열화상 영상의 Image Translation을 통한 Pseudo-RGB 기반 장소 인식 시스템
Pseudo-RGB-based Place Recognition through Thermal-to-RGB Image Translation
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Many studies have been conducted to ensure that Visual Place Recognition is reliable in various environments, including edge cases. However, existing approaches use visible imaging sensors, RGB cameras, which are greatly influenced by illumination changes, as is widely known. Thus, in this paper, we use an invisible imaging sensor, a long wave length infrared camera (LWIR) instead of RGB, that is shown to be more reliable in low-light and highly noisy conditions. In addition, although the camera sensor used to solve this problem is an LWIR camera, but since the thermal image is converted into RGB image the proposed method is highly compatible with existing algorithms and databases. We demonstrate that the proposed method outperforms the baseline method by about 0.19 for recall performance.
Abstract
Many studies have been conducted to ensure that Visual Place Recognition is reliable in various environments, including edge cases. However, existing approaches use visible imaging sensors, RGB cameras, which are greatly influenced by illumination changes, as is widely known. Thus, in this paper, we use an invisible imaging sensor, a long wave length infrared camera (LWIR) instead of RGB, that is shown to be more reliable in low-light and highly noisy conditions. In addition, although the camera sensor used to solve this problem is an LWIR camera, but since the thermal image is converted into RGB image the proposed method is highly compatible with existing algorithms and databases. We demonstrate that the proposed method outperforms the baseline method by about 0.19 for recall performance.
참고문헌 (15)
- Faheem Zafari, "A Survey of Indoor Localization Systems and Technologies", IEEE Communications Surveys & Tutorials, 21(3), pp.2568~2599 (2019), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Sampo Kuutti, "A Survey of the State-of-the-Art Localization Techniques and Their Potentials for Autonomous Vehicle Applications", IEEE Internet of Things Journal, 5(2), pp.829~846 (2018), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Xiwu Zhang, "Visual place recognition: A survey from deep learning perspective", Pattern Recognition, 113, pp.107760~ (2021), Elsevier BV[DOI]
- Relja Arandjelovic, "NetVLAD: CNN Architecture for Weakly Supervised Place Recognition", 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016), IEEE
- Gabriele Berton, "Rethinking Visual Geo-localization for Large-Scale Applications", 2022 IEEE, 2022, ~[DOI]
- Akihiko Torii, "24", 7 place recognition by view synthesis, 2015 (2015), ~[DOI]
- Janghun Hyeon, "Pose Correction for Highly Accurate Visual Localization in Large-scale Indoor Spaces", 2021 IEEE, 2021, ~[DOI]
- Egor Ershov, "NTIRE 2022 Challenge on Night Photography Rendering", 2022 IEEE, 2022, ~[DOI]
- Tayyab Naseer, "Robust Visual Localization Across Seasons", IEEE Transactions on Robotics, 34(2), pp.289~302 (2018), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Asha Anoosheh, "Night-to-Day Image Translation for Retrieval-based Localization", 2019 International Conference on Robotics and Automation (ICRA) (2019), IEEE
- V. Tsagaris, "Fusion of visible and infrared imagery for night color vision", Displays, 26(4-5), pp.191~196 (2005), Elsevier BV[DOI]
- Daechan Han, "Multispectral Domain Invariant Image for Retrieval-based Place Recognition", 2020 IEEE International Conference on Robotics and Automation (ICRA) (2020), IEEE
- Y. Yuan, "Hrformer: High-resolution vision transformer for dense predict", Advances in Neural Information Processing Systems 34(NeurIPS 2021) (2021)
- Yukyung Choi, "KAIST Multi-Spectral Day", Night Data Set for Autonomous and Assisted Driving, 2018, pp.19(3), 934~948[DOI]
- D. Hendrycks, "Benchmarking neural network robustness to common corruptions and perturbations", Machine Learning (2019)[DOI]