期刊
IEEE SIGNAL PROCESSING LETTERS
卷 28, 期 -, 页码 2197-2201出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LSP.2021.3123907
关键词
Semantics; Image segmentation; Feature extraction; Loss measurement; Visualization; Image recognition; Image coding; Visual place recognition; multi-modal fusion; dynamics-invariant space; image translation; deep learning
资金
- Postgraduate Research and Practice Innovation Program of Jiangsu Province [SJCX20_0035]
- Fundamental Research Funds for the Central Universities [3208002102D]
- National Natural Science Foundation of China [61803084]
This research successfully improves place recognition in dynamic environments by utilizing multi-modal fusion, deep learning architecture, and spatial-pyramid-matching model.
Visual place recognition is one of the essential and challenging problems in the fields of robotics. In this letter, we for the first time explore the use of multi-modal fusion of semantic and visual modalities in dynamics-invariant space to improve place recognition in dynamic environments. We achieve this by first designing a novel deep learning architecture to generate the static semantic segmentation and recover the static image directly from the corresponding dynamic image. We then innovatively leverage the spatial-pyramid-matching model to encode the static semantic segmentation into feature vectors. In parallel, the static image is encoded using the popular Bag-of-words model. On the basis of the above multi-modal features, we finally measure the similarity between the query image and target landmark by the joint similarity of their semantic and visual codes. Extensive experiments demonstrate the effectiveness and robustness of the proposed approach for place recognition in dynamic environments.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据