Lately stereo matching has become a key aspect in autonomous driving, providing highly accurate solutions at relatively low cost. Top approaches on state of the art benchmarks rely on learning mechanisms such as convolutional neural networks (ConvNets) to boost matching accuracy. We propose a new real-time stereo reconstruction method that uses a ConvNet for semantically segmenting the driving scene. In a “divide and conquer” approach this segmentation enables us to split the large heterogeneous traffic scene into smaller regions with similar features. We use the segmentation results to enhance Census Transform with an optimal census mask and the SGM energy optimization step with an optimal Pi penalty for each predicted class. Additionally, we improve the sub-pixel accuracy of the stereo matching by finding optimal interpolation functions for each particular segment class. In both cases we propose new stochastic optimization methods based on genetic algorithms that can incrementally adjust the parameters for better solutions. Tests performed on Kitti and real traffic scenarios show that our method outperforms the accuracy of previous solutions.
Semantic segmentation-based stereo reconstruction with statistically improved long range accuracy
2017 IEEE Intelligent Vehicles Symposium (IV) ; 1795-1802
2017-06-01
423223 byte
Conference paper
Electronic Resource
English
Improving sub-pixel accuracy for long range stereo
British Library Online Contents | 2012
|ACCURACY ANALYSIS OF SURFACE NORMAL RECONSTRUCTION IN STEREO VISION
British Library Conference Proceedings | 2014
|Statistically Evaluating the Imputation Accuracy of Highway Agencies
British Library Conference Proceedings | 2004
|