OpenStreetCam’s mission is to help you improve OSM with street-view imagery. Photos taken with regular smartphones seem to be good enough for capturing map features like traffic signs, lanes or crosswalks. However, browsing the 120 million+ photos in OSC to find relevant things to map will take a while. The human factor is fundamental to OSM’s culture and we don’t see that changing, but we want to make editing street related attributes more efficient with automation.
We’re happy to announce a beta release of the traffic signs recognition on OpenStreetCam photos, made possible with machine learning. We processed a few million photos and detected around 500.000 traffic signs so far, currently available for tracks in several areas in United States and Canada. We’re working on extending the training sets and optimize the processing so that the area’s soon expanded.
What’s new from a user perspective: the track page on openstreetcam.org will now show detected traffic signs when available:
There’s a preview list of all detections in the track, detection overlays on photos and, of course, filters. Filters might now get a rep as something really exciting, but we’re excited about one of ours: the OSM status. Here’s why: after detecting a sign we compare it to the corresponding OSM feature and check if they’re consistent. Based on that, filtering is available.
For a practical example, let’s take speed limits: Instead of manually cross checking every detection with the maxspeed tag in OSM, one can only review detections where presumably maxspeed is not set or the value’s different in OSM. Just tick the Need review in OSM box.
Hereareafew more examples of trips that have already been processed with our sign detections.
We’re busy working on a few things:
Scale the training sets and pipeline to extend the supported areas.
Traffic signs integration in the JOSM plugin.
Tagging new traffic signs support in the webpage.
If you like what we do and want to help:
First and foremost, you can use detections to improve OSM. If you’re seeing detections on tracks check them out, see what needs reviewing in OSM and edit. You can open iD or JOSM to photo’s location straight from the webpage.
Help us improve the traffic signs recognition. There’s a chance you will find some bad detections. You can review them and flag whether they’re good or bad, see the two buttons above the photo. We’re adding those reviews to training sets to improve recognitions, so please play nice.
Help us add these detections to the iD editor as well.
Tip: you can navigate between detections with Ctrl/Cmd + right/left arrows and confirm/invalidate with Ctrl/Cmd + up/down arrows. Goes pretty fast.
From 2D images we can extract a limited range of information like width, height and color. These can be useful to determine the regions of interest in our images: street signs, lanes, or even roads.
However, for a more accurate detection, the depth perception
is crucial. Here comes the 3D reconstruction into play. Extracting a 3rd dimension, the depth, we can determine how far from the
camera the regions of interest are and consequently, their shape. This way we can distinguish the road from the obstacles (cars, pedestrians, curbstones) simply because we know that the road has an increasing distance from the camera while the objects have a constant distance (fig. 1).
Late last week, we released new versions of the OpenStreetCam apps and the web site. While we continue to make the platform faster and more reliable, we also like to keep adding interesting and fun features from time to time! This new release introduces points and levels. Every time you drive, you earn points. Earn enough points and you level up.
We went back in and calculated points for all your existing trips, so why not head to the newly designed leaderboard and see how you stack up against your fellow cammers? You can also see the leaderboard in the app:
We also enabled leaderboards by country on top of the daily, weekly and monthly rankings.
Your profile screen in the app and on the site will show you exactly how many points you have, how many you earned per trip, and what your current level is.
More points for unexplored roads
So as you are driving around, you will automatically earn points for every picture recorded. But not all pictures earn you equal points! The less explored a road is, the more points you get — up to 10x the points for roads that have no coverage at all yet!
(This made it possible for me to gain 11k points on a 50 minute drive last week: most of the roads had no coverage yet, so I was getting 10x points for most of the way. )
You can see which roads are less covered, or not covered at all yet, in the app. Just look for the roads with lighter or no purple OSC overlay:
We calculate the quality of coverage by the number of trips that cover the way as well as the age of the existing trips. This way we encourage each other to always have the most recent imagery available for OpenStreetMap.
We hope you enjoy the new features! Please let us know what you think by writing us at firstname.lastname@example.org.
This summer, we launched OpenStreetView and received great response both from the OpenStreetMap community and the press.
After only 4 months, you have already contributed almost 12 million images covering 322 thousand kilometers. We have released open source apps, upload and OpenStreetMap editing tools, and are working on many improvements aimed at improving OSM faster than is possible now.
As part of our fast growing public profile, we have also attracted the attention of Google Inc, who holds the ‘Street view’ trademark. They are really interested in OpenStreetView but also expressed concerns about the name creating confusion. Obviously to us this confusion does not exist, but after considering the pros and cons carefully, we decided to change the name.
From now on, OpenStreetView will be known as OpenStreetCam.
Aside from the name, nothing changes. In fact, we will be launching some pretty cool new features and improvements very soon, so please stay tuned for that. If you have not tried OpenStreetCam yet, why not download the free and open apps for Android or iOS, explore the coverage or start editing with OSC in OpenStreetMap?