Five Years of Mapillary—From the First Image to a Global Platform
This week marks five years since we started this little “project” of ours. It seemed controversial at first but now, five years later, it’s become a completely normal and sane thing. Time for a short reflection on this half-decade.
Improving the Viewing Experience: Image Undistortion in MapillaryJS
Radial distortion is a common problem when the 3D world is represented in 2D images. With the latest MapillaryJS release, we are now undistorting every image. This leads to a better 3D representation and improves the viewing experience of Mapillary images.
Analyzing Parking Signs at Scale: How Mapillary is Working with Amazon Rekognition to Help US Cities End Their Parking Troubles
Managing parking infrastructure is a billion-dollar problem for cities all across the US. There has been no easy way for cities and Departments of Transportation to access parking sign data, resulting in poor decisions around parking infrastructure and planning. Today, Mapillary and Amazon Rekognition are introducing a scalable way to help US cities get a handle of their parking infrastructure.
Announcing the Winners of the Joint COCO and Mapillary Recognition Challenge Workshop for ECCV 2018
Earlier this year, COCO and Mapillary invited computer vision researchers to participate in a workshop co-located with this year’s European Conference on Computer Vision. Today we’re announcing the winners.
Winning the ECCV Semantic Segmentation Challenge for Autonomous Navigation in Unstructured Environments
Mapillary just scored another success in computer vision benchmarking. This wouldn't be possible without our community: by contributing more than 350 million images from all over the world, they've created a dataset that helps build robust algorithms for making sense of any street scene that a self-driving car may encounter.
Celebrating Five Million Kilometers of Mapillary Coverage
At Mapillary, we believe that the best way to visually represent our planet is through people and organizations working together. As of today, our community has collectively mapped five million kilometers!
Extending the Mapillary Vistas Dataset for Perfecting Street Scene Segmentation Models
The newly released extension of the Mapillary Vistas Dataset provides over 60 new object classes and even more granularity, including traffic light states. With a total of more than 150 classes, it remains the most diverse publicly available training dataset covering street scenes from around the world.
Welcoming Till Quack to the Mapillary Team
This week we're happy to welcome Till Quack as Mapillary's first VP of Product
Winning the CVPR Semantic Segmentation Challenge: How Mapillary Makes Computer Vision Algorithms Effective and Robust
Mapillary has won the Semantic Segmentation Challenge as part of the 2018 CVPR Robust Vision Workshop. Here's how we did it.
Launching Mapillary for Organizations: Work Together with the Freshest Map Data
Mapillary now supports organizations to easily create and share street-level imagery and automatically extracted data to keep maps and geospatial datasets up to date.
Simpler Command Line Tools for Everyone
The updated Mapillary command line tools make uploading and preprocessing your imagery easier—and not just for programmers.
More Flexibility to Compare Images with MapillaryJS
After the recent update of MapillaryJS, you can now compare any pair of images, regular as well as panoramas. It also features a simpler design to make MapillaryJS integrate smoothly in various applications.
HERE and Mapillary: Linking Two Global Communities
Our partnership with HERE goes global to reinforce the power of community mapping.
Accurate Privacy Blurring at Scale
We have developed an accurate and fast algorithm for privacy blurring on street-level images. The new model, based on semantic segmentation, detects 99.9% of identifiable faces and license plates and is optimized for large-scale processing.
Scaling up with a $15M Investment
BMW i Ventures, Samsung Catalyst Fund, and NavInfo join our existing investors to support growing the world’s largest collaborative street-level imagery platform for extracting map data using computer vision.
MapillaryJS Now Enables Fast Sequence Navigation
With the recent update of MapillaryJS, we have added controls for fast sequence navigation and better sequence overview. Now you can easily navigate to the beginning, end, or any other position of interest in a sequence.
Mapillary for ArcGIS Pro Enters Public Beta
Mapillary for ArcGIS Pro is now available as a Public Beta with considerable performance improvements compared to the previous version. We invite you to join directly from the Mapillary for ArcGIS page.
Mapillary GIS Meetup—Malmö, 6 Feb
Join us for an evening of GIS talk and demos to learn how street-level imagery can help automatize road and street inventories.
New Benchmarks for Semantic Segmentation Models
Mapillary Research ranks no. 1 for semantic segmentation of street scenes on the Cityscapes and Mapillary Vistas leaderboards.
2017 Year in Review
With another year coming to a close, we’d like to highlight some of its best Mapillary moments.
