Outlier Robust Feature Correspondence by Learning Based Matching Process

Feature correspondence is a crucial aspect of various computer vision and robot vision tasks.Unlike traditional optimization-based matching techniques,researchers have recently adopted a learning-based approach for matching,but these methods face challenges in dealing with outlier features.This paper presents an outlier robust feature correspondence method that employs a pruned attentional graph neural network and a matching layer to address the outlier issue.Additionally,the authors introduce a modified cross-entropy matching loss to handle the outlier problem.As a result,the proposed method significantly enhances the performance of learning-based matching algorithms in the presence of outlier features.Benchmark experiments confirm the effectiveness of the proposed approach.

A feature extraction and correspondence algorithm for laser range finder with sensor uncertainty

This paper presents a feature extraction and correspondence algorithm which employs a novel feature transform. Unlike conventional approaches such as Hough Transform, we employ a robust but simple approach to extract the geometrical feature under real dynamic world conditions. Multi-threshold segmentation and the split-and-merge method are employed to interpret geometrical features such as edge, concave corners, convex corners, and segments in a unified framework. The features are represented by feature tree (F-Tree) so as to compactly represent the environments and some important properties of the F-Tree are discussed in this paper. To demonstrate the validity of the approach, we show the actual experiment results which are based on real Laser Range Finder data and real time analysis. The comparative study with Hough Transform shows the advantages and the high performance of the proposed algorithm.

Feature matching based on geometric constraints in weakly calibrated stereo views of curved scenes

The identification of the correspondences of points of views is an important task. A new feature matching algorithm for weakly calibrated stereo images of curved scenes is proposed, based on mere geometric constraints. After initial correspondences are built via the epipolar constraint, many point-to-point image mappings called homographies are set up to predict the matching position for feature points. To refine the predictions and reject false correspondences, four schemes are proposed. Extensive experiments on simulated data as well as on real images of scenes of variant depths show that the proposed method is effective and robust.

Feature matching using quasi-conformal maps

We present a fully automatic method for finding geometrically consistent correspondences while discarding outliers from the candidate point matches in two images. Given a set of candidate matches provided by scale-invariant feature transform(SIFT) descriptors, which may contain many outliers, our goal is to select a subset of these matches retaining much more geometric information constructed by a mapping searched in the space of all diffeomorphisms. This problem can be formulated as a constrained optimization involving both the Beltrami coefficient(BC) term and quasi-conformal map, and solved by an efficient iterative algorithm based on the variable splitting method. In each iteration, we solve two subproblems, namely a linear system and linearly constrained convex quadratic programming. Our algorithm is simple and robust to outliers. We show that our algorithm enables producing more correct correspondences experimentally compared with state-of-the-art approaches.

Graph Convolutional Network Combined with Semantic Feature Guidance for Deep Clustering

The performances of semisupervised clustering for unlabeled data are often superior to those of unsupervised learning,which indicates that semantic information attached to clusters can significantly improve feature representation capability.In a graph convolutional network(GCN),each node contains information about itself and its neighbors that is beneficial to common and unique features among samples.Combining these findings,we propose a deep clustering method based on GCN and semantic feature guidance(GFDC) in which a deep convolutional network is used as a feature generator,and a GCN with a softmax layer performs clustering assignment.First,the diversity and amount of input information are enhanced to generate highly useful representations for downstream tasks.Subsequently,the topological graph is constructed to express the spatial relationship of features.For a pair of datasets,feature correspondence constraints are used to regularize clustering loss,and clustering outputs are iteratively optimized.Three external evaluation indicators,i.e.,clustering accuracy,normalized mutual information,and the adjusted Rand index,and an internal indicator,i.e., the Davidson-Bouldin index(DBI),are employed to evaluate clustering performances.Experimental results on eight public datasets show that the GFDC algorithm is significantly better than the majority of competitive clustering methods,i.e.,its clustering accuracy is20% higher than the best clustering method on the United States Postal Service dataset.The GFDC algorithm also has the highest accuracy on the smaller Amazon and Caltech datasets.Moreover,DBI indicates the dispersion of cluster distribution and compactness within the cluster.

Feature-based RGB-D camera pose optimization for real-time 3D reconstruction

In this paper we present a novel featurebased RGB-D camera pose optimization algorithm for real-time 3D reconstruction systems. During camera pose estimation, current methods in online systems suffer from fast-scanned RGB-D data, or generate inaccurate relative transformations between consecutive frames. Our approach improves current methods by utilizing matched features across all frames and is robust for RGB-D data with large shifts in consecutive frames. We directly estimate camera pose for each frame by efficiently solving a quadratic minimization problem to maximize the consistency of3 D points in global space across frames corresponding to matched feature points. We have implemented our method within two state-of-the-art online 3D reconstruction platforms. Experimental results testify that our method is efficient and reliable in estimating camera poses for RGB-D data with large shifts.