Study on a Monocular Camera-based Unmanned Vehicle Position Estimation Technique

doi:10.15683/kosdi.2026.3.31.091

All Issue

2026 Vol.22, Issue 1 Preview Page Next Page

Original Article

Study on a Monocular Camera-based Unmanned Vehicle Position Estimation Technique 단안 카메라 기반 무인 이동체 위치 추정 기법 연구: 서용빈¹ㆍ주준호²ㆍ손초³ㆍ김영억⁴*
Yongbin Seo¹, Junhao Zhou², Chao Sun³, Youngok Kim⁴*; ¹Master Course, Department of Electronic Engineering, Kwangwoon University, Seoul, Republic of Korea
²Ph.D Course, Department of Electronic Engineering, Kwangwoon University, Seoul, Republic of Korea
³Ph.D, Department of Electronic Engineering, Kwangwoon University, Seoul, Republic of Korea
⁴Professor, Department of Electronic Engineering, Kwangwoon University, Seoul, Republic of Korea

31 March 2026. pp. 91-104

PDF

Abstract

Purpose: This study proposes a monocular camera-based precise position estimation technique for unmanned vehicles that can solve the problems of data sparsity and nonlinearity of pixel coordinates and achieve accurate predictions. Method: Using a small motorized vehicle as a target, we define eight movement trajectory scenarios in indoor and outdoor environments and extract position, velocity, and angle information at eight time points. Time-series data augmentation is applied to the LSTM Seq2Seg model and a composite loss function are utilized to simultaneously predict positions at all eight time points. Result: The proposed technique was evaluated based on Ground Sampling Distance, and achieved high prediction performance with a MAE of 2.59 cm and a MSE of 3.21 cm. Conclusion: This study proposed a precise position estimation technique for unmanned vehicles based on a monocular camera, and confirmed the precise prediction performance through experiments.

Keywords

Disaster

Unmanned Vehicle

Monocular Camera

Deep Learning

Position Estimation

연구목적: 본 연구는 소규모 시계열 데이터 세트 환경에서 발생하는 데이터 희소성 및 픽셀 좌표의 비선형성 문제를 해결하고, 최종 위치 오차를 감소시키기 위한 복합 손실 함수를 통해 정확한 예측을 할 수 있는 단안 카메라 기반 무인 이동체 정밀 위치 추정 기법을 제안하고자 한다. 연구방법: 차량을 모방한 소형 모터카를 목표물로 활용하여 실내외 환경에서 8번의 이동 궤적 시나리오를 정의하고, 1초 간격의 8개 시점 위치, 속도, 각도 정보를 추출한다. 모델의 강건성을 위해 시계열 데이터 증강을 적용하였으며, LSTM Sequence-to-Sequence (Seq2Seg) 모델 및 최종 위치 오차를 감소시키기 위한 복합 손실 함수를 활용하여 전체 8개 시점의 위치를 동시에 예측한다. 연구결과: 제안된 기법은 Ground Sampling Distance 기반 물리적 단위계 환산으로 성능을 평가하였으며 전체 시나리오에 대해 평균 절대오차 2.59cm, 평균 제곱 오차 3.21cm으로 높은 예측 성능을 달성하였다. 결론: 본 연구는 단안 카메라에 기반 한 미래 시점 위치 예측을 위해 설계된 전처리 과정과 LSTM Seq2Seq 모델을 기반으로 무인 이동체의 정밀 위치 추정 기법을 제안하였고, 실험을 통해 정밀한 예측 성능을 확인하였다. 제안된 기법은 단안 카메라만으로도 재난 현장이나 군사 작전 등에 투입되는 무인 이동체의 위치 추정에 활용될 것으로 기대된다.

