Shared coworking space five tried & tested shared office design
Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with...
Transcript of Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with...
![Page 1: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/1.jpg)
Institut für Kartographie und Geoinformatik | Leibniz Universität Hannover
Monika SesterInstitute of Cartography and GeoinformaticsLeibniz Universität Hannover
Data Analysis: Trajectories and VGIData
![Page 2: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/2.jpg)
Outline
Exploiting „new“ data sources (Trajectories, Social Media) Different applications areas: analysis of traffic, football,
disaster
Trajectory acquisition and interpretation
Trajectory analysis
VGI-data analysis
![Page 3: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/3.jpg)
Deep Learning of Behavioural Models in SharedSpaces
Hao Cheng
![Page 4: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/4.jpg)
| 4
Motivation
► The behavior of roadusers in shared spacesneed to be investigatedfor mixed traffictrajectory predictionand management
► Established modelslack flexibility (e.g.w.r.t. different usertypes andconstellations)
How to build flexible and robust models using real-world data for mixed traffic trajectory predictionwith collision avoidance in shared space?
How to build flexible and robust models using real-world data for mixed traffic trajectory predictionwith collision avoidance in shared space?
![Page 5: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/5.jpg)
| 5
Data Shared space dataset
Layout of a shared spaceAccumulated mixted traffic trajectories
![Page 6: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/6.jpg)
| 6
Feature Incorporation for Long Short-TermMemory Incorporate user type and/or sight of view with spatio-temporal
features as input for Long Short-Term Memory models (Cheng andSester 2018)
Plus: probability of a collision (PDM)
![Page 7: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/7.jpg)
| 7
Prediction by LSTM-PDM—Qualitative AnalysisMultiple road users
![Page 8: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/8.jpg)
| 8
Prediction by LSTM-PDM—Qualitative AnalysisPedestrian waiting for the oncoming vehicles
![Page 9: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/9.jpg)
| 9
Current research
► Include groups and group behaviour
► To this end: evaluation of data setand determination of groups (usingclustering approach)
► Questions: How do car drivers behave with
respect to a group of people (and viceversa)?
When do groups split in order to giveway to other traffic participants?
![Page 10: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/10.jpg)
Udo Feuerhake
Football Analysis
![Page 11: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/11.jpg)
Udo Feuerhake| 11
Football Analysis – Advanced Analyses
► Recognition of Patterns in …
… individual player movements to …
• … characterize players
• … predict player movements
… team (group) movements to …
• … identify team tactics
… pass sequences to …
• … predict next passes
![Page 12: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/12.jpg)
Udo Feuerhake| 12
Recognition of Individual Movement Patterns
► Movement pattern = frequent repetitive movement
► Approach without segmentation step is required moving window algorithm
Transformation to a sequence mining problem
• Trajectory as a sequence of movements/positions/…
![Page 13: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/13.jpg)
Udo Feuerhake| 13
Recognition of Individual Movement Patterns
► Transforming a trajectory to a sequence
Points as sequence items
No invariances (only exact reproduction)
= ,… ,
![Page 14: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/14.jpg)
Udo Feuerhake| 14
Recognition of Individual Movement Patterns
► Transforming a trajectory to a sequence
Movements/movement vectors as sequence items
Translation invariances
= ,… , or
= ,… ,
![Page 15: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/15.jpg)
Udo Feuerhake| 15
Recognition of Individual Movement Patterns
► Transforming a trajectory to a sequence
Movements/ movement vector changes as sequence items
Translation & rotation invariances
= ,… ,
![Page 16: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/16.jpg)
Udo Feuerhake| 16
Recognition of Individual Movement Patterns
► Problem of continuous data/attributes
Sequence will consist of non repetitive elements (as all data willbe nearly unique!)
No patterns will be found at all
► Solution?
