머신러닝 기반 다중운집 인파 밀집도 예측 및 실시간 위치 추적 시스템 개발
Development of Machine Learning Based Crowd Density Estimation and Real Time Location Tracking System on Mass Gatherings
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
다중운집 지역에서 인파 과밀로 인한 사고를 방지하기 위해서는 실시간으로 인파 밀집도를 예측하고 위치를 추적하는 기술이 매우 중요하다. 본 논문에서는 실내 환경에서 수집되는 다양한 센싱 정보를 기반으로 실내 인파의 밀집도 및 위치를 추적하고, 이를 모니터링 하는 시스템을 제안한다. 제안하는 시스템은 무선 WiFi 신호 세기 및 카메라 영상을 입력으로, 핑거프린트 위치 추정 및 객체 탐지 기법을 적용하여 실시간 사용자 위치를 예측한다. 또한, 구역별 밀집도를 계산하기 위해 모니터링 대상 공간을 일정 크기의 구역으로 나눈 뒤 각 구역에 체류하는 예측 된 인파의 수를 카운트한다. 본 연구는 웹 기반의 통합 모니터링 플랫폼을 제안하며, 이를 통해 구역별 밀집도 및 실시간 인파 위치의 통합 모니터링이 가능하다. 제안하는 시스템의 효용성을 검증하기 위해 실 환경에서 테스트 및 검증을 수행했다. 실험 결과, 제안하는 시스템은 실시간 사용자 위치를 정확하게 예측할 수 있으며, 실내 과밀 상황 발생 시 신속하게 탐지 및 모니터링을 수행하고 해당 사용자에게 통지할 수 있음을 확인했다.
Abstract
In order to prevent accidents due to overcrowding on mass gatherings, it is crucial to predict and track crowd density in real-time. This paper proposes a system for tracking and monitoring indoor crowd density and their locations based on diverse sensing information collected in indoor environments. The proposed system leverages wireless WiFi signal strength and camera images as input, applying fingerprint location estimation and object detection techniques to predict real-time user locations. The monitored space is divided into predefined-size zones, and the predicted crowd count in each zone is used to calculate the density. A web-based integrated monitoring platform is developed to integrate monitoring of zone-specific density and real-time crowd location estimation. To validate the effectiveness of the proposed system, empirical tests and verifications were conducted in a real environment. The experimental results confirm that the proposed system can accurately predict real-time user locations, promptly detect and monitor overcrowding situations indoors, and notify the relevant users when necessary.
참고문헌 (31)
- "Korea population density"[URL]
- "Urbanized areas population density"[URL]
- "INFOWORKS, FMCW 4D LiDAR, disaster and safety technology project won a contract"[URL]
- "‘Human’ recognition even if only head is visible on CCTV...Dense analysis technology with increased accuracy"[URL]
- "DAINS, Artificial intelligence ensures safety in crowded and crowded environments"[URL]
- B. Li, "Approaches on crowd counting and density estimation : a review", Pattern Analysis and Applications, 24, pp.853~874 (2021)
- D. Y. Kim, "Design of safety sensor system for autonomous mobile robot in crowded space", Information and Control Symposium, pp.41~42 (2019)
- Y.-J. Roh, "The crowd density estimation using pedestrian depth information", Proc. Korea Information Processing Society, 30(2), pp.705~708 (2023)
- Subburaman, "Counting people in the crowd using a generic head detector", IEEE 9th International Conference on Advanced Video and Signal-Based Surveillance (AVSS), pp.470~475 (2012)
- Y.-L. Hou, "People counting and human detection in a challenging situation", IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans, 41(1), pp.24~33 (2010)
- X. Liu, "Leveraging unlabeled data for crowd counting by learning to rank", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.7661~7669 (2018)
- D. B. Sam, "Almost unsupervised learning for dense crowd counting", Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 33(1), pp.8868~8875 (2019)
- Y. Yuan, "Crowd density estimation using wireless sensor networks", IEEE 7th International Conference on Mobile Ad-hoc and Sensor Networks (MSN), pp.138~145 (2011)
- G. -W. Yeom, "A study on the improvement of the safety management of crowd accidents in the Itaewon disaster", Legal Theory & Practice Review, 11(4), pp.273~292 (2023)
- "Raspberry Pi Camera Module 2"[URL]
- "COCO Dataset"[URL]
- J. Redmon, "You only look once: Unified, real-time object detection", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.779~788 (2016)
- "YOLO v5"[URL]
- "Pretrained Checkpoints, YOLO v5"[URL]
- D. Dluznevskij, "Investigation of YOLOv5efficiency in iPhone supported systems", Baltic J. Modern Computing, 9(3), pp.333~344 (2021)
- "Raspberry Pi 3 Model B+"[URL]
- "Raspberry Pi 4"[URL]
- E. Perahia, "Gigabit wireless LANs : an overview of IEEE 802. 11 ac and 802. 11 ad", ACM SIGMOBILE Mobile Computing and Communications Review, 15(3), pp.23~33 (2011)
- X. Zhu, "Indoor intelligent fingerprintbased localization : principles, approaches and challenges", IEEE Communications Surveys & Tutorials, 22(4), pp.2634~2657 (2020)
- Ansari, Israfil, "Recognition of car manufacturers using faster R-CNN and perspective transformation", Journal of Korea Multimedia Society, 21(8), pp.888~896 (2018)
- B. Ezhumalai, "An efficient indoor positioning method based on Wi-Fi RSS fingerprint and classification algorithm", Sensors, 21(10), pp.1~19 (2021)
- R. Girshick, "Rich feature hierarchies for accurate object detection and semantic segmentation", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.580~587 (2014)
- J. Dai, "R-FCN: Object detection via region-based fully convolutional networks", Advances in Neural Information Processing Systems (NeurIPS), pp.2016~ (2016)
- "Geometric image transformations"[URL]
- Y. Xie, "An improved k-nearestneighbor indoor localization method based on Spearman distance", IEEE Signal Processing Letters, 23(3), pp.351~355 (2016)
- J. Niu, "ZIL : An energy-efficient indoor localization system using ZigBee radio to detect WiFi fingerprints", IEEE Journal on Selected Areas in Communications, 33(7), pp.1431~1442 (2015)