본문 바로가기
KERD
논문KCI 등재

횡단보도 보행자 인지 향상을 위한 ByteTrack 기반 다중객체추적

ByteTrack-Based Multi-Object Tracking for Recognition of Pedestrian in Crosswalk

이유진|이상민|노유진
한국물류과학기술학회 (The Society of Logistics Science and Technology)|2022.12|물류과학기술연구 (Journal of Logistics Science & Technology)|제3권 제2호|pp. 56-77|DOI 10.23178/jlst.3.2.202212.004

0

조회

0

다운로드

0

인용

0

참고문헌

키워드

.
주제분류과학기술학

초록

.

Abstract

According to traffic accident statistics, 42% of traffic accidents between 2017 and 2021 were crossing accidents. To reduce these accidents, the research on the collision avoidance assistance for pedestrian safety is in the spotlight in machine learning field. However, there are few studies to improve the accuracy of recognizing the crossing multiple pedestrians and estimating the residual time to the crossing. We here propose using hybrid approach combining Yolo-X and ByteTrack to obtain the accurate detector of pedestrians. We gathered the actual data set of the pedestrian crossing for the accurate multi-pedestrian tracking model. The proposed approach can detect and track the crossing pedestrians in real time. Furthermore, we can estimate the pedestrian’s walking direction, speed, acceleration, and distance to the crosswalk for inferring the motion of pedestrians entering the crosswalk. The experimental results present that the proposed approach outperforms the alternatives in terms of tracking accuracy and computation cost.

참고문헌 (48)

