Traffic Jams in Helsinki
Are there traffic jams in Helsinki? People living in Helsinki would say YES, and people living in central Europe would probably laugh at this. The traffic jams are relatively mild compared to many other places but there are clearly times and locations where the traffic slows down significantly.
RoadCloud and WhereOS have joined forces to collect, analyze and visualize data collected from the fleet of commercial vehicles through RoadCloud sensors. “It’s amazing how detailed information you can collect from road network conditions through RoadCloud sensors”, says JP Partanen, CEO of WhereOS.
In the series of articles, we explain how the data can be collected from vehicle fleets and processed into models, that can further be used to solve different business problems such as traffic conditions, road conditions, or even creating machine learning / artificial intelligence model to predict these conditions based on other external variables such as weather forecasts. In this article, we explain how we created a video visualization of traffic conditions & jams throughout the day. “We are impressed with WhereOS, and how it quick it was to turn our data into an insightful video. We are integrating our data API to WhereOS and making our anonymized vehicle data easily accessible”, says Ari Tuononen, CEO of RoadCloud.
Capturing Vehicle Flow Data with RoadCloud IoT Sensors
RoadCloud has equipped commercial vehicle fleet with RoadCloud IoT sensors to collect and monitor vehicle data and road conditions. The sensors are automatically collecting basic information such speed, heading and acceleration, but more importantly information about road surface conditions such as road friction, road state (dry/snow/ice/water), temperature, bumps and pot holes as a few examples. The data collection is taking place 24/7, as the commercial vehicles are continuously throughout the day and night.
The sensor data is uploaded to the RoadCloud data backbone, where it is stored for further use & analysis. The data can be processed as historical data, or as a real-time feed of continuous updating data.
Analyzing and Visualizing the Sensor Data with WhereOS
WhereOS connects to the RoadCload data backbone and can process the data further. In this visualization, the RoadCloud data is processed and combined with OpenStreetMap (OSM) street network data in several pipelines:
- OSM data preparation pipeline extracts the OpenStreetMap street network for the desired region, Helsinki capital area in this case, and splits the streets into segments of desired length (e.g. 200m).
- RoadCloud data extraction pipeline loads data from RoadCloud data backbone, and assigns joins the GPS (latitude & longitude) data points into corresponding street segments. Joining uses WhereOS geokey/geohash based operation for matching massive amount of geographical shapes – GPS points and polylines/linestrings (street segments) – together.
- NTILE pipeline takes the joined data, and approximates maximum speed for each street segment, by taking average of the 10% highest speeds driven on that specific street segment.
- Hourly traffic pipeline calculates average speed driven for each individual street segment for each hour, and also the speed decrease from the maximum speed.
- Rendering pipeline takes speed decrease for each street segment for each hour and produces an MP4 video where each frame represents traffic conditions (speed decrease) for each street segment for the given hour. Each street segment is colored so that red equals to high speed decrease (i.e. high traffic / traffic jam) and green means no decrease (i.e. traffic speed close to maximum).
WhereOS uses Spark and Hive as the execution engine for the pipelines. WhereOS pipelines can be created using SQL and R programming languages including built-in functions for ETL (extract, transform, load) operations, statistical analysis, machine learning and artificial intelligence (AI), geographical and geospatial analysis, data visualization etc.
Traffic Jam Video & Further Innovation
The data used for this video has been collected from the vehicles over the time of one full year (2018). You can see how the rush hour traffic affects the average speeds at different locations on different times of the day.
The RoadCloud data can be used for many other analyses such as: How the road conditions – friction, road state (dry/wet/ice/snow), temperature – affect the average speeds. Or how a speed bump or some other new traffic arrangement affects the traffic around it. In the upcoming articles we will dig deeper into the data and create new interesting visualizations out of it.