Vehicular velocity prediction is of great significance to intelligent transportation system, as it provides a possible future velocity sequence for vehicle's decision-making system. A velocity prediction method via meta learning is proposed, which provides an adaptive and generative framework for multiple-driving cycles. The prediction model is devised using a deep neural network structure. The model's training is performed by the recently proposed meta-supervised learning, which ensures that one trained model could meet the adaptability to multiple driving cycles. The complete framework consists of three parts: Pre-training, fine-tune-training and real-time prediction, which is tested to predict the hybrid electric city buses' future velocity in a variable traffic scenario. The average prediction accuracy of 3, 5 and 10 s horizons is 0.51, 0.63 and 0.88 m s −1 , which is 25.9%, 16.78% and 7.47% higher than that trained by the conventional supervised learning method. As suggested, the proposed prediction method is effective and could meet the requirement of energysaving control for hybrid electric city buses. With further study, potential application of this method may also exist in the field of driving behaviour prediction and transportation mode recognition. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
In this paper, we present a stereo matching algorithm based on planar surface hypothesis. It improves the results of low texture regions and mixed pixels on object boundaries. First, regions are segmented by applying the mean-shift segmentation method. Then we propose a coarse-to-fine algorithm to increase the reliable correspondences in low texture regions. Third, the Belief Propagation algorithm is used to optimize disparity plane labeling. Finally, for a mixed pixel, we utilize the results of the depth plane and the local region of it to regulate its disparity. Experimental results using the Middlebury stereo test show that the performance of our method is high.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.