Stereo image dense matching, which plays a key role in 3D reconstruction, remains a challenging task in photogrammetry and computer vision. In addition to block-based matching, recent studies based on artificial neural networks have achieved great progress in stereo matching by using deep convolutional networks. This study proposes a novel network called a dual guided aggregation network (Dual-GANet), which utilizes both left-to-right and right-to-left image matchings in network design and training to reduce the possibility of pixel mismatch. Flipped training with a cost volume consistentization is introduced to realize the learning of invisible-to-visible pixel matching and left–right consistency matching. In addition, suppressed multi-regression is proposed, which suppresses unrelated information before regression and selects multiple peaks from a disparity probability distribution. The proposed dual network with the left–right consistent matching scheme can be applied to most stereo matching models. To estimate the performance, GANet, which is designed based on semi-global matching, was selected as the backbone with extensions and modifications on guided aggregation, disparity regression, and loss function. Experimental results on the SceneFlow and KITTI2015 datasets demonstrate the superiority of the Dual-GANet compared to related models in terms of average end-point-error (EPE) and pixel error rate (ER). The Dual-GANet with an average EPE performance = 0.418 and ER (>1 pixel) = 5.81% for SceneFlow and average EPE = 0.589 and ER (>3 pixels) = 1.76% for KITTI2005 is better than the backbone model with the average EPE performance of = 0.440 and ER (>1 pixel) = 6.56% for SceneFlow and average EPE = 0.790 and ER (>3 pixels) = 2.32% for KITTI2005.
Purpose
Using social networks to identify users with traits similar to those of the target user has proven highly effective in the development of personalized recommendation systems. Existing methods treat all dimensions of user data as a whole, despite the fact that most of the information related to different dimensions is discrete. This has prompted researchers to adopt the skyline query for such search functions. Unfortunately, researchers have run into problems of instability in the number of users identified using this approach.
Design/methodology/approach
We thus propose the m-representative skyline queries to provide control over the number of similar users that are returned. We also developed an R-tree-based algorithm to implement the m-representative skyline queries.
Findings
By using the R-tree based algorithm, the processing speed of the m-representative skyline queries can now be accelerated. Experiment results demonstrate the efficacy of the proposed approach.
Originality/value
Note that with this new way of finding similar users in the social network, the performance of the personalized recommendation systems is expected to be enhanced.
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.