Turning Video into Traffic Data Part Two

In Turning Video into Traffic Data Part One, I wrote about Miovision’s systematic method for processing the large amount of video that is uploaded to our system. I detailed our three step process for video configuration, quality assurance, and data validation, and explained how computer vision is used to detect vehicle movements from video. If you haven’t yet read Part One, I would recommend you start there.

In this second-and-final post, I will be diving into the details of data accuracy, how we account for error, how we develop our best-in-class algorithm, and how that helps our customers rely on the quality of Miovision data for any project of any size.

Additional content credits to Justin Eichel, PhD, Miovision Technical Director and Computer Vision Architect, and James Barr, Miovision Product Manager.

Deconstructing a Frame of Video into Spatial Regions for Counting

When video is uploaded to Miovision, cardinal direction and number of lanes are required inputs. That is because each video is split into video segments to be processed individually.

Each video segment is determined by spatial region, lane and approach. Segments are then  distributed through a number of processes on a cloud computing service and queued for distribution to a computer vision task.

When computer vision tasks are complete, each video segment is queued for human review and verification. Humans manually count a 12% cross-section from each hour of video to ensure that the computer vision algorithm is properly producing counts and the data is accurate.

annotating an intersection

Screenshot: When the customer uploads a video to the Miovision Platform, they are required to annotate each leg of the intersection (or other road facility) and denote the camera position in relation to vehicle movements. This ensures proper configuration, and this metadata is stored with the count data and video for posterity. The annotation provided in this step is then deconstructed one step further at Miovision and made into counting tasks.

Read more

Busy Junction at Night from Above

Turning Video into Traffic Data Part One

As of this spring, Miovision will have turned 1.5 million hours of video into traffic data from multiple video sources, including our own Scout Video Collection Unit. With daily volumes as high as 7,000 hours of video, we rely on a systematic method of combining computer vision algorithms  and human verification to ensure data reports meet our customers’ expectations.

In this two-part blog series, I’ll be writing about how Miovision turns video into traffic data with significant support from Miovision Technical Director and Computer Vision Architect Justin Eichel, PhD.

Video-Based Traffic Data Collection

For those not familiar with Miovision’s traffic data collection solution, here’s a quick overview:

  1. Customer records video: this can be of an intersection, midblock, highway count, roundabout or pedestrian and bicycle location. Video can be provided by any video source, but we recommend our best-in-class Scout video collection unit.
  2. Video is uploaded to Miovision: every customer has a cloud-based account on the Miovision Platform where they can upload video and quickly select the types and amount of data they need.
  3. Data Reports are Downloaded: the video is turned into traffic data on the Miovision Platform. Data reports are stored on the customer account and available for download in a variety of formats, along with the video recording.

three step process

Read more

Miovision’s Traffic Signal Survey Results Infographic

Every year since 2012, Miovision has conducted a peer-driven Traffic Signal Survey. The survey measures the current state of traffic signal maintenance and operations in North America. The question categories include: traffic data collection traffic data reporting and visualization activities software and systems traffic signal connectivity

Outsourcing Traffic Data Collection

Outsourcing Traffic Data Collection Research InitiativeIn July, we contacted engineering firms across Canada and the US to take part in Miovision’s second research initiative. It would focus on engineering firms who outsource some or all of their traffic data collection to vendors.

We targeted engineering firms, as many of these firms complete large transportation projects, where data collection is only a fraction of the project.

Read more