Fangming Yuan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Fangming Yuan has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Peer Neubert
University of Koblenz
2 shared publications - Peter Protzel
Chemnitz University of Technology
2 shared publications - Stefan Schubert
TU Chemnitz
1 shared publication
Latest Publications
- 29 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (3) , 2686-2693
Local Positional Graphs and Attentive Local Features for a Data and Runtime-Efficient Hierarchical Place Recognition Pipeline
Large-scale applications of Visual Place Recognition (VPR) require computationally efficient approaches. Further, a well-balanced combination of data-based and training-free approaches can decrease the required amount of training data and effort and can reduce the influence of distribution shifts between the training and application phases. This paper proposes a runtime and data-efficient hierarchical VPR pipeline that extends existing approaches and presents novel ideas. There are three main contributions: First, we propose Local Positional Graphs (LPG), a training-free and runtime-efficient approach to encode spatial context information of local image features. LPG can be combined with existing local feature detectors and descriptors and considerably improves the image-matching quality compared to existing techniques in our experiments. Second, we present Attentive Local SPED (ATLAS), an extension of our previous local features approach with an attention module that improves the feature quality while maintaining high data efficiency. The influence of the proposed modifications is evaluated in an extensive ablation study. Third, we present a hierarchical pipeline that exploits hyperdimensional computing to use the same local features as holistic HDC-descriptors for fast candidate selection and for candidate reranking. We combine all contributions in a runtime and data-efficient VPR pipeline that shows benefits over the state-of-the-art method Patch-NetVLAD on a large collection of standard place recognition datasets with 15 $\%$ better performance in VPR accuracy, 54× faster feature comparison speed, and 55× less descriptor storage occupancy, making our method promising for real-world high-performance large-scale VPR in changing environments. Source code is provided online: https://github.com/Yuan-Fangming/Hir-ATLAS
- 29 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (3) , 2686-2693
Local Positional Graphs and Attentive Local Features for a Data and Runtime-Efficient Hierarchical Place Recognition Pipeline
Large-scale applications of Visual Place Recognition (VPR) require computationally efficient approaches. Further, a well-balanced combination of data-based and training-free approaches can decrease the required amount of training data and effort and can reduce the influence of distribution shifts between the training and application phases. This paper proposes a runtime and data-efficient hierarchical VPR pipeline that extends existing approaches and presents novel ideas. There are three main contributions: First, we propose Local Positional Graphs (LPG), a training-free and runtime-efficient approach to encode spatial context information of local image features. LPG can be combined with existing local feature detectors and descriptors and considerably improves the image-matching quality compared to existing techniques in our experiments. Second, we present Attentive Local SPED (ATLAS), an extension of our previous local features approach with an attention module that improves the feature quality while maintaining high data efficiency. The influence of the proposed modifications is evaluated in an extensive ablation study. Third, we present a hierarchical pipeline that exploits hyperdimensional computing to use the same local features as holistic HDC-descriptors for fast candidate selection and for candidate reranking. We combine all contributions in a runtime and data-efficient VPR pipeline that shows benefits over the state-of-the-art method Patch-NetVLAD on a large collection of standard place recognition datasets with 15 $\%$ better performance in VPR accuracy, 54× faster feature comparison speed, and 55× less descriptor storage occupancy, making our method promising for real-world high-performance large-scale VPR in changing environments. Source code is provided online: https://github.com/Yuan-Fangming/Hir-ATLAS
- 3 December 2020
- Published by Springer Nature
- p. 209-213
LocalSPED: A Classification Pipeline that Can Learn Local Features for Place Recognition Using a Small Training Set
- 3 December 2020
- Published by Springer Nature
- p. 209-213
LocalSPED: A Classification Pipeline that Can Learn Local Features for Place Recognition Using a Small Training Set