Integration of YOLO detection algorithm with trajectory prediction of pedestrians for advanced driver assistance system

• Autorzy: Budzani Sebastian , Szwedka Mateusz

Identyfikatory

DOI

10.15199/48.2024.12.12

Warianty tytułu

PL

Integracja algorytmu detekcji YOLO z przewidywaniem trajektorii ruchu pieszego dla zaawansowanego systemu wspomagania kierowcy

• Języki publikacji: EN

Abstrakty

EN

The article explores the potential of integrating the YOLOv3 detection algorithm with trajectory prediction in ADAS systems. It presents the concept and analyzes the effectiveness of this combination in various driving scenarios. Additionally, it discusses practical implementation aspects and suggests directions for the development of this solution for advanced driver assistance systems.

PL

W artykule zaprezentowano potencjał integracyjny algorytmu detekcji YOLO w wersji 3 z predykcja˛ trajektorii w systemach ADAS. Przedstawia on koncepcję oraz analizę efektywności tego połączenia w różnych warunkach drogowych. Ponadto omawia praktyczne aspekty implementacji i sugeruje kierunki rozwoju tego rozwiązania dla zaawansowanych systemów wspomagania kierowcy.

Słowa kluczowe

EN

pedestrian detection; trajectory prediction; ADAS; YOLO

PL

detekcja pieszych; predykcja trajekorii; ADAS; YOLO

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2024
• Tom: R. 100, nr 12
• Strony: 53--58
• Opis fizyczny: Bibliogr. 29 poz., rys., tab.

