UAV-based monitoring of pedestrian groups

Similar documents
#19 MONITORING AND PREDICTING PEDESTRIAN BEHAVIOR USING TRAFFIC CAMERAS

Exploration of design solutions for the enhancement of crowd safety

Predicting Human Behavior from Public Cameras with Convolutional Neural Networks

Trial 3: Interactions Between Autonomous Vehicles and Pedestrians and Cyclists

(Supplementary) Investigation Waves in a Ripple Tank

Pedestrian Dynamics: Models of Pedestrian Behaviour

Recognition of Tennis Strokes using Key Postures

Real Time Bicycle Simulation Study of Bicyclists Behaviors and their Implication on Safety

AutonoVi-Sim: Modular Autonomous Vehicle Simulation Platform Supporting Diverse Vehicle Models, Sensor Configuration, and Traffic Conditions

Figure 1. Results of the Application of Blob Entering Detection Techniques.

MODELING OF THE INFLOW BEHAVIOR OF EVACUATING CROWD INTO A STAIRWAY

Emergency Rides. Driving Simulators Research Development Production. 1. General. Rev

ROUNDABOUT CAPACITY: THE UK EMPIRICAL METHODOLOGY

Cricket umpire assistance and ball tracking system using a single smartphone camera

PEDESTRIAN behavior modeling and analysis is

arxiv: v1 [cs.ma] 22 Nov 2017

Unmanned Aerial Vehicle Failure Modes Algorithm Modeling

Drift indication for helicopter approach and landing

Traffic Engineering Research Centre Department of Civil and Environmental Engineering, NTNU

MoPac South: Impact on Cesar Chavez Street and the Downtown Network

Analysis of Movement

Models for Pedestrian Behavior

HOW DO ELDERLY PEDESTRIANS PERCEIVE HAZARDS IN THE STREET?

Design of a Pedestrian Detection System Based on OpenCV. Ning Xu and Yong Ren*

A STUDY ON GAP-ACCEPTANCE OF UNSIGNALIZED INTERSECTION UNDER MIXED TRAFFIC CONDITIONS

THe rip currents are very fast moving narrow channels,

WALKING MOTION ANALYSIS USING SMALL ACCELERATION SENSORS

Procedures for Off-Nominal Cases: Three Closely Spaced Parallel Runway Operations

Walking with coffee: when and why coffee spills

Integrated Pedestrian Simulation in VISSIM

Aalborg Universitet. Publication date: Document Version Accepted author manuscript, peer reviewed version

Seismic Survey Designs for Converted Waves

New Technology used in sports. By:- ABKASH AGARWAL REGD NO BRANCH CSE(A)

Sensing and Modeling of Terrain Features using Crawling Robots

The Importance of Mina site within Mecca urban cover change between 1998 and 2013

A hybrid and multiscale approach to model and simulate mobility in the context of public event

Dynamic Network Behavior of Offshore Wind Parks

EVACUATION SIMULATION FOR DISABLED PEOPLE IN PASSENGER SHIP

Online Companion to Using Simulation to Help Manage the Pace of Play in Golf

Open Research Online The Open University s repository of research publications and other research outputs

Deformable Convolutional Networks

A STUDY OF SIMULATION MODEL FOR PEDESTRIAN MOVEMENT WITH EVACUATION AND QUEUING

Title: Modeling Crossing Behavior of Drivers and Pedestrians at Uncontrolled Intersections and Mid-block Crossings

The Next ITF topology TRIGO?

Scaling up of ADAS Traffic Impacts to German Cities

CSE 190a Project Report: Golf Club Head Tracking

Concurrent Monitoring, Analysis, and Visualization of Freeway and Arterial Performance for Recurring and Non-recurring Congestion

AN APPROACH FOR ASSESSMENT OF WEAVING LENGTH FOR MID-BLOCK TRAFFIC OPERATIONS

Small Footprint Topo-Bathymetric LiDAR

THE EFFECTS OF LEAD-VEHICLE SIZE ON DRIVER FOLLOWING BEHAVIOR: IS IGNORANCE TRULY BLISS?