  1. Akhauri, S., "Enhanced transfer learning for autonomous driving with systematic accident simulation", 2020 IEEE, 2020, 5986~5993[DOI]
  2. Almalioglu, Y., "Deep learning-based robust positioning for all-weather autonomous driving", Nature Machine Intelligence, pp.1~12 (2022)
  3. Al-Qizwini, M., "Deep learning algorithm for autonomous driving using googlenet", 2017 IEEE Intelligent Vehicles Symposium (IV), pp.89~96 (2017), IEEE
  4. Althoff, M., "Model-based probabilistic collision detection in autonomous driving", IEEE Transactions on Intelligent Transportation Systems, 10(2), pp.299~310 (2009)
  5. Bernardin, K., "Multiple object tracking performance metrics and evaluation in a smart room environment", Sixth IEEE International Workshop on Visual Surveillance, in conjunction with ECCV, 90(91) (2006), Citeseer
  6. Bochinski, E., "High-speed tracking-by-detection without using image information", 2017 14th IEEE international conference on advanced video and signal based surveillance (AVSS), pp.1~6 (2017), IEEE
  7. Chen, N., "Zebra crossing recognition method based on edge feature and Hough transform", Journal of Zhejiang University of science and technology, 31(6), pp.476~483 (2019)
  8. Cho, M. G., "A study on the obstacle recognition for autonomous driving RC car using lidar and thermal infrared camera", 2019 Eleventh International Conference on Ubiquitous and Future Networks (ICUFN), pp.544~546 (2019), IEEE
  9. Chu, K., "Local path planning for off-road autonomous driving with avoidance of static obstacles", IEEE transactions on intelligent transportation systems, 13(4), pp.1599~1616 (2012)
  10. Dendorfer, P., "Mot20 : A benchmark for multi object tracking in crowded scenes", arXiv preprint arXiv:2003.09003, ~ (2020)
  11. Ess, A., "A mobile vision system for robust multi-person tracking", 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp.1~8 (2008), IEEE
  12. Farag, W., "Traffic signs identification by deep learning for autonomous driving", Smart Cities Symposium 2018, pp.1~6 (2018), IET
  13. Ge, Z., "Yolox: Exceeding yolo series in 2021", arXiv preprint arXiv:2107.08430, ~ (2021)
  14. Girshick, R., "Rich feature hierarchies for accurate object detection and semantic segmentation", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.580~587 (2014)
  15. Grigorescu, S., "A survey of deep learning techniques for autonomous driving", Journal of Field Robotics, 37(3), pp.362~386 (2020)
  16. He, K., "Deep residual learning for image recognition", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.770~778 (2016)
  17. Jin, Y., "Data Analysis for Sensor Fusion of AVM Camera and Automotive Radar", Korean Society of Automotive Engineers Spring Conference, pp.581~583 (2018)
  18. 김도영, "자율주행차의 물류산업 적용에 관한 연구: 물류 허브 변화를 중심으로", 한국SCM학회지, 18(2), pp.81~90 (2018), 한국SCM학회[DOI]
  19. Kim, T., "Logistics Sorting System using Autonomous Driving Robot", Journal of The Korea Soceity of Computer and Information, 29(2), pp.491~492 (2021)
  20. Krizhevsky, A., "Imagenet classification with deep convolutional neural networks", Communications of the ACM, 60(6), pp.84~90 (2017)
  21. Kwon, T. W., "Diagnostic performance of artificial intelligence model for pneumonia from chest radiography", Plos one, 16(4), pp.e0249399~ (2021)[DOI]
  22. LeCun, Y., "Gradient-based learning applied to document recognition", Proceedings of the IEEE, 86(11), pp.2278~2324 (1998)
  23. Lee, S., "A Study on the Collision Avoidance Algorithm Using FMCWRadar", Proceedings of the Korean Telecommunications Society Conference, pp.668~669 (2021)
  24. Li, G., "A deep learning based image enhancement approach for autonomous driving at night", Knowledge-Based Systems, 213, pp.106617~ (2021)
  25. Luiten, J., "Hota : Ahigher order metric for evaluating multi-object tracking", International journal of computer vision, 129(2), pp.548~578 (2021)
  26. "Pedestrian Dataset" (2017)[URL]
  27. Milan, A., "MOT16 : A benchmark for multi-object tracking", arXiv preprint arXiv:1603.00831, ~ (2016)
  28. Noh, S., "Collision avoidance in on-road environment for autonomous driving", 2014 14th International Conference on Control, Automation and Systems (ICCAS 2014), pp.884~889 (2014), IEEE
  29. Okuyama, T., "Autonomous driving system based on deep q learnig", 2018 International conference on intelligent autonomous systems (ICoIAS), pp.201~205 (2018), IEEE
  30. Pak, A., "CARNet: A Dynamic Autoencoder for Learning Latent Dynamics in Autonomous Driving Tasks", arXiv preprint arXiv:2205.08712, ~ (2022)
  31. 박상미, "물류환경에서 집품 작업자를 위한 추종형 무인운반차 디자인 프로세스 개발 및 검증", 로지스틱스연구, 28(5), pp.11~26 (2020), 한국로지스틱스학회[DOI]
  32. Park, Y., "Development of complexity index and predictions of accident risks for mixed autonomous driving levels", 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp.1181~1188 (2018), IEEE
  33. Prabhakar, G., "Obstacle detection and classification using deep learning for tracking in high-speed autonomous driving", 2017 IEEE region 10symposium (TENSYMP), pp.1~6 (2017), IEEE
  34. Redmon, J., "You only look once: Unified, real-time object detection", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.779~788 (2016)
  35. Ristani, E., "Performance measures and a data set for multi-target, multi-camera tracking", European conference on computer vision, pp.17~35 (2016), Springer
  36. Shalev-Shwartz, S., "Safe, multi-agent, reinforcement learning for autonomous driving", arXiv preprint arXiv:1610.03295, ~ (2016)
  37. Simonyan, K., "Very deep convolutional networks for large-scale image recognition", arXiv preprint arXiv:1409.1556, ~ (2014)
  38. Szegedy, C., "Going deeper with convolutions", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.1~9 (2015)
  39. "Traffic Accidents by Accident Type" (2021)[URL]
  40. Uddin, M. S., "Detection of pedestrian crossing using bipolarity feature-an image-based technique", IEEE Transactions on Intelligent transportation systems, 6(4), pp.439~445 (2005)
  41. Wang, Z., "Towards real-time multi-object tracking", European Conference on Computer Vision, pp.107~122 (2020), Springer
  42. 웨이치, "컨테이너 터미널에 적용 가능한 인더스트리 4.0 기반 제품", 서비스의 개념 설계 및 중요성 분석, 2018, pp.26(3), 91~110[DOI]
  43. Xu, S., "PP-YOLOE : An evolved version of YOLO", arXiv preprint arXiv:2203.16250, ~ (2022)
  44. Y. Hashimoto, "Probability estimation for pedestrian crossing intention at signalized crosswalks", 2015 IEEE International Conference on Vehicular Electronics and Safety (ICVES), pp.114~119 (2015)
  45. Zeng, F., "Motr: End-to-end multiple-object tracking with transformer", arXiv preprint arXiv:2105.03247, ~ (2021)
  46. Zhang, Y., "Bytetrack:Multi-object tracking by associating every detection box", arXiv preprint arXiv:2110.06864, ~ (2021)
  47. Zhang, Y., "Fairmot : On the fairness of detection and re-identification in multiple object tracking", International Journal of Computer Vision, 129(11), pp.3069~3087 (2021)
  48. Zhang, Z. D., "CDNet: a real-time and robust crosswalk detection network on Jetson nano based on YOLOv5", Neural Computing and Applications, pp.1~12 (2022)