► Determine item similarities to deal with variances
Clustering of items
![Page 17: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/17.jpg)
Udo Feuerhake| 17
Recognition of Individual Movement Patterns
► Use of sequence mining algorithm to extract patterns from thesequence of clusters (clustered items) Algorithm to find repetitive subsequences in long supersequence
► Application of modified version of Apriori algorithm
![Page 18: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/18.jpg)
Udo Feuerhake| 18
Recognition of Individual Movement Patterns
► Results No invariances allowed Translation is allowed
![Page 19: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/19.jpg)
Udo Feuerhake| 19
Recognition of Team Movement Patterns
► In general: repetitive relative movements of a group ofobjects
► Requirements: Group members are already known
Group size has to be constant over time
t
![Page 20: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/20.jpg)
Udo Feuerhake| 20
Pass Sequence Pattern Mining
![Page 21: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/21.jpg)
Stefania Zourlidou
Crowd sensing for traffic regulationdetection and recognition
![Page 22: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/22.jpg)
Stefania Zourlidou| 22
Examples of traffic rules: T-junction control systems
![Page 23: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/23.jpg)
Stefania Zourlidou| 23
Traffic control technology
Uncontrolled intersections, without signs orsignals (or sometimes with a warning sign).Priority (right-of-way) rules may vary bycountry
Yield-controlled intersections may or may nothave specific "YIELD" signs (known as "GIVEWAY" signs in some countries).
Stop-controlled intersections have one or more"STOP" signs. Two-way stops are common,while some countries also employ four-waystops (or multi-way stop control).
Signal-controlled intersections depend ontraffic signals, usually electric, which indicatewhich traffic is allowed to proceed at anyparticular time.
right of way rule
![Page 24: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/24.jpg)
Stefania Zourlidou| 24
A trajectory-based approach
► Given a large vehicle trajectory data set, how can we infertraffic rules for enriching maps with traffic regulations?
![Page 25: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/25.jpg)
Stefania Zourlidou| 25
Supervised approach: Speed profiles
► Assumption: intersections show characteristic speed profiles e.g. stop at stop sign, speed decrease to give way at ordinary
intersections, etc.
Multiple occurrences reinforce statement about intersection (type)
![Page 26: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/26.jpg)
Stefania Zourlidou| 26
Supervised approach
Learning the traffic context of intersections from speed profiledata
Supervised Learning method to classify each tracking point ofeach trajectory
![Page 27: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/27.jpg)
Stefania Zourlidou| 27
Approach
Application of classification methods• e.g. C4.5, Logistic Regression or Random Forest
-100m
100m
Input vector=[v-100, v-199,…, v0, v1, v100] [vi: Speed value imeters before(-)/ after(+) the ]
-100m
100m
![Page 28: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/28.jpg)
Stefania Zourlidou| 28
Detected locations
Results of the aggregation after individual trajectory classification.Colours encode consensus levels for detected intersections red: low consensus, i.e. outliers/false classifications due to e.g.
traffic congestions green: high consensus.
Peaks in classification confidence correspond to actual intersectionlocations.
![Page 29: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/29.jpg)
Stefania Zourlidou| 29
Traffic signal controlled intersection
![Page 30: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/30.jpg)
Extraction of high definition maps fromLidar data
Steffen Busch
![Page 31: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/31.jpg)
GeometricDetection & Tracking
Scan to depth image
Depth image to labels
Lane projection to point cloud Plane estimation for each lane
Labels to segments
Region Growing
![Page 32: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/32.jpg)
Neural NetworkDetection & Tracking
Segmentation by Neural Network
200.000 images (Depth and Intensityvalues) and labels
• ~4h scans• 6 junctions in Hanover• Labelling of traffic participants
True positiveTrue negativeFalse negativeFalse positive
![Page 33: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/33.jpg)
Data assessmentTrajectories
Detections by ground filtering, lane matching and regiongrowing
![Page 34: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/34.jpg)
Trajectory Example Königswortherplatz
Iterative Extended KalmanFilter
Constant acceleration andyaw rate
Bicycle model
Greedy Assignment DB SCAN Detection clustering Hungarian Method per cluster
![Page 35: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/35.jpg)
High Definition MappingMarkov Chain Monte Carlo Optimization
![Page 36: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/36.jpg)
Near accidents from trajectories
Christian Koetsier
![Page 37: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/37.jpg)
IKG Christian Koetsier | 37
Goal
► Automated recognition of “unsafe” driving situations For example: (near) accidents
► Search / Identification of the trigger Other road users (cars, cyclists, pedestrians)
The environment (glare, shading, unevenness in the road)
Individual (distraction, misbehaviour)
► Include "unsafe" driving situations as well as their triggers inthe maps, so that they can be considered in future drivingmaneuvers.
![Page 38: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/38.jpg)
IKG Christian Koetsier | 38
Surveillance camera pipeline
Anomaliestrajectories
….
….