Assessing the Traffic and Energy Impacts of Connected and Automated Vehicles (CAVs)

Anatomy of a Homer. Purpose. Required Equipment/Supplies. Optional Equipment/Supplies. Discussion

Welcome. Background. Goals. Vision

MWGen: A Mini World Generator

How do we design for pedestrians? Case study: transforming the Walworth Road

Investigating the Bubble Behavior in Pool Boiling in Microgravity Conditions Thilanka Munasinghe, Member, IAENG

Petacat: Applying ideas from Copycat to image understanding

Welcome to Step Outside with Togo & Nogo a road safety training resource for year 2 children

Pedestrian Mobility in Theme Park Disasters

Chapter 6. Analysis of the framework with FARS Dataset

Active Pedestrian Safety: from Research to Reality

Sea and Land Breezes METR 4433, Mesoscale Meteorology Spring 2006 (some of the material in this section came from ZMAG)

Variables influencing lane changing behaviour of heavy vehicles

WildCat RF unit (0.5W), full 32-byte transmissions with built-in checksum

Search Techniques. Contents

Designing a Traffic Circle By David Bosworth For MATH 714

GEA FOR ADVANCED STRUCTURAL DYNAMIC ANALYSIS

Pedestrian, Bicycle and Traffic Calming Strategic Implementation Plan. January 18, 2011

Titelbild. Höhe: 13cm Breite: 21 cm

IEEE RAS Micro/Nano Robotics & Automation (MNRA) Technical Committee Mobile Microrobotics Challenge 2016

Jamming phenomena of self-driven particles

Traffic circles. February 9, 2009

Object Recognition. Selim Aksoy. Bilkent University

ENHANCED PARKWAY STUDY: PHASE 2 CONTINUOUS FLOW INTERSECTIONS. Final Report

Pedestrian Project List and Prioritization

Roundabout Design 101: Roundabout Capacity Issues

Advanced PMA Capabilities for MCM

Artificial Intelligence for the EChO Mission Scheduler

Pedestrian Behaviour Modelling

JPEG-Compatibility Steganalysis Using Block-Histogram of Recompression Artifacts

REPRESENTATION OF HUMAN GAIT TRAJECTORY THROUGH TEMPOROSPATIAL IMAGE MODELLING

Figure 2: Principle of GPVS and ILIDS.

Section 1 Types of Waves

Challenges in determining water surface in airborne LiDAR topobathymetry. Amar Nayegandhi, Dewberry 15 th Annual JALBTCX Workshop, June 11 th 2014

Using sensory feedback to improve locomotion performance of the salamander robot in different environments

A PHASE-AMPLITUDE ITERATION SCHEME FOR THE OPTIMIZATION OF DETERMINISTIC WAVE SEQUENCES

CS 4649/7649 Robot Intelligence: Planning

Emergency Door Capacity: Influence of Door Width, Population Composition and Stress Level

Large-Scale Bicycle Flow Experiment: Setup and Implementation

An Assessment of FlowRound for Signalised Roundabout Design.

Evaluation of the depth camera based SLAM algorithms

Investigation of Quasi-detonation Propagation Using Simultaneous Soot Foil and Schlieren Photography

Video recording setup

Section 1 Types of Waves. Distinguish between mechanical waves and electromagnetic waves.

AUSTRIAN RISK ANALYSIS FOR ROAD TUNNELS Development of a new Method for the Risk Assessment of Road Tunnels

An Investigation of Dynamic Soaring and its Applications to the Albatross and RC Sailplanes

Semi-automatic tracking of beach volleyball players

Prediction of Nearshore Waves and Currents: Model Sensitivity, Confidence and Assimilation

The Application of Pedestrian Microscopic Simulation Technology in Researching the Influenced Realm around Urban Rail Transit Station

Meeting Summary Public Information Meeting #1 Warren County Pathway Corridor Project September 27, 2018

Transcription:

UAV-based monitoring of pedestrian groups Florian Burkert, Friedrich Fraundorfer Technische Universität München, 04.09.2013, UAV-g 2013, Rostock 1

Motivation 2

Overview State of the art UAV imagery for pedestrian group behaviour Scenario planning and data acquisition Pre-processing and dataset Group behaviour model of the complex event detector (CED) Experimental results Discussion 3

State of the art Classification of recurring individual trajectories [Nascimento et al, 2010] Recognition of pairwise human interaction [Oliver et al., 2000] Unusual event detection in pedestrian groups [Mehran et al., 2009] * 1 Recognition of motion patterns in dense crowds [Rodriguez et al., 2011] *² Only a few pedestrians analyzed Recurring events crucial for learning No classification of the situation in a crowd * 1 http://mha.cs.umn.edu/movies/crowd-activity-all.avi *² http://www.di.ens.fr/willow/research/datadriven/ 4

