A Hierarchical Image Analysis for Extracting Parking Lot Structures from Aerial Images

Abstract

The availability of road network information simplifies autonomous driving by providing useful prior information about driving environments which is valuable for planning and perception. It tells a robotic vehicle where it can drive, models of what can be expected where, and provides contextual cues that influence driving behaviors. Currently, however, road network information for driving environments is manually generated using a combination of GPS survey and aerial imagery. These techniques for converting digital imagery into road network information are labor intensive, reducing the benefit provided by digital maps. To fully exploit the benefits of digital imagery, these processes should be automated. As a step toward this goal, we present an algorithm that extracts the structure of a parking lot visible from a given aerial image. We propose a hierarchical approach to generating and evaluating candidate hypotheses. We test three different machine learning algorithms and their combinations for removing erroneous hypotheses. From the experimental results, our Markov Random Field implementation performs best in terms of false negative rate and Eigenspots performs best in terms of false positive rate.