Twórcy

autor

Budzani Sebastian

• Silesian University of Technology, ul. Akademicka 16, 44-100 Gliwice

autor

Szwedka Mateusz

• Silesian University of Technology, ul. Akademicka 16, 44-100 Gliwice

Bibliografia

• [1] Global status report on road safety 2023 https://www.who.int/publications/i/item/ /9789240086517/, [Accessed on 27.06.2024]
• [2] Roja Ezzati Amini, Kui Yang, Constantinos Antoniou: Development of a conflict risk evaluation model to assess pedestrian safety in interaction with vehicles, Accident Analysis & Prevention, 175 106773, 2022.
• [3] Sharma N., Dhiman C., Indu S.: Pedestrian intention prediction for autonomous vehicles: A comprehensive survey, Neurocomputing, 508 pp. 120–152, 2022.
• [4] Rasouli A., Kotseruba I., Tsotsos J.K.: Are They Going to Cross? A Benchmark Dataset and Baseline for Pedestrian Crosswalk Behavior, 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), Venice, Italy, pp. 206– 213, 2017.
• [5] Fang Z., López A.M.: Is the Pedestrian going to Cross? Answering by 2D Pose Estimation, 2018 IEEE Intelligent Vehicles Symposium (IV), Changshu, China, pp. 1271–1276, 2017.
• [6] Wu H., Wang L., Zheng S., Xu Q. Wang J.: Crossing-Road Pedestrian Trajectory Prediction Based on Intention and Behavior Identification, 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC), Rhodes, Greece, pp. 1–16, 2020.
• [7] Sung K.: Pedestrian Positioning Using an Enhanced Ensemble Transform Kalman Filter, Sensors, 23(15):6870, 2023.
• [8] Marginean, A.; Brehar, R.; Negru, M.: Understanding pedestrian behaviour with pose estimation and recurrent networks, In Proceedings of the 2019 6th International Symposium on Electrical and Electronics Engineering (ISEEE), Galati, Romania, pp 1–6, 2019.
• [9] Lorenzo J., Parra I., Wirth F., Stiller C., Llorca D.F., Sotelo M.A.: RNN-based Pedestrian Crossing Prediction using Activity and Pose-related Features, 2020 IEEE Intelligent Vehicles Symposium (IV), Las Vegas, NV, USA, pp 1801–1806, 2020.
• [10] Gesnouin J., Pechberti S., Bresson G., Stanciulescu B., Moutarde F.: Predicting intentions of pedestrians from 2d skeletal pose sequences with a representation–focused multi– branch deep learning network, Algorithms, 13(12) pp. 1–23, 2020.
• [11] Ezzati Amini R., Dhamaniya A., Antoniou C.: Towards a Game Theoretic Approach to Model Pedestrian Road Crossings, Transportation Research Procedia, 52 pp 692–699, 2021.
• [12] Song X., Kang M., Zhou S., Wang J., Mao Y., Zheng N.: Pedestrian Intention Prediction Based on Traffic-Aware Scene Graph Model, 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Kyoto, Japan, pp 9851– 9858, 2022.
• [13] Surasak T., Takahiro I., Cheng C. -h., Wang C. -e., Sheng P. -y.: Histogram of oriented gradients for human detection in video, 5th International Conference on Business and Industrial Research (ICBIR), Bangkok, Thailand, pp 172–176, 2018.
• [14] Saqib M., Khan S. D., Sharma N., Blumenstein M.: Person Head Detection in Multiple Scales Using Deep Convolutional Neural Networks, 2018 International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, Brazil, pp 1–7, 2018.
• [15] Zhang Y., Lin J.: Research on pedestrian occlusion detection based on SSD algorithm, In Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI ’19). Association for Computing Machinery, New York, NY, USA, pp 417–421, 2019.
• [16] Wu Y., Chen C. Wang B.: Pedestrian Detection Based on Improved SSD Object Detection Algorithm, 2022 International Conference on Networking and Network Applications (NaNA), Urumqi, China, pp 550–555, 2022.
• [17] Zhong J., Sun H., CaoW., He Z.: Pedestrian Motion Trajectory Prediction With Stereo-Based 3D Deep Pose Estimation and Trajectory Learning, IEEE Access, 8, pp 23480–23486, 2020.
• [18] Lin, C.-Y.; Kau, L.-J.; Chan, C.-Y: Bimodal Extended Kalman Filter-Based Pedestrian Trajectory Prediction, Sensors, 22(8231), 2022.
• [19] Quan R., Zhu L., Wu Y., Yang Y.: Holistic LSTM for Pedestrian Trajectory Prediction, IEEE Transactions on Image Processing, 30, pp 3229–3239, 2022.
• [20] Korbmacher R., Tordeux A.: Review of Pedestrian Trajectory Prediction Methods: Comparing Deep Learning and Knowledge-Based Approaches, IEEE Transactions on Intelligent Transportation Systems, 23(12), pp 24126–24144, 2022.
• [21] Bengar, J.Z., Gonzalez-Garcia, A., Villalonga, G., Raducanu, B., Aghdam, H.H., Mozerov, M.G., López, A.M., Weijer, J.V.: Temporal Coherence for Active Learning in Videos, 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), pp. 914–923, 2019.
• [22] SYNTHIA: The SYNTHetic collection of Imagery and Annotations, Universitat Autònoma de Barcelona, [web page] http://synthia-dataset.net/table-classes/, [Accessed on 29.05.2024]
• [23] Xupeng Kou, Shuaijun Liu, Kaiqiang Cheng, Ye Qian Development of a YOLO-V3-based model for detecting defects on steel strip surface Measurement, Volume 182, 3pp, September 2021, 109454
• [24] Redmon J., Farhadi A., YOLOv3: An Incremental Improvement, Washington University, 2018
• [25] Redmon J., Divvala S., Girschick R., Farhadi A., You Only Look Once: Unified, Real-Time Object Detection University of Washington, 2016
• [26] Pearson Correlation and Linear Regression http://sites.utexas.edu/sos/guided/inferential /numeric/bivariate/cor/, [Accessed on 06.06.2024]
• [27] Zwillinger D., Kokoska S., CRC Standard Probability and Statistics Tables and Formulae. Chapman and Hall: New York., 2000, Section 14.7
• [28] Maurice G. Kendall, Rank Correlation Methods (4th Edition), Charles Griffin and Co., 1970.
• [29] Timothy C. Urdan, Statistics in Plain English - 4th Edition, Routledge, New York, 2016

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki i promocja sportu (2025).