State of the art Goal: Complex event detection in public scenes Perfect birds-eye visibility provided by UAV imagery Contribution: Interpretation of pedestrian group behaviour in unknown scenes Declaration of the specific type of event New UAV test dataset 5

Overview State of the art UAV imagery for pedestrian group behaviour Scenario planning and data acquisition Pre-processing and dataset Group behaviour model of the complex event detector (CED) Experimental results Discussion 6

UAV dataset planning Composition of scenarios Goal: Representation of possible situations in pedestrian crowds Input: - Research on Social Force Model [Helbing] - Everyday life experience - Media showing pedestrian crowds 7

UAV dataset planning Composition of scenarios Goal: Representation of possible situations in pedestrian crowds Input: - Research on Social Force Model [Helbing] - Everyday life experience - Media showing pedestrian crowds Volunteers Simulating predefined scenarios Minimal information provided natural behaviour Material UAV: Battery life + recharging Marking of volunteers Physical obstacles 8

UAV dataset data acquisition Location: pitch in Munich UAV: AscTec Falcon 8 + Panasonic DMC Lumix LX3 Altitude ~85m ~1,5cm ground resolution, coverage 48x27m ROI: 25x25m; Size of pedestrian: 30x45 pixels Flight sessions of 12 minutes 9

UAV dataset pre-processing Image alignment Homography-based transformation using SIFT correspondences Manual pedestrian tracking Trajectories 10

UAV dataset pre-processing Image alignment Homography-based transformation using SIFT correspondences Manual pedestrian tracking Trajectories 11

UAV dataset pre-processing Image alignment Homography-based transformation using SIFT correspondences Manual pedestrian tracking Trajectories 12

UAV dataset Name norm. pace fast pace #sequ. normal #sequ. fast # pics normal #pics fast #pics total 1 Parallel group motion 4 4 76 38 114 2 Diverging 4 2 42 13 55 3 Converging 4 2 47 20 67 4 Random walking 1-127 - 127 5 Individual crossing standing/walking group 8 8 135 71 206 6 Groups crossing standing/head-on/sidewards 12 10 224 88 312 7 Group overtaking group 4-50 - 50 8 Group passing wide gap 4 4 70 44 114 9 Group passing narrow gap 4 4 79 44 123 10 Group passing corridor 4 4 93 52 145 11 Groups passing corridor head-on 4 2 90 38 128 12 Groups merging triple junction 3 3 95 56 151 13 Group avoiding obstacle 4 4 89 41 130 14 Groups brawling 2-102 - 102 15 Group escaping 2-27 - 27 13

Overview State of the art UAV imagery for pedestrian group behaviour Scenario planning and data acquisition Pre-Processing and dataset Group behaviour model of the complex event detector (CED) Experimental results Discussion 14

CED group behaviour model Goal: detection of specific scenarios in public scenes How do pedestrians behave when they are organized in groups? Pedestrian group behaviour model (Considerably influenced by UAV dataset) [Burkert, F., Butenuth, M., 2012. Complex Event Detection in Pedestrian Groups from UAVs. ISPRS Annals I-3, Congress 2012] 15

Overview State of the art UAV imagery for pedestrian group behaviour Scenario planning and data acquisition Pre-Processing and dataset Group behaviour model of the complex event detector (CED) Experimental results Discussion 16

Experimental results Corridor scenario 17

Experimental results Bottleneck scenario 18

Experimental results Bottleneck scenario Robustness: 13 of 16 bottleneck scenarios can be detected (various paces, various gap sizes) 19

Overview State of the art UAV imagery for pedestrian group behaviour Scenario planning and data acquisition Pre-Processing and dataset Group behaviour model of the complex event detector (CED) Experimental results Discussion 20

Discussion UAV imagery or airplane imagery? + monitoring period + flexibility + ground resolution o weather sensitivity o viewing angle Summary Dataset with 15 group motion scenarios Pedestrian group behaviour model Event detection of specific complex scenarios Monitoring of pedestrian groups from UAVs 21

Discussion Outlook Dataset Additional dataset with real-world scenes Image sequences with higher frame-rates Complex Event Detector Probabilistic framework for CED Optional learning of the environment to include obstacles in a scene model 22

Thank you for your attention florian.burkert@bv.tum.de friedrich.fraundorfer@tum.de 23