A constrained clustering based approach for matching a collection of feature sets

Yan, Junchi; Ren, Zhe; Zha, Hongyuan; Chu, Stephen M.

doi:10.1109/icpr.2016.7900232

Cited by 13 publications

(7 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [34], the clustering perspective is used in an algorithm that iterates between a matching step and the selection of mean features (similarly to k-means); this algorithm is sensitive to the initialization used, and multiple iterations are typically needed in order to achieve convergence.…”

Section: Clusteringmentioning

confidence: 99%

Fast Multi-image Matching via Density-Based Clustering

Tron

Zhou

Esteves

et al. 2017

2017 IEEE International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

We consider the problem of finding consistent matches across multiple images. Current state-of-the-art solutions use constraints on cycles of matches together with convex optimization, leading to computationally intensive iterative algorithms. In this paper, we instead propose a clusteringbased formulation: we first rigorously show its equivalence with traditional approaches, and then propose QuickMatch, a novel algorithm that identifies multi-image matches from a density function in feature space. Specifically, QuickMatch uses the density estimate to order the points in a tree, and then extracts the matches by breaking this tree using feature distances and measures of distinctiveness. Our algorithm outperforms previous state-of-the-art methods (such as MatchALS) in accuracy, and it is significantly faster (up to 62 times faster on some benchmarks), and can scale to large datasets (with more than twenty thousands features).

show abstract

Section: Clusteringmentioning

confidence: 99%

Fast Multi-image Matching via Density-Based Clustering

Tron

Zhou

Esteves

et al. 2017

2017 IEEE International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

show abstract

“…Given the results shown in Figure 6(b), we can see that our approach obtains the best performance when the dropout rate is in the range of [0.4, 0.5] and the performance decreases fast as the dropout rate increases from 0.6 to 0.8. The sampling number has several optimal values in our evaluation range, including [20,30], [50,60] or [80, 90].…”

Section: E Discussionmentioning

confidence: 99%

“…The second category of methods use the spatial similarity among objects using, e.g., distances between the objects in pairwise graph matching [6,29], angular relationships of objects in hypergraph matching [34,42], spatial relationships built by four or more objects in clique matching [35], and a combination of multiple spatial relationships [5]. The third category of methods recognize object correspondences by enforcing the circle-consistent constraints in multiple views [10], e.g., based on convex relaxation [3], spectral relaxation [32] and graph clustering [50].…”

Section: A Correspondence Identificationmentioning

confidence: 99%

Bayesian Deep Graph Matching for Correspondence Identification in Collaborative Perception

Gao¹,

Zhang²

2021

Robotics: Science and Systems XVII

View full text Add to dashboard Cite

Correspondence identification is essential for multirobot collaborative perception, which aims to identify the same objects in order to ensure consistent references of the objects by a group of robots/agents in their own fields of view. Although recent deep learning methods have shown encouraging performance on correspondence identification, they suffer from two shortcomings, including the inability to address non-covisibility in collaborative perception that is caused by occlusion and limited fields of view of the agents, and the inability to quantify and reduce uncertainty to improve correspondence identification. To address both issues, we propose a novel uncertainty-aware deep graph matching method for correspondence identification in collaborative perception. Our new approach formulates correspondence identification as a deep graph matching problem, which identifies correspondences based upon graph representations that are constructed from the agents' observations. We introduce a novel deep graph matching network under the Bayesian framework to explicitly quantify uncertainty in the identified correspondences. In addition, we design a novel loss function that explicitly reduces correspondence uncertainty and perceptual non-covisibility during learning. We evaluate our approach in the robotics applications of collaborative assembly and multi-robot coordination using high-fidelity simulations and physical robots. Experiments have shown that, through addressing both uncertainty and non-covisibility, our approach achieves the state-of-the-art performance of correspondence identification.

show abstract

“…Methods in the third category use a graph representation of the problem. In [17] and [3], the authors have elegantly observed the equivalence relation between cycle consistency and cluster structure of the association graph. This observation is used to find a suboptimal solution to the problem based on existing graph clustering algorithms.…”

Section: A Related Workmentioning

confidence: 99%

CLEAR: A Consistent Lifting, Embedding, and Alignment Rectification Algorithm for Multi-View Data Association

Fathian¹,

Khosoussi²,

Tian³

et al. 2019

Preprint

View full text Add to dashboard Cite

Many robotics applications require alignment and fusion of observations obtained at multiple views to form a global model of the environment. Multi-way data association methods provide a mechanism to improve alignment accuracy of pairwise associations and ensure their consistency. However, existing methods that solve this computationally challenging problem are often too slow for real-time applications. Furthermore, some of the existing techniques can violate the cycle consistency principle, thus drastically reducing the fusion accuracy. This work presents the CLEAR (Consistent Lifting, Embedding, and Alignment Rectification) algorithm to address these issues. By leveraging insights from the multi-way matching and spectral graph clustering literatures, CLEAR provides cycle consistent and accurate solutions in a computationally efficient manner. Numerical experiments on both synthetic and real datasets are carried out to demonstrate the scalability and superior performance of our algorithm in real-world problems. This algorithmic framework can provide significant improvement in the accuracy and efficiency of existing discrete assignment problems, which traditionally use pairwise (but potentially inconsistent) correspondences. An implementation of CLEAR is made publicly available online. SUPPLEMENTARY MATERIALCLEAR source code and the code for generating comparison results: https://github.com/KavehFathian/clear.

show abstract

A constrained clustering based approach for matching a collection of feature sets

Cited by 13 publications

References 51 publications

Fast Multi-image Matching via Density-Based Clustering

Fast Multi-image Matching via Density-Based Clustering

Bayesian Deep Graph Matching for Correspondence Identification in Collaborative Perception

CLEAR: A Consistent Lifting, Embedding, and Alignment Rectification Algorithm for Multi-View Data Association

Contact Info

Product

Resources

About