동적 도시 환경에서 의미론적 시각적 장소 인식
Semantic Visual Place Recognition in Dynamic Urban Environment
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In visual simultaneous localization and mapping (vSLAM), the correct recognition of a place benefits in relocalization and improved map accuracy. However, its performance is significantly affected by the environmental conditions such as variation in light, viewpoints, seasons, and presence of dynamic objects. This research addresses the problem of feature occlusion caused by interference of dynamic objects leading to the poor performance of visual place recognition algorithm. To overcome the aforementioned problem, this research analyzes the role of scene semantics in correct detection of a place in challenging environments and presents a semantics aided visual place recognition method. Semantics being invariant to viewpoint changes and dynamic environment can improve the overall performance of the place matching method. The proposed method is evaluated on the two benchmark datasets with dynamic environment and seasonal changes. Experimental results show the improved performance of the visual place recognition method for vSLAM.
Abstract
In visual simultaneous localization and mapping (vSLAM), the correct recognition of a place benefits in relocalization and improved map accuracy. However, its performance is significantly affected by the environmental conditions such as variation in light, viewpoints, seasons, and presence of dynamic objects. This research addresses the problem of feature occlusion caused by interference of dynamic objects leading to the poor performance of visual place recognition algorithm. To overcome the aforementioned problem, this research analyzes the role of scene semantics in correct detection of a place in challenging environments and presents a semantics aided visual place recognition method. Semantics being invariant to viewpoint changes and dynamic environment can improve the overall performance of the place matching method. The proposed method is evaluated on the two benchmark datasets with dynamic environment and seasonal changes. Experimental results show the improved performance of the visual place recognition method for vSLAM.
참고문헌 (19)
- M. Cummins, "Appearance-only SLAM at large scale with FAB-MAP 2. 0", The International Journal of Robotics Research, 30(9), pp.1100~1123 (2011)[DOI]
- E. Pepperell, "All-environment visual place recognition with SMART", 2014 IEEE International Conference on Robotics and Automation (ICRA) (2014)
- P. Neubert, "Appearance change prediction for long-term navigation across seasons", 2013European Conference on Mobile Robots (2013)
- P. Corke, "Dealing with shadows : Capturing intrinsic scene appearance for image-based outdoor localisation", 2013 IEEE, 2013, ~
- C. McManus, "Shady dealings : Robust, long-term visual localisation using illumination invariance", 2014 IEEE International Conference on Robotics and Automation (ICRA) (2014)
- Z. Chen, "Convolutional Neural Network-based Place Recognition", 16th Australasian Conference on Robotics and Automation 2014 (2014)
- R. Arandjelovic, "NetVLAD : CNN Architecture for Weakly Supervised Place Recognition", IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 40(6) (2018)
- T. -H. Wang, "Omnidirectional CNN for Visual Place Recognition and Navigation", 2018 IEEE International Conference on Robotics and Automation (ICRA) (2018)
- B. Chen, "Loop Closure Detection Based on Multi-Scale Deep Feature Fusion", Applied Sciences, 9(6) (2019)[DOI]
- "Semantic Image Based Geolocation Given a Map" (2016)[URL]
- Y. Hou, "Use of Roadway Scene Semantic Information and Geometry-Preserving Landmark Pairs to Improve Visual Place Recognition in Changing Environments", IEEE Access, 5, pp.7702~7713 (2017)[DOI]
- T. Naseer, "Semanticsaware visual localization under challenging perceptual conditions", 2017 IEEE International Conference on Robotics and Automation (ICRA) (2017)
- H. Xu, "A Loop Closure Detection Algorithm in Dynamic Scene", International Conference on Computer, Communication and Network Technology (CCNT 2018) (2018)
- "LoST? Appearance-Invariant Place Recognition for Opposite Viewpoints using Visual Semantics" (2018)[URL]
- Peng Wu, "A novel fusing semantic- and appearance-based descriptors for visual loop closure detection", Optik, 243, pp.167230~ (2021), Elsevier BV[DOI]
- Baifan Chen, "Hierarchical Visual Place Recognition Based on Semantic-Aggregation", Applied Sciences, 11(20), pp.9540~ (2021), MDPI AG[DOI]
- G. Singh, "Hierarchical Loop Closure Detection for Long-term Visual SLAM with Semantic-Geometric Descriptors", 2021 IEEE International Intelligent Transportation Systems Conference (ITSC) (2021)
- Zhian Yuan, "SVG-Loop: Semantic–Visual–Geometric Information-Based Loop Closure Detection", Remote Sensing, 13(17), pp.3520~ (2021), MDPI AG[DOI]
- G. Lin, "RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation", 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)