Robust Pedestrian Tracking in Crowd Scenarios Using an Adaptive GMM-based Framework

In this paper, we address the issue of pedestrian tracking in crowd scenarios. People in close social relationships tend to act as a group which is a great challenge to individually discriminate and track pedestrians on a LiDAR system. In this paper, we integrally model groups of people and track them in a recursive framework based on Gaussian Mixture Model (GMM). The model is optimized by an extended Expectation-Maximization (EM) algorithm which can adaptively vary the number of mixture components over scans. Experimental results both qualitatively and quantitatively indicate the reliability and accuracy of our tracker in populated scenarios.

[1]  J. Munkres.  ALGORITHMS FOR THE ASSIGNMENT AND TRANSIORTATION tROBLEMS* , 1957 .

[2]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.

[3]  Azriel Rosenfeld,et al.  Tracking Groups of People , 2000, Comput. Vis. Image Underst..

[4]  Rainer Stiefelhagen,et al.  Multiple Object Tracking Performance Metrics and Evaluation in a Smart Room Environment , 2006 .

[5]  Wolfram Burgard,et al.  Multiple Hypothesis Tracking of Clusters of People , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[6]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[7]  Ulrike von Luxburg,et al.  A tutorial on spectral clustering , 2007, Stat. Comput..

[8]  Dirk Wollherr,et al.  A clustering method for efficient segmentation of 3D laser data , 2008, 2008 IEEE International Conference on Robotics and Automation.

[9]  Fawzi Nashashibi,et al.  Fast algorithm for pedestrian and group of pedestrians detection using a laser scanner , 2009, 2009 IEEE Intelligent Vehicles Symposium.

[10]  Sebastian Thrun,et al.  Model based vehicle detection and tracking for autonomous urban driving , 2009, Auton. Robots.

[11]  Wolfram Burgard,et al.  Tracking groups of people with a multi-model hypothesis tracker , 2009, 2009 IEEE International Conference on Robotics and Automation.

[12]  Roland Siegwart,et al.  A Layered Approach to People Detection in 3D Range Data , 2010, AAAI.

[13]  Joel A. Hesch,et al.  Tracking People with a 360-Degree Lidar , 2010, 2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance.

[14]  Radu Horaud,et al.  Rigid and Articulated Point Registration with Expectation Conditional Maximization , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Paul Newman,et al.  What could move? Finding cars, pedestrians and bicyclists in 3D laser data , 2012, 2012 IEEE International Conference on Robotics and Automation.

[16]  B. V. K. Vijaya Kumar,et al.  A multi-sensor fusion system for moving object detection and tracking in urban driving environments , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[17]  Bin Dai,et al.  Gaussian-Process-Based Real-Time Ground Segmentation for Autonomous Land Vehicles , 2013, Journal of Intelligent & Robotic Systems.

[18]  Anurag Mittal,et al.  Co-operative Pedestrians Group Tracking in Crowded Scenes Using an MST Approach , 2015, 2015 IEEE Winter Conference on Applications of Computer Vision.

[19]  Paul Newman,et al.  Model-free detection and tracking of dynamic objects with 2D lidar , 2015, Int. J. Robotics Res..

[20]  Alberto Del Bimbo,et al.  MuseumVisitors: A dataset for pedestrian and group detection, gaze estimation and behavior understanding , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[21]  Jean-Charles Noyer,et al.  A Model-Based Joint Detection and Tracking Approach for Multi-Vehicle Tracking With Lidar Sensor , 2015, IEEE Transactions on Intelligent Transportation Systems.

[22]  Wolfram Burgard,et al.  Motion-based detection and tracking in 3D LiDAR scans , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[23]  Silvio Savarese,et al.  A Probabilistic Framework for Real-time 3D Segmentation using Spatial, Temporal, and Semantic Cues , 2016, Robotics: Science and Systems.

[24]  Cyrill Stachniss,et al.  Fast range image-based segmentation of sparse 3D laser scans for online operation , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[25]  Shinpei Kato,et al.  Precise and efficient model-based vehicle tracking method using Rao-Blackwellized and scaling series particle filters , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[26]  Bo Zhang,et al.  Group LSTM: Group Trajectory Prediction in Crowded Scenarios , 2018, ECCV Workshops.

[27]  Jianhao Jiao,et al.  Automatic Calibration of Multiple 3D LiDARs in Urban Environments , 2019, 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[28]  Nanning Zheng,et al.  SR-LSTM: State Refinement for LSTM Towards Pedestrian Trajectory Prediction , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  Dinesh Manocha,et al.  DensePeds: Pedestrian Tracking in Dense Crowds Using Front-RVO and Sparse Features , 2019, 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[30]  Steven L. Waslander,et al.  Improving 3D Object Detection for Pedestrians with Virtual Multi-View Synthesis Orientation Estimation , 2019, 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[31]  Qiang Xu,et al.  nuScenes: A Multimodal Dataset for Autonomous Driving , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).