Your GPS is great for getting you where your going, but the accuracy of the navigation system does have its downfalls. Leading you down a one way street or a dead end is not unheard of since changes on the roadways are not picked up by the GPS. Currently the mapping companies need to get someone to drive up and down streets in a vehicle with cameras fixed in all directions noting the changes on the streets. They take this footage back to the office where it is analyzed, frame by frame, and someone records where all the changes are. Because this is a tedious task, mistakes are often made.

The Smart Cars project, a joint effort between the National ICT Australia (NICTA), the Australian Commonwealth Scientific and Research Organization (CSIR), and the Australian National University, could make these problems a thing of the past. The NICTA, using Linux based technology will develop technology to make personal navigation systems more accurate.

AutoMap, developed by the NICTA, uses machine vision techniques that can detect and classify geometric shapes from video footage. These shapes include things like signs and company logos, the type of fixtures that change frequently in a neighborhood and make it difficult for digital map makers to keep their products up to date. Instead of having cameras fixed to vehicles specifically for recording changes on the roads, the cameras can be mounted on vehicles that already travel the roads on a regular basis, such as taxi cabs or garbage trucks. The technology could be on the market in as little at 12 months.