Boosting Semantic Segmentation Performance with NVIDIA and Amazon
The new NVIDIA Tesla V100 graphics processing units and TensorRT 3.0 library together with Amazon EC2 P3 instances make Mapillary’s semantic segmentation models 27 times faster while using 81% less memory.
Advancing Map Data Extraction with Line Features
We’ve taken a big step forward in extracting map data from images. 19 of the object classes we’re detecting in images via semantic segmentation, all representing line-shaped real-world objects, are now available as line features located on the map.
Added Controls for Sequence Playback: Change Speed and Direction
The latest MapillaryJS release adds support for changing the speed and direction when playing a sequence.
#CompletetheMap—Launching the Global Challenge
After a number a successful local challenges, Complete the Map is going global. To participate in the largest Mapillary challenge, register a location you'd like to contribute to. Kick-off on 11st December!
Introducing the Mapillary Tasker: Collaborate with Anyone on Mapillary
To reinforce the power of collaboration, we made it easier for contributors to work together on clearly defined tasks focused on street-level images. The Mapillary Tasker will let you invite people to help complete capture, map editing, or data verification tasks in your area.
Anyone Can Teach the Computer: The Mapillary Verifier Tool
Today we release a feature for verifying Mapillary’s object detections. The Verifier tool gives anyone the chance to help improve data accuracy while competing in a fun game.
A New Way to Organize Imagery: Introducing Tagging
The tagging feature in Mapillary will let you organize imagery by adding tags to whole images or specific objects in images. As Mapillary in general, this function is also collaborative, so anyone is able to search for tags added by everyone else.
Celebrating 200 Million Images
Thanks to all of you, we've added another hundred million images in less than a year!
Mapillary Partners with Trimble: High-Precision Street-Level Imagery at Your Fingertips
Trimble releases support for Mapillary Exporter to facilitate getting map data from high-quality, high-precision street-level imagery.
Microsoft Donates Imagery to Help with Disaster Recovery in Texas and Florida
To support disaster recovery efforts related to Hurricanes Harvey and Irma, Microsoft is sharing 360° street-level imagery of the affected areas in Texas and Florida to the Mapillary platform.
Visualizing AI Detections for Improved Map Editing
Our new AI detections feature lets you quickly find images where objects have been automatically detected, making it easier to use Mapillary imagery to edit maps and geospatial datasets.
Introducing Mapillary for ArcGIS Pro
Mapillary imagery is now available in ArcGIS Pro. The Beta release of Mapillary for ArcGIS Pro will let you use street-level imagery for visual reference, feature editing, and comparison over time.
Get on the Bus! With OpenStreetMap and Mapillary
Let’s work together to improve the information on bus routes across the US. Join us for the OpenStreetMap US Summer Bus Mapathon!
Street-level Storytelling: Introducing the Mapillary Photostories Tool
Tell your stories in more than words and images! The Mapillary Photostories tool lets you take viewers to the places that matter to you and tell the tales around them.
#CompletetheMap Challenges—Targeted Collection of Fresh Imagery
We're running challenges around the world to create fresh coverage in selected locations and explore the potential for targeted image collection. The goal is to complete the map.
Collaborating to Map the Planet: Extending Our Partnership with HERE
Following a successful pilot, we’re continuing our partnership with HERE, the global map data and location services provider. We’re working with HERE and their Map Creator community to deliver better maps to millions of people—and add millions of images to the Mapillary database along the way.
Mapillary API: Hello to v3 and Goodbye to v2
Here is what you need to know about migrating to Mapillary API v3 as v2 retires.
Pushing the Limits of Scene Understanding: LSUN’17 Workshop and Semantic Image Segmentation Challenges
We invite researchers to participate in a challenge for large-scale scene understanding models as part of the LSUN workshop at this year’s Computer Vision and Pattern Recognition (CVPR) conference.
New iOS Camera Features and Updated User Interface
Mapillary for iOS now lets you capture with the phone's internal camera together with external cameras, and use each camera in any of the three capturing modes (distance- or time-based automatic, or manual mode). In addition, we've added support for more GoPro cameras, and freshened up the camera screen to make it really easy to use the new functions.
Making Digital Mapping Technologies Smarter with an Austrian Research Grant
We are glad to acknowledge that Mapillary Research has received funding from the Austrian Research Promotion Agency (FFG) for building next-generation maps. We have added more computational power and two expert researchers to our Research team to ramp up developing the computer vision algorithms that generate digital map data from Mapillary imagery.
