![Page 1: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/1.jpg)
Visual Traffic Jam Analysis based on Trajectory DataZuchao Wang1, Min Lu1, Xiaoru Yuan1, 2, Junping Zhang3, Huub van de Wetering4
1) Key Laboratory of Machine Perception (MOE), and School of EECS, Peking University 2) Center for Computational Science and Engineering, Peking University
3) Key Laboratory of Intelligent Information Processing, and School of Computer Science, Fudan University4) Department of Mathematics and Computer Science, Technische Universiteit Eindhoven
Visualization Workshop’13
Accepted by IEEE VAST 2013
![Page 2: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/2.jpg)
Introduction
� Traffic jam is a critical problem in big cities
BeijingTrafficJams
![Page 3: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/3.jpg)
Introduction
� We are able to monitor traffic jams nowadays
Real time road condition from Google Map
![Page 4: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/4.jpg)
Introduction
� Understanding the traffic jams remains a challenge due to their complexities– Road condition change with time– Different roads have different congestion patterns– Congestions propagate in the road network
We develop a visual analytics system to study these complexities
![Page 5: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/5.jpg)
Related Works
� Traffic modelingWe hope to study the traffic jams on the roads
Outlier tree[Liu et al. 2011]
Probabilistic Graph Model[Piatkowski et al. 2012]
We hope to summarize historic traffic jams with simple model
![Page 6: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/6.jpg)
Related Works
� Traffic event visualization
[Andrienko et al. 2011]
Incident Cluster Explorer[Pack et al. 2011]
We hope to visualize the relationship of traffic events
![Page 7: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/7.jpg)
Design Requirement
� Traffic jam data model– Complete: include location, time, speed– Structured: study propagation of jams– Road bound
� Visual interface– Informative: show location, time, speed,
propagation path, size of propagation– Multilevel: support from city level to road level– Filterable
![Page 8: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/8.jpg)
Data Description
� Beijing taxi GPS data
![Page 9: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/9.jpg)
Data Description
� Beijing taxi GPS data– Size: 34.5GB– Taxi number: 28,519– Sampling point number: 379,107,927– Time range: 2009/03/02~25 (24 days, but 03/18 data
is missing)– Sampling rate: 30 seconds per point (but 60% data
missing)� Beijing road network (from OpenStreetMap)– Size: 40.9 MB– 169,171 nodes and 35,422 ways
![Page 10: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/10.jpg)
Preprocessing
Road Speed Data
Traffic Jam Event Data
Traffic Jam Propagation Graphs
Raw taxiGPS Data
Raw Road Network
Input data
Traffic jam data
![Page 11: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/11.jpg)
Preprocessing
Raw taxiGPS Data
Raw Road Network
![Page 12: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/12.jpg)
Preprocessing: Data Cleaning
GPS Data Cleaning
Raw taxiGPS Data
Raw Road Network
Cleaned GPS Data
ta g
Cleaned
Road Network Processing
Processed Road
Network
RoPr
rocesse
![Page 13: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/13.jpg)
Preprocessing: Map Matching
Map Matching
Raw taxiGPS Data
Raw Road Network
Cleaned GPS Data
Processed Road
Network
GPS Trajectories Matchedto the Road Network
PS Trajec
MMMaMapp MMMMM
s Matc
MMMM
ctories
Cleaned rocesse
![Page 14: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/14.jpg)
Preprocessing: Road Speed Calculation
Road Speed Calculation
Raw taxiGPS Data
Raw Road Network
Cleaned GPS Data
Processed Road
Network
GPS Trajectories Matchedto the Road Network
Road Speed Data
PS Trajec s Matcctories
R
Speed
Cleaned rocesse
…… …
9:10 am 50 km/h
9:20 am 45 km/h
9:30 am 12 km/h
9:40 am 15 km/h
…… …
…… …
9:10 am 55 km/h
9:20 am 10 km/h
9:30 am 12 km/h
9:40 am 45 km/h
…… …
a
Road speed: for each road at each time bin
b
![Page 15: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/15.jpg)
Preprocessing: Traffic Jam Detection
Traffic Jam Detection
Raw taxiGPS Data
Raw Road Network
Cleaned GPS Data
Processed Road
Network
GPS Trajectories Matchedto the Road Network
Road Speed Data
Traffic Jam Event Data
PS Trajec s Matcctories
Speed
Tr
am Eve
Cleaned rocesse
…… …
9:10 am 55 km/h
9:20 am 10 km/h
9:30 am 12 km/h
9:40 am 45 km/h
…… …
a
Traffic jam events: road, start/end time bin
b
e0
e1
…… …
9:10 am 50 km/h
9:20 am 45 km/h
9:30 am 12 km/h
9:40 am 15 km/h
…… …
![Page 16: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/16.jpg)
Preprocessing: Propagation Graph Construction
Propagation Graph Construction
Raw taxiGPS Data
Raw Road Network
Cleaned GPS Data
Processed Road
Network
GPS Trajectories Matchedto the Road Network
Road Speed Data
Traffic Jam Event Data
