Tracing roads by hand is slow, and automation has the potential to greatly accelerate the process of mapping roads. That said, although there has been two decades of research in automatic map inference, these systems have not gained traction. Fundamentally, high error rates in these systems make full automation impractical. We instead consider machine-assisted map editing, where automatic map inference is integrated with existing, human-centric map editing workflows. To realize this, we built Machine-Assisted iD, where we extended the web-based iD editor with machine-assistance features. These features enable users to efficiently validate automatically inferred roads in an interactive workflow. We designed the system to tackle the addition of major, arterial roads in regions where existing maps have poor coverage, and the incremental improvement of coverage in regions where major roads are already mapped.
When Seeing Isn’t Solving: Data Lessons From Detroit’s Never-Ending Tax Foreclosure Crisis
What happens when you map a major problem and…nothing much happens? Can map makers and data nerds become change makers? Loveland Technologies started mapping tax foreclosed properties in Detroit and Wayne County...
