, called TILE2NET,   
   has been developed using a few U.S. areas as initial sources of data,   
   but it can be refined and adapted for use anywhere.   
      
   "We thought we needed a method that can be scalable and used in different   
   cities," says Maryam Hosseini, a postdoc in MIT's City Form Lab in the   
   Department of Urban Studies and Planning (DUSP), whose research has   
   focused extensively on the development of the tool.   
      
   The paper, "Mapping the Walk: A Scalable Computer Vision Approach for   
   Generating Sidewalk Network Datasets from Aerial Imagery," appears   
   online in the journal Computers, Environment and Urban Systems. The   
   authors are Hosseini; Sevtsuk, who is the Charles and Ann Spaulding   
   Career Development Associate Professor of Urban Science and Planning   
   in DUSP and head of MIT's City Form Lab; Fabio Miranda, an assistant   
   professor of computer science at the University of Illinois at Chicago;   
   Roberto M. Cesar, a professor of computer science at the University of   
   Sao Paulo; and Claudio T. Silva, Institute Professor of Computer Science   
   and Engineering at New York University (NYU) Tandon School of Engineering,   
   and professor of data science at the NYU Center for Data Science.   
      
   Significant research for the project was conducted at NYU when Hosseini   
   was a student there, working with Silva as a co-advisor.   
      
   There are multiple ways to attempt to map sidewalks and other pedestrian   
   pathways in cities and towns. Planners could make maps manually,   
   which is accurate but time-consuming; or they could use roads and make   
   assumptions about the extent of sidewalks, which would reduce accuracy;   
   or they could try tracking pedestrians, which probably would be limited   
   in showing the full reach of walking networks.   
      
   Instead, the research team used computerized image-recognition techniques   
   to build a tool that will visually recognize sidewalks, crosswalks,   
   and footpaths.   
      
   To do that, the researchers first used 20,000 aerial images from Boston,   
   Cambridge, New York City, and Washington -- places where comprehensive   
   pedestrian maps already existed. By training the image-recognition model   
   on such clearly defined objects and using portions of those cities as   
   a starting point, they were able to see how well TILE2NET would work   
   elsewhere in those cities.   
      
   Ultimately the tool worked well, recognizing 90 percent or more of all   
   sidewalks and crosswalks in Boston and Cambridge, for instance. Having   
   been trained visually on those cities, the tool can be applied to other   
   metro areas; people elsewhere can now plug their aerial imagery into   
   TILE2NET as well.   
      
   "We wanted to make it easier for cities in different parts of the world to   
   do such a thing without needing to do the heavy lifting of training [the   
   tool]," says Hosseini. "Collaboratively we will make it better and better,   
   hopefully, as we go along."  The need for such a tool is vast, emphasizes   
   Sevtsuk, whose research centers on pedestrian and nonmotorized movement   
   in cities, and who has developed multiple kinds of pedestrian-mapping   
   tools in his career. Most cities have wildly incomplete networks of   
   sidewalks and paths for pedestrians, he notes. And yet it is hard to   
   expand those networks efficiently without mapping them.   
      
   "Imagine that we had the same gaps in car networks that pedestrians have   
   in their networks," Sevtsuk says. "You would drive to an intersection   
   and then the road just ends. Or you can't take a right turn since there   
   is no road. That's what [pedestrians] are constantly up against, and we   
   don't realize how important continuity is for [pedestrian] networks."   
   In the still larger picture, Sevtsuk observes, the continuation of climate   
   change means that cities will have to expand their infrastructure for   
   pedestrians and cyclists, among other measures; transportation remains   
   a huge source of carbon dioxide emissions.   
      
   "When cities talk about cutting carbon emissions, there's no other way   
   to make a big dent than to address transportation," Sevtsuk says. "The   
   whole world of urban data for public transit and pedestrians and bicycles   
   is really far behind [vehicle data] in quality. Analyzing how cities   
   can be operational without a car requires this kind of data."  On the   
   bright side, Sevtsuk suggests, adding pedestrian and bike infrastructure   
   "is being done more aggressively than in many decades in the past. In the   
   20th century, it was the other way around, we would take away sidewalks to   
   make space for vehicular roads. We're now seeing the opposite trend. To   
   make best use of pedestrian infrastructure, it's important that cities   
   have the network data about it. Now you can truly tell how somebody can   
   get to a bus stop."   
       * RELATED_TOPICS   
             o Earth_&_Climate   
                   # Geography # Environmental_Science # Environmental_Policy   
                   # Air_Quality   
             o Science_&_Society   
                   # Transportation_Issues # Surveillance #   
                   Travel_and_Recreation # Urbanization   
       * RELATED_TERMS   
             o Automobile_safety o Artificial_reef o   
             Urban_planning o Topographic_map o Irrigation o   
             Traffic_engineering_(transportation) o Aerial_photography   
             o Vehicle_propulsion   
      
   ==========================================================================   
   Story Source: Materials provided by   
   Massachusetts_Institute_of_Technology. Original written by Peter   
   Dizikes. Note: Content may be edited for style and length.   
      
      
   ==========================================================================   
   Journal Reference:   
      1. Maryam Hosseini, Andres Sevtsuk, Fabio Miranda, Roberto M. Cesar,   
      Claudio   
         T. Silva. Mapping the walk: A scalable computer vision approach for   
         generating sidewalk network datasets from aerial imagery. Computers,   
         Environment and Urban Systems, 2023; 101: 101950 DOI: 10.1016/   
         j.compenvurbsys.2023.101950   
   ==========================================================================   
      
   Link to news story:   
   https://www.sciencedaily.com/releases/2023/03/230316140925.htm   
      
   --- up 1 year, 2 weeks, 3 days, 10 hours, 50 minutes   
    * Origin: -=> Castle Rock BBS <=- Now Husky HPT Powered! (1:317/3)   
   SEEN-BY: 15/0 106/201 114/705 123/120 153/7715 226/30 227/114 229/110   
   SEEN-BY: 229/111 112 113 307 317 400 426 428 470 664 700 292/854 298/25   
   SEEN-BY: 305/3 317/3 320/219 396/45   
   PATH: 317/3 229/426