Journal of the Korea Society of Computer and Information (한국컴퓨터정보학회논문지)

Korean Society of Computer Information (한국컴퓨터정보학회)
권호 표지
DOI QR코드

DOI QR Code

Localization of Mobile Users with the Improved Kalman Filter Algorithm using Smart Traffic Lights in Self-driving Environments

  • Jung, Ju-Ho (Computer Information Technology, Korea National University of Transportation) ;
  • Song, Jung-Eun (Computer Information Technology, Korea National University of Transportation) ;
  • Ahn, Jun-Ho (Computer Information Technology, Korea National University of Transportation)
  • Received : 2019.03.08
  • Accepted : 2019.04.30
  • Published : 2019.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

The self-driving cars identify appropriate navigation paths and obstacles to arrive at their destinations without human control. The autonomous cars are capable of sensing driving environments to improve driver and pedestrian safety by sharing with neighbor traffic infrastructure. In this paper, we have focused on pedestrian protection and have designed an improved localization algorithm to track mobile users on roads by interacting with smart traffic lights in vehicle environments. We developed smart traffic lights with the RSSI sensor and built the proposed method by improving the Kalman filter algorithm to localize mobile users accurately. We successfully evaluated the proposed algorithm to improve the mobile user localization with deployed five smart traffic lights.

Keywords

CPTSCQ_2019_v24n5_67_f0001.png 이미지

Fig. 1. Using Smart Traffic Lights in Experiment

CPTSCQ_2019_v24n5_67_f0002.png 이미지

Fig. 2. Photo inside the Smart Traffic Lights Hardware

CPTSCQ_2019_v24n5_67_f0003.png 이미지

Fig. 3. Smart Traffic Lights Hardware Architecture

CPTSCQ_2019_v24n5_67_f0004.png 이미지

Fig. 4. Change in RSSI value by distance

CPTSCQ_2019_v24n5_67_f0005.png 이미지

Fig. 5. Comparison of RSSI values such as 3 smart signalson the same line

CPTSCQ_2019_v24n5_67_f0006.png 이미지

Fig. 6. State Chart Diagram for Proposed Algorithm

CPTSCQ_2019_v24n5_67_f0007.png 이미지

Fig. 7. Mobile Application for RSSI Detection

CPTSCQ_2019_v24n5_67_f0008.png 이미지

Fig. 8. Experiment Scenario

CPTSCQ_2019_v24n5_67_f0009.png 이미지

Fig. 9. Experiment Environment

CPTSCQ_2019_v24n5_67_f0010.png 이미지

Fig. 10. Scenario 1: Tracking the location of amotionless mobile users

CPTSCQ_2019_v24n5_67_f0011.png 이미지

Fig. 13. Scenario 2: Tracking the location of mobile users

CPTSCQ_2019_v24n5_67_f0012.png 이미지

Fig. 14. The proposed algorithm of the moving person relative position not applied

CPTSCQ_2019_v24n5_67_f0013.png 이미지

Fig. 15. The proposed algorithm of the moving person Applied relative position

CPTSCQ_2019_v24n5_67_f0014.png 이미지

Fig. 11. The proposed algorithm of a person without motion Applied relative position

CPTSCQ_2019_v24n5_67_f0015.png 이미지

Fig. 12. The proposed algorithm of a person with motion Applied relative position

References

  1. Forbes, "Uber Self-Driving Car Crash: What Really Happened", May 2018. https://www.forbes.com/sites/ meriameberboucha/2018/05/28/uber-self-driving-car -crash-what-really-happened/#35ec95a54dc4
  2. The Seattle Times, "Don't be a 'smombie': Pay attention crossing the street", December 2017. https://www.seattletimes.com/opinion/dont-be-a-smombie-pay-attention -crossing-the-street/
  3. Puneet Kohli, Anjali Chadha, "Enabling Pedestrian Safety using Computer Vision Techniques: A Case Study of the 2018 Uber Inc. Self-driving Car Crash", arXiv:1805. 11815, May 2018
  4. Jinkyu Kim, Hyunggi Cho, Myung Hwangbo, Jaehyung Choi, John Canny, Youngwook Paul Kwon, "Deep Traffic Light Detection for Self-driving Cars from a Large-scale Dataset", 2018 21st International Conference on Intelligent Transportation Systems (ITSC), Nov 2018, DOI: 10.1109/ITSC.2018.8569575
  5. Kiwoong Jung, Pedro B. V. Bermudez, HyeonCheol Hwang, YongGuk Oh, Jaeho Kwak, "Passenger's location estimation using Kalman Filter for Beacon fare collection in a Wireless Low Floor Tram", 2018 International Conference on Electronics, Information, and Communication (ICEIC), Jan 2018, DOI: 10.23919/ELIN FOCOM.2018.8330712
  6. Yapeng Wang, Xu Yang, Yutian Zhao, Yue Liu, Laurie Cuthbert, "Bluetooth positioning using RSSI and triangulation methods", 2013 IEEE 10th Consumer Communications and Networking Conference (CCNC), Jan 2013, DOI: 10.1109/CCNC.2013.6488558
  7. W. Bulten, A. C. V. Rossum and W. F. G. Haselager, "Human SLAM, Indoor Localisation of Devices and Users," 2016 IEEE First International Conference on Internet-of-Things Design and Implementation (IoTDI), Berlin, 2016, pp. 211-222. doi: 10.1109/IoTDI.2015.19
  8. Yang-Su Kim, Beakcheol Jang, "Analysis of Bluetooth Indoor Localization Technologies and Experiment of Correlation between RSSI and Distance", Journal of The Korea Society of Computer and Information, Vol. 21 No. 10, pp. 55-62, October 2016, https://doi.org/10.9708/jksci.2016.21.10.055
  9. Jeong Hyun Yoon, Inah Chung, Ye Hoon Lee, "Location Estimation Technique in Bluetooth Beacon Based Indoor Positioning Systems", ICGHIT 2018, pp 41-44, DOI: https://doi.org/10.1007/978-981-13-0311-1_8
  10. Wen-Ching Chena, Kuo-Fong Kaoa, Yung-Tsang Changa, Chih-Hung Chang, "An RSSI-based Distributed Real-time Indoor Positioning Framework", 2018 IEEE International Conference on Applied System Invention (ICASI), April 2018, DOI: 10.1109/ICASI.2018.8394528
  11. Dhouha El Houssaini, Zina Mohamed, Sabrine Khriji, Kamel Besbes, Olfa Kanoun, "A Filtered RSSI Model based on HardwareCharacteristic for Localization Algorithm inWireless Sensor Networks", 2018 32nd International Conference on Advanced Information Networking and Applications Workshops, May 2018, doi: 10.1109/WAINA.2018.00073
  12. Smart traffic lights for pedestrian safety, Chungcheong Information and Communication Co. and imobi Co.

Cited by

  1. 국내 환경에 적합한 Kalman-filter 기반 사용자 운동거리 측정 알고리즘 설계 및 구현 vol.23, pp.12, 2019, https://doi.org/10.6109/jkiice.2019.23.12.1624