키워드

재난

무인이동체

단안 카메라

딥러닝

위치 예측

References

Chen, G., Cao, H., Conradt, J., Tang, H., Rohrbein, F., Knoll, A. (2020). “Event-based neuromorphic vision for autonomous driving: A paradigm shift for bio-inspired visual sensing and perception.” IEEE Signal Processing Magazine, Vol. 37, No. 4, pp. 34-49. 10.1109/MSP.2020.2985815
Girma, A., Bahadori, N., Sarkar, M., Tadewos, T.G., Behnia, M.R., Mahmoud, M.N. (2020). “IoT-enabled autonomous system collaboration for disaster-area management.” IEEE/CAA Journal of Automatica Sinica, Vol. 7, No. 5, pp. 1249-1262. 10.1109/JAS.2020.1003291
Huang, H., Guan, B., Shang, Y., Yu, Q. (2025). “3D trajectory reconstruction of moving points based on a monocular camera.” Measurement, Vol. 256, No. Part B, 118136. 10.1016/j.measurement.2025.118136
Kim, S.H., Kim, S.J., Kim, J. (2025). “Impact of spatial resolution of topographic data on inundation analysis in urban streams: A case study of the Geum-Hak Cheon area.” Journal of the Korean Society of Disaster Information, Vol. 21, No. 1, pp. 283-293.
Marconi, L., Melchiorri, C., Beetz, M., Pangercic, D., Siegwart, R., Leutenegger, S., Carloni, R., Stramigioli, S., Bruyninckx, H., Doherty, P., Kleiner, A., Lippiello, V., Finzi, A., Siciliano, B., Sala, A., Tomatis, N. (2012). “The SHERPA project: Smart collaboration between humans and ground-aerial robots for improving rescuing activities in alpine environments.” Proceedings of the IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), College Station, TX, US, pp. 1-4. 10.1109/SSRR.2012.6523905
Nguyen, T., Crismer, A., De Cubber, G., Janssens, B., Bruyninckx, H. (2024). “Landing UAV on moving surface vehicles: Visual tracking and motion prediction of landing decks.” Proceedings of the IEEE/SICE International Symposium on System Integration (SII), Ha Long, Vietnam, pp. 827-833. 10.1109/SII58957.2024.10417303
Park, J.-W., Park, O.-N. (2025). “A study on safety measures for construction vehicles using sensor-based smart systems: Focusing on dump trucks.” Journal of the Korean Society of Disaster Information, Vol. 21, No. 1, pp. 128-136.
Wang, Y., Chen, W., Luan, T.H., Su, Z., Xu, Q., Li, R., Chen, N. (2022). “Task offloading for post-disaster rescue in unmanned aerial vehicle networks.” IEEE/ACM Transactions on Networking, Vol. 30, No. 4, pp. 1525-1539. 10.1109/TNET.2022.3140796
Yang, Z., Kang, X., Li, S., Zhao, C., Zhang, J., Gong, Y. (2022). “Study on the Trajectory positioning and prediction framework for unmanned aerial vehicles based on long short-term memory neural networks.” Proceedings of the International Conference on Big Data and Information Analytics (BigDIA), Guiyang, China, pp. 205-212. 10.1109/BigDIA56350.2022.9874109
Yokoyama, K., Morioka, K. (2020). “Autonomous mobile robot with a simple navigation system based on deep reinforcement learning and a monocular camera.” Proceedings of the IEEE/SICE International Symposium on System Integration (SII), Honolulu, HI, US, pp. 525-530. 10.1109/SII46433.2020.9025987
Zhou, T., Liang, P., Zhang, Z., Dai, Z., Li, G., Guo, H. (2023). “Research on fire protection systems based on deep learning.” Proceedings of the International Conference on Robotics, Automation and Intelligent Control (ICRAIC), Zhangjiajie, China, pp. 362-367. 10.1109/ICRAIC61978.2023.00069
Zhu, H., Claramunt, F.M., Brito, B., Alonso-Mora, J. (2021). “Learning interaction-aware trajectory predictions for decentralized multi-robot motion planning in dynamic environments.” IEEE Robotics and Automation Letters, Vol. 6, No. 2, pp. 2256-2263. 10.1109/LRA.2021.3061073

Information

Publisher :The Korean Society of Disaster Information
Publisher(Ko) :한국재난정보학회
Journal Title :Journal of the Society of Disaster Information
Journal Title(Ko) :한국재난정보학회논문집
Volume : 22
No :1
Pages :91-104
DOI :https://doi.org/10.15683/kosdi.2026.3.31.091

