Semantic segmentation of terrain and road terrain for advanced driver assistance systems

This thesis explores prospective terrain recognition for an anticipating terrain response driver assistance system. Recognition of terrain and road terrain is cast as a semantic segmentation task whereby forward driving images or point clouds are pre-segmented into atomic units and subsequently classified. In this work, colour, texture and sur-face saliency of atomic units are obtained with a bag-of-features approach. Five terrain classes are considered, namely grass, dirt, gravel, shrubs and tarmac. Since colour can be ambiguous among terrain classes such as dirt and gravel, several texture flavours are explored with scalar and structured output learning in a bid to devise an appropriate visual terrain saliency and predictor combination. Texture variants are obtained using local binary patters (LBP), filter responses (or textons) and dense key-point descriptors with daisy. Learning algorithms tested include support vector machine (SVM), random forest (RF) and logistic regression (LR) as scalar predictors while a conditional random field (CRF) is used for structured output learning. Once a suitable texture representation is devised the attention is shifted from monocular vision to stereo vision. Surface saliency from reconstructed point clouds can be used to enhance terrain recognition. Upon realisation that road recognition and terrain recognition can be assumed as equivalent problems in urban environments, the top most accurate models consisting of CRFs are augmented with compositional high order pattern potentials (CHOPP). This leads to models that are able to strike a good balance between smooth local labelling and global road shape. For urban environments the label set is restricted to road and non-road (or equivalently tarmac and non-tarmac). Experiments are conducted using a proprietary terrain dataset and a public road evaluation dataset.


  • English

Media Info

  • Pagination: 1 file

Subject/Index Terms

Filing Info

  • Accession Number: 01596290
  • Record Type: Publication
  • Source Agency: ARRB
  • Files: ATRI
  • Created Date: Apr 20 2016 1:55PM