Single image ground plane estimation

Accurate depth perception serves as a valuable piece of information for environmental understanding. Ground plane estimation is considered as an important part of a complete depth perception algorithm. In this paper, we devise a method to estimate a ground plane from a single static image. We introduce an ensemble of features to be extracted on predicted ground pixels and follow a different, but simpler, approach from the previous works to estimate the depths. Powerful gradient boosting regression instead of linear parameter estimation yields fascinating results as baseline depth estimation. Finally, our RANSAC based depth smoothing with the ability to reject outliers achieves current state of the art results.