Complete the Map Challenge - Berlin
Over the next three weeks, we’re bringing together the Mapillary community in Berlin in a challenge to photo map zones of Mitte and Kreuzberg. Anyone in Berlin or passing through during this time is welcome to join the
Releasing the World’s Largest Street-level Imagery Dataset for Teaching Machines to See
Mapillary Vistas, the world’s largest and most diverse publicly available, pixel-accurately and instance-specifically annotated street-level imagery dataset, will empower autonomous mobility and transport at the global scale.
Save and Share Your Filter Setups with URLs
You can easily save and share the filters you have set up in the Mapillary viewer, since we now store filters in the URL.
Edit Map Objects with MapillaryJS
The latest MapillaryJS release adds support for map object editing in the viewer.
More Mapillary Partners
We are happy to add three more organizations to our list of partners to help make the most out of street-level imagery.
Find Your Local Vendors on Eniro with Mapillary Street-Level Photos
We're proud to announce that Eniro has integrated Mapillary into their search services, enabling their visitors to find the location of businesses and individuals via street-level images that have been provided by local people.
Street-level Imagery for Appraisals: Partnering with Bruce Harris
We are glad to announce our partnership with Bruce Harris & Associates to make street-level imagery accessible and affordable in appraisal services.
Towards Global Traffic Sign Recognition
We are taking a big step towards recognizing traffic signs all over the world by adding support for more than 500 traffic signs globally, together with an appearance-based taxonomy for traffic signs. This is the beginning of our journey of recognizing every road sign in the world, no matter where it is.
Mapillary for ArcGIS Online v2 Now Available
Improved performance, design and availability—the new Mapillary for ArcGIS Online app is now on the ArcGIS Marketplace.
Are You up for the Challenge? Win an LG 360° Cam
It is time for a Mapillary challenge! Take the chance to win an LG 360° camera by sharing your favourite Mapillary photo sequence with the hashtag #MapillaryExplore.
More Power to Manage Mapillary Resources: Introducing API v3
The API is an important way to make Mapillary useful to developers. Today we are glad to announce the release of Mapillary API v3 that is more simple, powerful, and flexible to use.
Meet Mapillary Ambassadors for 2017
We're happy to introduce you the latest team of Mapillary Ambassadors—15 awesome people that work with our community.
Full Resolution Zoom: View Exactly What You Captured
Our new full resolution zoom feature lets you view every photo in its finest detail and make the most out of high-resolution imagery.
Improved Notifications: Stay on Top of Your Mapillary Activities
You may have noticed that a few things have changed in the Mapillary app. We made it easier for you to get an overview of your Mapillary activities while also providing a deeper understanding of what is going on with each activity.
2016 Year in Review
As we are approaching the end of 2016 I wanted to share some details and stats with you all. 2016 was a great Mapillary year. Here are some of the highlights.
Mapillary Raster Tiles Are Back
Next to vector tiles, we're glad to bring back Mapillary raster tiles to enable better mapping.
Embed Mapillary Street-level Photos Anywhere
Today we are excited to introduce embedding for Mapillary street-level photos. The embed will help you bring Mapillary photos with you anywhere to tell your story.
100 Million Photos - Geotagged, Connected, and Available for All
Last year I wrote a blog post when we hit 10 million photos, to mark the date and thank everyone who helped us get there together. Today, we just passed 100 million.
Faster Navigation: Introducing MapillaryJS 2.0
MapillaryJS 2.0 improves the general performance of retrieving data and decreases the image loading time when navigating to a new place on the map.
Denser 3D Point Clouds in OpenSfM
We've improved OpenSfM—the technology we use to create 3D reconstructions from images. By adding post-processing, we get denser 3D point clouds resulting in better visualization, positioning, and much more.
Time Travel by Mapillary
A couple of weeks ago I went to the Petersen Automotive Museum in Los Angeles to do some research on time travel. After a couple of weeks of work on design and implementation, we arrived at time travel the Mapillary way.
Mapillary for Android—Same Mission, New Beginning
Today we are excited to share a complete makeover of Mapillary for Android with the 3.0 release. Reviewing, uploading and exploring are now much smoother and "more Mapillary", making it really easy to help you create a visual representation of the world.
Your Chance to Shape Our Community: Become a Mapillary Ambassador
We’re happy to announce that the Mapillary Ambassador Programme is expanding. If you feel enthusiastic about Mapillary and want to help grow the community then this is your opportunity.
Mapillary Now Able to Recognize and Label Objects in the Wild
We are happy to announce one of the first new contributions driven by our AI Lab in Graz, Austria - adding a feature that provides semantic segmentations for a select number of object categories. In this blog post, we will discuss what this is all about and why we think that this development will be useful for our members and customers.
