In this paper we propose an approach for estimating the confidence of stereo matches for superpixel-based disparity estimation. To our knowledge, this is the first such method reported in the literature. Starting from a simple superpixel stereo algorithm, we present a representative set of features that can be extracted from the disparity map and the superpixel fitting process. A random forest classifier is then trained on these features to predict whether the disparity assigned to each pixel of a test disparity map is correct or not. We perform experiments on the KITTI stereo benchmark and show that our confidence estimator is very accurate in predicting which disparities are correct and which are not. We also present a post-processing algorithm for improving the accuracy of the disparity maps that exploits the confidence estimates to reject wrong disparity values and achieves significant error reduction.
The momentum around Software-defined Networking (SDN) is increasing. It has become clear that the network architecture needs to evolve to be able to provide current and next generation networking services, both from a performance and implementation point of view. However, most of the current SDN research has looked to specificities of SDN and few have looked from a full stack perspective. Although the former are essential, also the latter perspective needs to be taken into account. In this sense, our work proposes a complete and modular SDN framework targeted at connectivity services. This framework allows the creation and management of network connectivity services over an OpenFlow based network, with mechanisms of fault-management, as well as the optimal usage of the infrastructure. The performance results obtained from the SDN framework evaluation in a real environment show that the three different scenarios, service activation, link loss, and reaction to a new link, are dynamically supported with fast reaction to the network changes.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.