[{"data":1,"prerenderedAt":186},["ShallowReactive",2],{"project-16052214":3},{"id":4,"name":5,"line":6,"line_source":7,"title":8,"url":9,"domain":10,"maker":11,"posted_at":12,"year":13,"points":14,"comments":15,"rank_in_year":16,"shown_in_year":17,"top":18,"tier":19,"category":20,"subcategory":21,"format":22,"keywords":23,"reception":29,"sentiment":30,"stance_mix":31,"scored_comments":35,"aspects":36,"strip":39,"post_text":40,"what":41,"said":67,"maker_in_thread":117,"shape":123,"grid":126,"attempts":147,"same_week":148,"maker_shows":136,"maker_hidden":178,"reader_version":179,"card":180},"16052214","images-to-osm","Mask R-CNN Neural Network for Mapping Sport Fields in OpenStreetMap","title","Show HN: Mask R-CNN Neural Network for Mapping Sport Fields in OpenStreetMap","https:\u002F\u002Fgithub.com\u002Fjremillard\u002Fimages-to-osm","github.com","jasonremillard",1514905727,2018,94,10,465,2155,22,"notable","ai","computer vision mapping","other",[24,25,26,27,28],"mask r-cnn","openstreetmap","sports fields","aerial imagery","neural network","curious",0.267,{"positive":32,"neutral":33,"mixed":34,"critical":34},2,3,0,5,{"idea":37,"execution":38},{"positive":32,"critical":34},{"positive":34,"critical":34},[35,34,34,34,34,33,34,33,35,33],null,{"problem":42,"audience":48,"pricing":40,"motivation":40,"time_to_build":40,"stack":60,"openness":65,"stage":66,"team_size":65},{"value":43,"source":44,"evidence":45},"Mapping sport fields in OpenStreetMap from aerial imagery","maker",[46],{"id":47},"post",{"value":49,"source":50,"evidence":51},"OpenStreetMap mappers","inferred",[52,56],{"id":53,"by":54,"text":55},"16053137","riordan","This is awesome and exactly the kind of thing that can give the OSM Armchair Mappers some very accurate superpowers. It'd be great to see this fed into the OSM Tasking Manager…",{"id":57,"by":58,"text":59},"16053183","maxerickson","If I understand correctly the creator has already validated the output for much of the Northeast. (They've proposed an import:…",[61],{"value":62,"source":44,"evidence":63},"Mask R-CNN",[64],{"id":47},"unknown","launched",{"praise":68,"objections":78,"requests":92,"questions":101,"alternatives":109},[69],{"value":70,"source":71,"evidence":72},"Impressive and useful for OSM mappers","commenter",[73,77],{"id":74,"by":75,"text":76},"16052800","francisofascii","This is impressive. I wonder if a similar technique could be used to identify parking lots. The U.S. seems to have an over abundance of parking lots, so it would be cool to back…",{"id":53,"by":54,"text":55},[79,85],{"value":80,"source":44,"evidence":81},"Parking lot import would be too large for OSM community",[82],{"id":83,"by":11,"text":84},"16053297","Thanks! It would probably work well for parking lots, but there are a horrifying number of them. I don’t think the OSM community would tolerate such a large import.",{"value":86,"source":71,"evidence":87},"Basketball courts not visible in aerial imagery",[88],{"id":89,"by":90,"text":91},"16053661","Mediterraneo10","I mapped quite a bit of Morocco while traveling through there recently. Interestingly, I find that a lot of sports fields in villages are for both football and basketball, but…",[93,97],{"value":94,"source":71,"evidence":95},"Apply the technique to parking lots",[96],{"id":74,"by":75,"text":76},{"value":98,"source":71,"evidence":99},"Feed output into MapRoulette or Tasking Manager for validation",[100],{"id":53,"by":54,"text":55},[102],{"value":103,"source":71,"evidence":104},"What issues were encountered implementing Mask R-CNN and training",[105],{"id":106,"by":107,"text":108},"16053475","edshiro","Very interesting! I recently finished reading the paper on Mask R-CNN and find it's a very neat addition to the R-CNN family. What are some of the issues that you encountered…",[110],{"value":111,"source":71,"evidence":112},"DeepOSM",[113],{"id":114,"by":115,"text":116},"16053008","toomuchtodo","https:\u002F\u002Fgithub.com\u002Ftrailbehind\u002FDeepOSM https:\u002F\u002Fnews.ycombinator.com\u002Fitem?id=11808639",{"comments":32,"answered":34,"key":118},[119,120],{"id":83,"text":84},{"id":121,"text":122},"16054614","This is just for the US North East. Football and basketballs fields are never shared because basketball fields are always paved.",{"commenters":124,"max_depth":33,"maker_replies":32,"first_comment_mins":125,"lifespan_hours":35},8,75,[127,129,131,134,137,140,141,142,144,145],[74,34,35,128,75,34],"project\u002Fpositive\u002Fidea",[114,34,34,130,115,34],"other\u002Fneutral\u002Fnone",[132,34,34,133,58,34],"16053198","commenter\u002Fneutral\u002Fnone",[83,34,34,135,11,136],"project\u002Fneutral\u002Fidea",1,[138,34,34,133,139,34],"16055101","rmc",[89,136,33,135,90,34],[121,136,34,133,11,136],[106,32,33,143,107,34],"maker\u002Fneutral\u002Fexecution",[53,33,35,128,54,34],[57,33,33,146,58,34],"project\u002Fneutral\u002Fnone",[],[149,154,159,164,169,174],{"id":150,"name":151,"points":152,"category":153},"16052558","Sapper.js",410,"languages",{"id":155,"name":156,"points":157,"category":158},"16049026","mind-circus.org",341,"games",{"id":160,"name":161,"points":162,"category":163},"16064770","HNCute",208,"productivity",{"id":165,"name":166,"points":167,"category":168},"16021874","Themer",135,"dev_tools",{"id":170,"name":171,"points":172,"category":173},"16042888","Roulette Pizza",127,"consumer_social",{"id":175,"name":176,"points":177,"category":158},"16032889","Gameboy",82,false,"v2",{"id":181,"name":5,"line":6,"ai":178,"cat":20,"year":13,"points":14,"comments":15,"rec":29,"s":182,"top":18,"kw":183,"maker":11,"domain":10,"tier":19,"attempts":34,"strip":184,"url":9,"mix":185,"praise":70,"objection":80,"sub":21},16052214,0.27,[24,25,26,27,28],"5000030353",[32,33,34,34],1794036562127]