Mapillary Joins Berkeley DeepDrive
We’re incredibly excited to join University of California Berkeley’s DeepDrive initiative to help push computer vision and deep learning forward. This, we hope, will improve understanding of street images for safer cities, autonomous cars, and better maps.
Everything is Better in 360: iOS App Gets 360 Support
We have added 360° camera support to the iOS app. The first camera we have added support for is the LG 360 Cam.
State of the Photo Map 2016
Two months ago I wrote a longer update on Mapillary and OpenStreetMap for the State of the Map US conference in Seattle. A lot has happened since, so I wanted to share a short OpenStreetMap-related update in time for State of the Map in Brussels.
Mapillary Named By Fast Company in 2016 Innovation by Design Awards
Big news! We’re finalists in two categories in Fast Company's Innovation By Design Awards 2016.
View What Interests You Most: Introducing Filters
Today we're re-releasing filters from the old Mapillary, sprinkled with a new flavor. If you're not familiar with filtering in general, here is the lowdown.
Partnering With HERE: Community Mapping Pilot
Today we're launching a community mapping pilot with HERE, the global provider of map data and services. We’re excited to welcome fans of MapCreator, HERE’s community tool for editing maps, and hope we can help each other in our mapping projects.
Introducing the Mapillary Humanitarian Mapping Kit, in Partnership with Humanitarian OpenStreetMap Team
Humanitarian OpenStreetMap Team (HOT) does amazing work in building and supporting local mapping communities around the world for people to create their own maps for socio-economic development and disaster preparedness. This is also one of the founding blocks of what we are creating with Mapillary.
Introducing A New, Better Mapillary
Today we’re excited to release the new Mapillary. This major update will improve the experience of exploring places with a redesigned map and a new viewer. We’re also releasing a new editor to edit photos captured by the Mapillary community, as well as improved upload functionality.
The New Mapillary—Design Principles
Redesigning and reimplementing Mapillary turned out to be an unprecedented project in the life of the company, as we basically rebuilt everything from scratch. We started from the ground up: first, we built a new tiler, which allowed us to actually show each photo in a sequence, just like beads on a string. We then asked ourselves if it would be possible to use Mapillary on the full screen map/photo at all times?
Meet Us at State of the Map US 2016!
This week we’re going to State of the Map US in Seattle and we’re looking forward to connect with both old and new friends from this vibrant open community.
Large-scale Map Matching with Meili
This is a joint post by Kevin Kreiser (Mapzen) and Tao Peng (Mapillary).
Mapillary Announced as 2016 Technology Pioneer by World Economic Forum
Our goal at Mapillary is to change the world — at least, to change the way we capture our world and record that representation. So we’re excited to announce this week that we’ve been honored by the World Economic Forum as one of their 2016 Technology Pioneers, a selection of the world’s most innovative early-stage companies.
Mapillary Chrome extension
Mapillary community members have captured and shared millions of photos with the world. You might have seen some spectacular examples on our Instagram and in our newsletters. We'd like to announce a new way to discover great photos on Mapillary in the official Mapillary Chrome extension! Every time you open a new tab you'll see a beautiful photo from Mapillary. You'll also be able to experience walking around these photos thanks to MapillaryJS. Just hit "Explore".
MapillaryEDU: Supporting a New Generation of Mappers
While doing some routine analysis of our photo coverage a few months ago, we noticed some unusual activity in a very specific area in Washington D.C.:
The latest component in a growing list extending the functionality of MapillaryJS exposes an API and functionality for photo tagging. With the tagging component we are adding support for displaying, creating and editing tags.
Say 'Servus' to Our New AI Lab!
Today we're excited to announce our recent addition to the computer vision side of Mapillary. We're opening an office and a deep learning AI lab in Graz, Austria. This is a big step in our quest of understanding places and how these places change over time based on our community's photographs.
Remake of mapillary.com
Did you think that things are slowing down at mapillary.com? Quite the opposite is happening. We're giving our entire site a complete remake.
Support for Multiple Action Cameras
A couple of months ago, we added support for Garmin cameras in the iOS app, and early adopters have shown that it produces amazing photos and sequences. Today we are adding support for multiple Garmin cameras. This means that you can create flexible "camera rigs" so that you can capture more than one direction. With four cameras, you can capture 360 degrees at the same time and don't have to drive the same route as often.