![Page 39: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/39.jpg)
IKG Christian Koetsier | 39
Detection and trajectories
► Static surveillance camera data
![Page 40: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/40.jpg)
Interpretation of behaviour – a modelbased approach
Hai Huang and Lijuan Zhang
![Page 41: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/41.jpg)
41
Determination of anomalous behaviour
► Idea: Driver shows specific behaviourwhen he/she is lost
► -> provide immediate help!
► Components of behaviour: Frequent turns
Detour
Route repetition
► For these components, typicalprobabilities for normal behaviour aredetermined
► Fusion of probabilities via HiddenMarkov Modell
[Huang & Zhang]
![Page 42: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/42.jpg)
42
Determination of anomalous behaviour
► Example: Route from bottom to top
Start
Goal
![Page 43: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/43.jpg)
43
Determination of anomalous behaviour
► 100 Trajectories
![Page 44: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/44.jpg)
44
Examples
► Details
![Page 45: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/45.jpg)
45
Indication of anomalous traffic situation
![Page 46: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/46.jpg)
Social Media for Pluvial Flood DetectionYu Feng
![Page 47: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/47.jpg)
Social Media for Pluvial Flood Detection Feng Yu| 47
Motivation
Source: http://blog.yokellocal.com/local-social-media-marketing-twitter
![Page 48: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/48.jpg)
Social Media for Pluvial Flood Detection Feng Yu| 48
36469 Tweets15263 Tweets 21206 Tweets
Tweets with keywords and marked as positive
Tweets with keywords andmarked as negative
Tweets randomly selectedwithout keywords
Time,locationTweet
TextRain / No rain
Data acquisition
Data annotation Trainings-Datensatz
Model for Prediction
Training of text classifier with ConvNets
![Page 49: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/49.jpg)
Social Media for Pluvial Flood Detection Feng Yu| 49
Transfer learning for image recognition
2048 Merkmale
Xgboost(GradientBoosting)
BinaryPrediction
Pre-trained GoogLeNet (Inception V3)(Trained based on 1.2M images- ImageNet)
Feature generator
Classificator 1
IrrelevantImages
Image
Classificator 2
RelevantImagesTrueTrue
False
False
Acc: 93%
Acc: 86%
Training of image classifier with transfer learning
![Page 50: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/50.jpg)
Social Media for Pluvial Flood Detection Feng Yu| 50
TextClassifi-
cator
Tweet
Timelocation
ImageClassifi-
cator
Rain/Floodeyewitnesses
True True
Map + Events
ImagesVideosText
Spatiotemporal Analyses• Clustering – ST-DBSCAN• Hotspot-Detection – Getis-Ord-Gi*
Event Detection
![Page 51: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/51.jpg)
Student project
![Page 52: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/52.jpg)
IKG Christian Koetsier | 52
RideVibes
► Scenario: You want to ride from Welfenschloss to ikg by bike
► Which route would you prefer?
![Page 53: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/53.jpg)
IKG Christian Koetsier | 53
RideVibes
► Mobile app for bike adapted navigation which includes the“comfort factor”
► The “comfort factor” includes the road surface quality (roughness)
existence of potholes and curbsides
number of unwanted stops (traffic lights, other obstacles)
► Measure, extract and map this factors to extend the commonbike routing
![Page 54: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/54.jpg)
IKG Christian Koetsier | 54
RideVibes
► Data acquisition Smartphone-App
GPS + sensor data
► Map data Map matching of GPS
trajectories
Obtain features fromtrajectories and sensordata
Update routing graph
Example
► Routing based onadditional features
![Page 55: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/55.jpg)
Summary
![Page 56: Data Analysis: Trajectories and VGI Data · world data for mixed traffic trajectory prediction with collision avoidance in shared space? | 5 Data Shared space dataset Accumulated](https://reader034.fdocuments.us/reader034/viewer/2022042317/5f06bc0c7e708231d41977ee/html5/thumbnails/56.jpg)
Summary
Exploiting „new“ data sources (Trajectories, Social Media)
Machine Learning (ML), Deep Learning (DL), Optimizationapproaches
Cheng: behaviour prediction - DL Feuerhake: foodball patterns – ML, association rules Zourlidou: traffic regulations - ML Busch: High Definition maps – DL and optimization Koetsier: near accidents – use of DL + Kalman Filtering Huang: Hidden Markov Models Feng: strong rainfall events – DL