Traffic Jam Propagation Graphs
PS Trajec s Matcctories
Speed
am Eve
PC
m Pro
Cleaned rocesse
…… …
9:10 am 55 km/h
9:20 am 10 km/h
9:30 am 12 km/h
9:40 am 45 km/h
…… …
a
Defining propagation based on spatial/temporal relationship:
b
e0
e1
…… …
9:10 am 50 km/h
9:20 am 45 km/h
9:30 am 12 km/h
9:40 am 15 km/h
…… …
e0 happens before e1, and on a dWay following e1
e1e0
![Page 17: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/17.jpg)
Visual Interface
Road Speed Data
Traffic Jam Event Data
Traffic Jam Propagation Graphs
Propagation Graphs of Interest
One Propagation
Graph
Road Segment Level Exploration and Analysis
Propagation Graph Level Exploration
Time and Size DistributionSpatial Density
Propagation Graph List
Spatial Filter Temporal & Size Filter Topological Filter
Topological Clustering
Road of Interest
Propagation Graphs of Interest
One Propagation
GraphGraph
R
PE
Sp
Road of Interest
Dynamic Query
![Page 18: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/18.jpg)
Visual Interface: City Level
Road Speed Data
Traffic Jam Event Data
Traffic Jam Propagation Graphs
Propagation Graphs of Interest
Propagation Graph List
![Page 19: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/19.jpg)
Visual Interface: City Level
� Graph list view
![Page 20: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/20.jpg)
Visual Interface: City Level
� Graph list view: icon design
Time range
Spatial path: color for congestion time on each dWay
Size: #events, duration, distance
![Page 21: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/21.jpg)
Visual Interface: City Level
Road Speed Data
Traffic Jam Event Data
Traffic Jam Propagation Graphs
Propagation Graphs of Interest Time and Size DistributionSpatial Density
Propagation Graph List
Spatial Filter Temporal & Size Filter Topological Filter
Topological Clustering
Dynamic Query
![Page 22: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/22.jpg)
Visual Interface: Single Graph Level
Road Speed Data
Traffic Jam Event Data
Traffic Jam Propagation Graphs
Propagation Graphs of Interest
One Propagation
GraphGraph
Propagation Graph Level Exploration
![Page 23: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/23.jpg)
Visual Interface: Single Graph Level
� Flow graph
Jam start pointsJam end points
![Page 24: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/24.jpg)
Visual Interface: Single Road Level
Road Speed Data
Traffic Jam Event Data
Traffic Jam Propagation Graphs
Propagation Graphs of Interest
One Propagation
Graph
Road Segment Level Exploration and Analysis
Road of Interest
Propagation Graphs of Interest
One Propagation
GraphGraph
R
Road of Interest
![Page 25: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/25.jpg)
Visual Interface: Single Road Level
� Table like pixel based visualizationTime of a day: 144 columns (each for a 10min)
Days: 24 rows(each for one day)
Each cell represents one time binColor encode speed
![Page 26: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/26.jpg)
Visual Interface: Single Road Level
� Table like pixel based visualization
Make non-jam cells smaller to highlight jam events
![Page 27: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/27.jpg)
Case Study
� Road level exploration and analysis� Visual propagation graph analysis� Congestion propagation pattern exploration
![Page 28: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/28.jpg)
Case Study: Road Level Exploration and Analysis
� Different road congestion patterns
![Page 29: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/29.jpg)
Case Study: propagation graph analysis
� Spatial temporal information of one propagation
Spatial path Temporal delay
Large delay
![Page 30: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/30.jpg)
Case Study: Propagation Pattern Exploration
� Propagation graphs for one region in the morning of different days
![Page 31: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/31.jpg)
Conclusions
� Present a process to automatically extract traffic jam data
� Design a visual analysis system to explore the traffic jams and their propagations
� Use our system to study a real taxi GPS dataset
![Page 32: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/32.jpg)
Future Works
� Improving the traffic jam model (e.g. with Probabilistic Graph Model)
� Support more analysis task� Try better visual design of propagation graphs� Make a formal evaluation
![Page 33: Visual Traffic Jam Analysis based on Trajectory Data · 2017. 12. 4. · Visual Traffic Jam Analysis based on Trajectory Data Zuchao Wang 1, Min Lu , Xiaoru Yuan1, 2, Junping Zhang3,](https://reader035.vdocuments.site/reader035/viewer/2022081601/60f7abde1d9e332dd063b667/html5/thumbnails/33.jpg)
Acknowledgements
� Funding:– National NSFC Project No. 61170204– National NSFC Key Project No. 61232012
� Data:– Datatang– OpenStreetMap
� Anonymous reviewers for valuable comments
http://vis.pku.edu.cn