Mapillary and GoPro: Taking Street Photos into the Hands of the Adventurer
We are excited to finally announce that we are part of GoPro's new Developer Program, which was unveiled yesterday at Pier 35 in San Francisco. The program includes more than 100 developers, and we were selected along with 33 other companies to showcase our integration at the launch expo yesterday. It was a busy day showing off how easy our integration lets Mapillary members capture using GoPro cameras. We also met some of the other developers in the program and many GoPro engineers.
Mapillary Joins the US National Park Service’s Centennial Celebration
In 1916, the US National Park Service (NPS) was created to oversee land that had been protected with national park status. Today, the NPS is responsible for more than 84 million acres, which includes areas such as historic sites and monuments, in addition to parks like Yellowstone. This year, the NPS is celebrating its 100th birthday by encouraging people to explore local sites that are part of the National Park System and then share their stories with the #FindYourPark campaign. It’s a beautiful initiative that showcases how the NPS protects areas of all shapes and sizes.
The component based architecture of our open source library MapillaryJS makes it easy to extend with new functionality that is independent from the logic of other elements. Inspired by the historical image comparisons created by @neogeografen we decided to build our own slider component.
Announcing Our $8M Series A Round
We just closed an $8 million Series A financing round to enable us to expand. Last year was an incredible year for our community and for Mapillary as a company but we still have a long way to go to realize our vision of visually mapping the world. With this investment, we are in a great position to go all the way. Atomico led this round, with participation from our previous backers Sequoia, LDV Capital, Playfair, and Wellington.
New Mapillary Ambassadors
We are happy to announce that our Ambassador Program has expanded and we have eight new Ambassadors!
MapillaryJS is a tool used for displaying street level photos anywhere on the internet. Today we are putting it into your hands. It enables you to add street level photos to your blog, website or even into your professional mapping applications. Getting started with MapillaryJS is easy:
Support for more action cameras; GoPro Hero3 and Garmin VirbX/VirbXE
Not long ago, we added support for GoPro® cameras in the iOS app, and early adopters have shown it produces amazing photos and sequences. Now we add support for GoPro® Hero3 as well as Garmin® VirbX/VirbXE and also introduce a high-speed mode using the time-lapse feature of these action cameras.
How Mapillary Works with Cities
At the last Esri User Conference, I met an environmental consultant who worked on a project verifying fire hydrant locations for a small town. He checked out each coordinate on Google Street View -- “by hand!” he insisted, referring to restrictions on using the Google Maps API for deriving datasets and asset tracking. He hadn’t minded the laborious process so much as an unexpected problem: Street View was neither current nor complete. Street View cars had driven through the town over three years ago, and hadn’t captured smaller streets and hiking trails.
Mapillary and GoPro® – A Match Made in Mapping Heaven
We love GoPro® cameras. These tiny action cameras create stunning, quality images. They have a wide field of view and can capture up to two photos every second, making them perfect when you're creating Structure from Motion, like we are with our 3D Navigation tool. Also, they are easy to mount on pretty much anything.
First, there was Picture-in-Picture (PiP). It was awesome and all the kids were raving about it. Now we introduce the next big thing, Map-in-Camera, or simply MiC.
Mapillary Ambassador Program
We are thrilled to announce a new way to engage with the Mapillary community to create a photo representation of the world.
Major Improvements to All Shapes in Mapillary
We have been struggling a long time to get detailed shapes for statistics, notifications and exploration at Mapillary. We have been relying on simplified shapes which were not fully accurate.
Point Clouds: Behind the Scenes of Our 3D Navigation
At Mapillary, we don’t want to simply show you photos on maps – we want you to feel immersed in whichever landscape you’re exploring. Behind-the-scenes, we have been 3D reconstructing every location our members photograph and now, we want to show you. We're giving our community the power to virtually explore their photos like never before.
Panorama Connections and Navigation
Consumer spherical cameras are coming. Some, like the Ricoh Theta, are already here. This means that it is now possible for individuals to capture spherical images massively. Preparing for that, we are now enabling pano navigation mode.
Mapillary Location Search Now Powered by Mapzen Search
Recently Mapzen launched Mapzen Search. It is a search engine for places worldwide, fully powered by open data and freely available to everyone.
Announcing Mapillary for ArcGIS
Today we're pleased to announce the release of Mapillary for ArcGIS!
First Photo Day - A Look at Two Years of Mapillary
Today, October 8, is First Photo Day here at Mapillary, the day when the first Mapillary photo was published in 2013. A lot has happened in these two roller-coaster years. Here is my summary.