Leonid Antsfeld
Boris Chidlovskii
ABSTRACT
Modern smartphones are equipped with built-in magnetometers that capture disturbances of the Earth's magnetic field induced by ferromagnetic objects. In indoor environment, using magnetic field data turns to be a strong alternative to conventional localization techniques as requiring no special infrastructure. We revise the state of the art methods based on landmark classification [5] and propose a novel approach. We represent magnetic data time series as image sequences and compose multi-channel input to a deep neural network. We use four methods, Recurrence plots, Gramian Angular Fields and Markov Transition Fields, to capture different patterns in magnetic data stream. We complete the landmark-based classification with deep regression on the user's position and combine convolutional and recurrent layers in the deep network. We evaluate our methods on the recently published MagPie dataset [3] and show that they outperform the state of the art methods.
- Imran Ashraf, Soojung Hur, and Yongwan Park. Enhancing performance of magnetic field based indoor localization using magnetic patterns from multiple smartphones. Sensors, 20(9):2704, 2020.Google Scholar
Cross Ref
- Fuqiang Gu, Xuke Hu, Milad Ramezani, Debaditya Acharya, Kourosh Khoshelham, Shahrokh Valaee, and Jianga Shang. Indoor localization improved by spatial context --- a survey. ACM Comput. Surv., 52(3):64:1--64:35, July 2019.Google ScholarDigital Library
- David Hanley, Alexander B. Faustino, Scott D. Zelman, David A. Degenhardt, and Timothy Bretl. MagPIE: a dataset for indoor positioning with magnetic anomalies. Intern. Conf. Indoor Positioning and Indoor Navigation (IPIN), pages 1--8, 2017.Google ScholarCross Ref
- S. Khoshrou, J.S. Cardoso, and L.F. Teixeira. Learning from evolving video streams in a multi-camera scenario. Machine Learning, 100:609--633, 2015.Google ScholarDigital Library
- Namkyoung Lee, Sumin Ahn, and Dongsoo Han. AMID: accurate magnetic indoor localization using deep learning. Sensors, 18(5):1598, 2018.Google ScholarCross Ref
- Zhiguang Wang and Tim Oates. Imaging time-series to improve classification and imputation. Proc. IJCAI, pages 3939--3945, 2015.Google Scholar
Index Terms
Magnetic sensor based indoor positioning by multi-channel deep regression: poster abstract
Recommendations
Accurate and Low-cost Mobile Indoor Localization with 2-D Magnetic Fingerprints
CrowdSenSys '17: Proceedings of the First ACM Workshop on Mobile Crowdsensing Systems and ApplicationsIndoor localization is particularly valuable in many indoor application scenarios, such as shopping malls and airports. An indoor localization system on smartphones should be low-power as well as accurate. In this paper, we present Turnin - a completely ...
A Polygonal Method for Ranging-Based Localization in an Indoor Wireless Sensor Network
In this paper, we propose an indoor localization method in a wireless sensor network based on IEEE 802.15.4 specification. The proposed method follows a ranging-based approach using not only the measurements of received signal strength (RSS) but also ...
A sensor based indoor localization through fingerprinting
Fingerprint based localization mostly considers to exploit existing infrastructure (APs or FM broadcast) to avoid hardware requirement and deployment cost. On the other hand these solutions confine them with such fixed infrastructures without having any ...
Comments