[1] Chen, G., Cao, H., Conradt, J., Tang, H., Rohrbein, F., Knoll, A. (2020). “Event-based neuromorphic vision for autonomous driving: A paradigm shift for bio-inspired visual sensing and perception.” IEEE Signal Processing Magazine, Vol. 37, No. 4, pp. 34-49. 10.1109/MSP.2020.2985815

[2] Girma, A., Bahadori, N., Sarkar, M., Tadewos, T.G., Behnia, M.R., Mahmoud, M.N. (2020). “IoT-enabled autonomous system collaboration for disaster-area management.” IEEE/CAA Journal of Automatica Sinica, Vol. 7, No. 5, pp. 1249-1262. 10.1109/JAS.2020.1003291

[3] Huang, H., Guan, B., Shang, Y., Yu, Q. (2025). “3D trajectory reconstruction of moving points based on a monocular camera.” Measurement, Vol. 256, No. Part B, 118136. 10.1016/j.measurement.2025.118136

[4] Kim, S.H., Kim, S.J., Kim, J. (2025). “Impact of spatial resolution of topographic data on inundation analysis in urban streams: A case study of the Geum-Hak Cheon area.” Journal of the Korean Society of Disaster Information, Vol. 21, No. 1, pp. 283-293.

[5] Marconi, L., Melchiorri, C., Beetz, M., Pangercic, D., Siegwart, R., Leutenegger, S., Carloni, R., Stramigioli, S., Bruyninckx, H., Doherty, P., Kleiner, A., Lippiello, V., Finzi, A., Siciliano, B., Sala, A., Tomatis, N. (2012). “The SHERPA project: Smart collaboration between humans and ground-aerial robots for improving rescuing activities in alpine environments.” Proceedings of the IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), College Station, TX, US, pp. 1-4. 10.1109/SSRR.2012.6523905

[6] Nguyen, T., Crismer, A., De Cubber, G., Janssens, B., Bruyninckx, H. (2024). “Landing UAV on moving surface vehicles: Visual tracking and motion prediction of landing decks.” Proceedings of the IEEE/SICE International Symposium on System Integration (SII), Ha Long, Vietnam, pp. 827-833. 10.1109/SII58957.2024.10417303

[7] Park, J.-W., Park, O.-N. (2025). “A study on safety measures for construction vehicles using sensor-based smart systems: Focusing on dump trucks.” Journal of the Korean Society of Disaster Information, Vol. 21, No. 1, pp. 128-136.

[8] Wang, Y., Chen, W., Luan, T.H., Su, Z., Xu, Q., Li, R., Chen, N. (2022). “Task offloading for post-disaster rescue in unmanned aerial vehicle networks.” IEEE/ACM Transactions on Networking, Vol. 30, No. 4, pp. 1525-1539. 10.1109/TNET.2022.3140796

[9] Yang, Z., Kang, X., Li, S., Zhao, C., Zhang, J., Gong, Y. (2022). “Study on the Trajectory positioning and prediction framework for unmanned aerial vehicles based on long short-term memory neural networks.” Proceedings of the International Conference on Big Data and Information Analytics (BigDIA), Guiyang, China, pp. 205-212. 10.1109/BigDIA56350.2022.9874109

[10] Yokoyama, K., Morioka, K. (2020). “Autonomous mobile robot with a simple navigation system based on deep reinforcement learning and a monocular camera.” Proceedings of the IEEE/SICE International Symposium on System Integration (SII), Honolulu, HI, US, pp. 525-530. 10.1109/SII46433.2020.9025987

[11] Zhou, T., Liang, P., Zhang, Z., Dai, Z., Li, G., Guo, H. (2023). “Research on fire protection systems based on deep learning.” Proceedings of the International Conference on Robotics, Automation and Intelligent Control (ICRAIC), Zhangjiajie, China, pp. 362-367. 10.1109/ICRAIC61978.2023.00069

[12] Zhu, H., Claramunt, F.M., Brito, B., Alonso-Mora, J. (2021). “Learning interaction-aware trajectory predictions for decentralized multi-robot motion planning in dynamic environments.” IEEE Robotics and Automation Letters, Vol. 6, No. 2, pp. 2256-2263. 10.1109/LRA.2021.3061073

Journal of the Society of Disaster Information ISSN:1976-2208(Print) 2671-5287(Online) 한국재난정보학회논문집

All Issue