PT Unknown
AU Naveen Onkarappa
   Angel Sappa
TI Laplacian Derivative based Regularization for Optical Flow Estimation in Driving Scenario
BT 15th International Conference on Computer Analysis of Images and Patterns
PY 2013
BP 483
EP 490
VL 8048
DI 10.1007/978-3-642-40246-3_60
DE Optical flow; regularization; Driver Assistance Systems; Performance Evaluation
AB Existing state of the art optical flow approaches, which are evaluated on standard datasets such as Middlebury, not necessarily have a similar performance when evaluated on driving scenarios. This drop on performance is due to several challenges arising on real scenarios during driving. Towards this direction, in this paper, we propose a modification to the regularization term in a variational optical flow formulation, that notably improves the results, specially in driving scenarios. The proposed modification consists on using the Laplacian derivatives of flow components in the regularization term instead of gradients of flow components. We show the improvements in results on a standard real image sequences dataset (KITTI).
ER