Pedestrian Flows Characterization and Estimation with Computer Vision Techniques

This work describes a straightforward implementation of detecting and tracking pedestrian walking across a public square using computer vision. The methodology consists of the use of the well-known YOLOv3 algorithm over videos recorded during different days of the week. The chosen location was the Piazza Duca d’Aosta in the city of Milan, Italy, in front of the main Centrale railway station, an access point for the subway. Several analyses have been carried out to investigate macroscopic parameters of pedestrian dynamics such as densities, speeds, and main directions followed by pedestrians, as well as testing strengths and weaknesses of computer-vision algorithms for pedestrian detection. The developed system was able to represent spatial densities and speeds of pedestrians along temporal profiles. Considering the whole observation period, the mean value of the Voronoi density was about 0.035 person/m2 with a standard deviation of about 0.014 person/m2. On the other hand, two main speed clusters were identified during morning/evening hours. The largest number of pedestrians with an average speed of about 0.77 m/s was observed along the exit direction of the subway entrances during both morning and evening hours. The second relevant group of pedestrians was observed walking in the opposite direction with an average speed of about 0.65 m/s. The analyses generated initial insights into the future development of a decision-support system to help with the management and control of pedestrian dynamics.

[1]  G. Valenti,et al.  Pedestrian analysis for crowd monitoring: the Milan case study (Italy) , 2023, 2023 8th International Conference on Models and Technologies for Intelligent Transportation Systems (MT-ITS).

[2]  Dan Jiao,et al.  Pedestrian walking speed monitoring at street scale by an in-flight drone , 2023, PeerJ Comput. Sci..

[3]  Y. Zou,et al.  Operation analysis of freeway mixed traffic flow based on catch-up coordination platoon. , 2022, Accident; analysis and prevention.

[4]  Upesh Nepal,et al.  Comparing YOLOv3, YOLOv4 and YOLOv5 for Autonomous Landing Spot Detection in Faulty UAVs , 2022, Sensors.

[5]  Eric Marchand,et al.  Tracking Pedestrian Heads in Dense Crowd , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Chien-Yao Wang,et al.  Scaled-YOLOv4: Scaling Cross Stage Partial Network , 2020, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Livia Mannini,et al.  Simulation framework for pedestrian dynamics: modelling and calibration , 2020, IET Intelligent Transport Systems.

[8]  Tomasz Szandała.  Review and Comparison of Commonly Used Activation Functions for Deep Neural Networks , 2020, Studies in Computational Intelligence.

[9]  Hong-Yuan Mark Liao,et al.  YOLOv4: Optimal Speed and Accuracy of Object Detection , 2020, ArXiv.

[10]  Jieping Ye,et al.  Object Detection in 20 Years: A Survey , 2019, Proceedings of the IEEE.

[11]  Cláudio T. Silva,et al.  A New Approach for Pedestrian Density Estimation Using Moving Sensors and Computer Vision , 2018, ACM Trans. Spatial Algorithms Syst..

[12]  Joseph Redmon,et al.  YOLOv3: An Incremental Improvement , 2018, ArXiv.

[13]  Yoshua Bengio,et al.  Residual Connections Encourage Iterative Inference , 2017, ICLR.

[14]  Kaiming He,et al.  Focal Loss for Dense Object Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[15]  Brian McWilliams,et al.  The Shattered Gradients Problem: If resnets are the answer, then what is the question? , 2017, ICML.

[16]  Xiaogang Wang,et al.  T-CNN: Tubelets With Convolutional Neural Networks for Object Detection From Videos , 2016, IEEE Transactions on Circuits and Systems for Video Technology.

[17]  Qi Wu,et al.  Image Captioning and Visual Question Answering Based on Attributes and External Knowledge , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Stefan Roth,et al.  MOT16: A Benchmark for Multi-Object Tracking , 2016, ArXiv.

[19]  Fabio Tozeto Ramos,et al.  Simple online and realtime tracking , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[20]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Hilmi Berk Celikoglu,et al.  Otoyol Trafik Akım Koşullarını Sınıflamada K-Ortalamalar Kümeleme Yöntemi , 2014 .

[23]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[24]  A. Seyfried,et al.  Methods for measuring pedestrian density, flow, speed and direction with minimal scatter , 2009, 0911.2165.

[25]  Rainer Stiefelhagen,et al.  Evaluating Multiple Object Tracking Performance: The CLEAR MOT Metrics , 2008, EURASIP J. Image Video Process..

[26]  Hubert Rehborn,et al.  Recognition and tracking of spatial–temporal congested traffic patterns on freeways , 2004 .

[27]  Geoffrey E. Hinton,et al.  Deep Learning , 2015 .

[28]  David J. Fleet,et al.  Computer Vision – ECCV 2014 , 2014, Lecture Notes in Computer Science.

[29]  T. Sayed,et al.  Automated Collection of Pedestrian Data Using Computer Vision Techniques , 2009 .

[30]  R. E. Kalman,et al.  A New Approach to Linear Filtering and Prediction Problems , 2002 .

[31]  Heng-Da Cheng,et al.  MEASUREMENT OF PEDESTRIAN FLOW DATA USING IMAGE ANALYSIS TECHNIQUES , 1990 .

[32]  Integrating pedestrian simulation , tracking and event detection for crowd analysis , 2022 .