관련 논문AI추천

HigherHRNet 기반의 발추정 기법을 통한 횡단보도 보행자 인식이현, 정경민, 한주훈대한임베디드공학회 · 대한임베디드공학회논문지2021 · 제16권 제5호객체탐지를 이용한 캠퍼스내 교통안전 시스템 개발이건, 양인범, 우지영, 이나영, 이민섭, 홍윤정한국컴퓨터정보학회 · 한국컴퓨터정보학회논문지2024 · 제29권 제1호A Tracking-by-Detection System for Pedestrian Tracking Using Deep Learning Technique and Color Information김상훈, MAI THANH NHAT TRUONG한국정보처리학회 · JIPS(Journal of Information Processing Systems)2019 · 제15권 제4호Refinement Module 기반 Three-Scale 보행자 검출 기법이현, 박수용, 정경민대한임베디드공학회 · 대한임베디드공학회논문지2023 · 제18권 제5호국내 도로 환경에 특화된 자율주행을 위한 멀티카메라 데이터 셋 구축 및 유효성 검증권순, 김제석, 박재형, 이재근, 이진희대한임베디드공학회 · 대한임베디드공학회논문지2022 · 제17권 제5호YOLOv5와 모션벡터를 활용한트램-보행자 충돌 예측 방법 연구김영민, 김진평, 안현욱, 장규진, 전희균, 황현철한국정보처리학회 · 정보처리학회 논문지2021 · 제10권 제12호

이 간행물의 다른 논문 (4건)

정시배송가능 시간대(time window) 제시를 위한 다중정류소(multi-depot) 다회전(multi-trip) 차량경로문제: 온라인 할당 및 오프라인 재할당 접근법채준재, 정동진, 이기주pp. 1-17UAM과 드론을 사용한 도시물류상의 선택적 이중구조 오리엔티어링 문제차형주, 김동균, 정태수pp. 18-35추가학습이 불필요한 이미지 특징 유사도 기반 상품 식별 시스템장병탁, 유영재, 박예솔, 김준오, 윤혜정pp. 36-55도시철도 물류 시스템의 통합관제시스템 설계 및 수평이송장치 경로 생성 알고리즘 연구황선우, 최준우, 김주욱, 한수민, 장경호, 박상원, 김영민pp. 78-93
원문 보기