RGB-TIR 특징 혼합을 활용한 조도 변화에 강건한 장소 인식 기법
Robust Place Recognition Using RGB-TIR Feature Fusion against Illumination Chang
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
본 연구는 자율주행 및 로봇 시스템에서의 시각적 장소 인식(Visual Place Recognition, VPR) 성능을 개선하기 위해 열적외선(Thermal Infrared, TIR) 데이터를 융합하는 새로운 방법론을 제안한다. 제안된 방법론은 Late Fusion 방식을 채택하여, MobileNetV3를 기반으로 각 센서로부터특징을 추출한 후, MixVPR 네트워크를 통해 두 데이터 정보를 결합한다. 실험 결과, 제안된방법론은 기존 방법론들과 비교하여 정량, 정성적인 평가에서 우수한 성능을 보였으며, 특히조도 변화에 따른 성능 저하를 효과적으로 극복할 수 있음을 검증하였다. 이러한 성과는 자율주행 차량과 로봇 시스템에서 동시적 위치 추정 및 지도 작성(SLAM) 기술의 신뢰성을 높이는데 기여할 수 있을 것으로 기대된다.
Abstract
This study proposes a novel approach to enhance Visual Place Recognition (VPR) performance in autonomous driving and robotic systems by integrating Thermal Infrared (TIR) data. The proposed method employs a Late Fusion strategy, extracting features from each sensor using a MobileNetV3- based network and then combining features through the MixVPR network. Experimental results demonstrate that the proposed method outperforms existing approaches in both quantitative and qualitative evaluations, effectively mitigating performance degradation due to the illuminance variations. These findings are expected to contribute to improving the reliability of Simultaneous Localization and Mapping (SLAM) technology in autonomous vehicles and robotic systems.
참고문헌 (17)
- Ali-Bey, A., "Mixvpr: Feature mixing for visual place recognition", Proceedings of the IEEE, 2023, 2998~3007
- Arandjelovic, R., "NetVLAD: CNN architecture for weakly supervised place recognition", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.5297~5307 (2016)
- Berton, G., "Deep visual geo-localization benchmark", Proceedings of the IEEE, 2022, 5396~5407
- Chang, J. U., "Thermal imagery-based object detection algorithm for low-light level nighttime surveillance system", The Journal of The Korea Institute of Intelligent Transportation Systems, 19(3), pp.129~136 (2020)
- Feng, D., "Deep multi-modal object detection and semantic segmentation for autonomous driving : Datasets, methods, and challenges", IEEE Transactions on Intelligent Transportation Systems, 22(3), pp.1341~1360 (2020)
- Gil, H., "Fieldscale : Locality-aware field-based adaptive rescaling for thermal infrared image", IEEE Robotics and Automation Letters, 9(7), pp.6424~6431 (2024)
- Howard, A., "Searching for mobilenetv3", Proceedings of the IEEE, 2019, 1314~1324
- Jiang, J., "Thermal-inertial SLAM for the environments with challenging illumination", IEEE Robotics and Automation Letters, 7(4), pp.8767~8774 (2022)
- Jung, Y. S., "Class 1·3 vehicle classification using deep learning and thermal image", The Journal of The Korea Institute of Intelligent Transportation Systems, 19(6), pp.96~106 (2020)
- Keetha, N., "Anyloc : Towards universal visual place recognition", IEEE Robotics and Automation Letters, 9(2), pp.1286~1293 (2023)
- Oertel, A., "Augmenting visual place recognition with structural cues", IEEE Robotics and Automation Letters, 5(4), pp.5534~5541 (2020)
- Qin, L., "BVT-SLAM : A binocular visible-thermal sensors SLAM System in low-light environments", IEEE Sensors Journal, 24(7), pp.11599~11609 (2023)
- Radenović, F., "Fine-tuning CNN image retrieval with no human annotation", IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(7), pp.1655~1668 (2018)
- Saputra, M. R. U., "Graph-based thermal-inertial SLAM with probabilistic neural networks", IEEE Transactions on Robotics, 38(3), pp.1875~1893 (2021)
- Vidas, S., "Hand-held monocular slam in thermal-infrared", 2012 12th International Conference on Control Automation Robotics & Vision (ICARCV), pp.859~864 (2012)
- Wang, Y., "Sgfnet : Semantic-guided fusion network for rgb-thermal semantic segmentation", IEEE Transactions on Circuits and Systems for Video Technology, 33(12), pp.7737~7748 (2023)
- Yun, S., "Sthereo:Stereo thermal dataset for research in odometry and mapping", 2022 IEEE, 2022, 3857~3864