Outline Introduction & Related Works Overview User Interface - - PDF document

▶
outline
SMART_READER_LITE
LIVE PREVIEW

Outline Introduction & Related Works Overview User Interface - - PDF document

Jun 14, 2023 240 likes •438 views

2013/10/24 IEEE Pacific Visualization Symposium 2011 TripVista: Triple Perspective Visual Trajectory Analytics and Its Application on Microscopic Traffic Data at a Road Intersection Hanqi Guo 1, 2 , Zuchao Wang 1 , Bowen Yu 1 , Huijing Zhao 1 ,

slide-1
SLIDE 1

2013/10/24 1

TripVista: Triple Perspective Visual Trajectory Analytics and Its Application on Microscopic Traffic Data at a Road Intersection

Hanqi Guo1, 2, Zuchao Wang1, Bowen Yu1, Huijing Zhao1, Xiaoru Yuan1, 2

IEEE Pacific Visualization Symposium 2011

1) Key Laboratory of Machine Perception (Ministry of Education), and School of EECS 2) Center for Computational Science and Engineering Peking University, Beijing, P.R. China

Outline

  • Introduction & Related Works
  • Overview
  • User Interface
  • Results
  • Conclusion
slide-2
SLIDE 2

2013/10/24 2

Introduction – Traffic Management

  • Traffic management has always been a critical

i i d i t issue in modern society

http://www.news-to-use.com/2010/08/china- traffic-jam-could-last-weeks.html http://www.foxnews.com/world/2010/08/24/long-haul-chinas-traffic- jam-stretching-long-km-weeks/

A traffic jam on National Expressway 110 in China, captured at

  • Aug. 24th, 2010, which stretched for 60-mile, lasted 11 days

Introduction – Research on Traffic

  • Scope

– Macro-trend of traffic – Micro-behaviors of traffic

  • To find out origin of accidents and jams
  • To evaluate traffic light configurations
  • Data source

– Simulation data – Real data

M f t d ti t ll d l d

  • Many features and exception are not well-modeled
  • Suffer from noise
  • Challenges

– Complexity, Noise, Size

slide-3
SLIDE 3

2013/10/24 3

Related Works

  • Spatial generalization and aggregation

[Andrienko2011]

Related Works

  • Spatial, temporal, attributes information

l l li k d closely linked

FromDady: [Hurter2009]

slide-4
SLIDE 4

2013/10/24 4

Overview – Data Acquisition

  • Laser scanning

Raw data collected as point cloud Preprocessed data as moving

  • bject, further

classified

Image courtesy of Zhao et al. 2009

Overview – Data Acquisition

  • Raw data as point cloud

Video courtesy of Zhao et al. 2009

slide-5
SLIDE 5

2013/10/24 5

Overview – Data Description

  • Microscopic trajectory dataset collected at a road

intersection intersection

– 209,426 trajectories

  • Length, width
  • Track type: pedestrian, bus,

bicycle, car and other

  • Sample point array

33 362 651 l d i t – 33,362,651 sampled points

  • Position, speed, direction, time

– 2 days’ data: 7:00 ~ 21:00 – Noise

Overview – Design Philosophy

  • Triple perspectives closely linked
slide-6
SLIDE 6

2013/10/24 6

User Interface

  • Spatial view + Temporal view + PCP

Spatial View Temporal View Control Panel Parallel Coordinates Time range selection

Spatial View

  • Spatial perspective

Compass

– Trajectory as curve – Compass

slide-7
SLIDE 7

2013/10/24 7

Spatial View

  • Spatial perspective

– Trajectory as curve – Compass – Ring-slider

Exit Angle Filter Entrance Angle Filter

Spatial View

  • Spatial perspective

Exit Angle Histogram

– Trajectory as curve – Compass – Ring-slider – Histogram

Entrance Angle Histogram

slide-8
SLIDE 8

2013/10/24 8

Temporal View

  • Temporal perspective

h – ThemeRiver

  • Glyph embedded

– Scatterplots

  • Start time VS Passing time
  • Start time VS MinSpeed
  • Start time VS AvgSpeed
  • Start time VS MaxSpeed
  • Start time VS Distance

Temporal View

  • Glyph design

– Trajectory direction clustering and glyph design

Ordinary directions Outlier

slide-9
SLIDE 9

2013/10/24 9

Temporal View

  • Algorithm for ThemeRiver with glyphs

– Original ThemeRiver [Harve2002]

Temporal View

  • Algorithm for ThemeRiver with glyphs

– Original ThemeRiver [Harve2002] – Possible glyph position

  • Fast Hierarchical

Importance Sampling [Ostromoukhov2004]

slide-10
SLIDE 10

2013/10/24 10

Temporal View

  • Algorithm for ThemeRiver with glyphs

– Original ThemeRiver [Harve2002] – Possible glyph position

  • Fast Hierarchical

Importance Sampling [Ostromoukhov2004]

– River subdivision

Temporal View

  • Algorithm for ThemeRiver with glyphs

– Original ThemeRiver [Harve2002] – Possible glyph position

  • Fast Hierarchical

Importance Sampling [Ostromoukhov2004]

– River subdivision – Final result

slide-11
SLIDE 11

2013/10/24 11

Parallel Coordinates

  • Multi-dimensional perspective

d – Two raw dimensions: start time, type – Nine derived dimensions: total time, average speed, minimum

speed, maximum speed, total distance, beginning angle, ending angle, angle change, smoothed angle change, minimum acceleration, maximum acceleration

Positive Correlation Negative Correlation

User Interactions

slide-12
SLIDE 12

2013/10/24 12

Results

  • Case I: Investigate specific behaviors
  • Case II: Find patterns and violations
  • Case III: Discover hidden information

Case I – Investigate Specific Behaviors

  • Recognize special spatial patterns in the traffic

view

d Turn-around pattern

slide-13
SLIDE 13

2013/10/24 13

Case I - Investigate Specific Behaviors (cont’d)

  • By ring-sliders

Case I - Investigate Specific Behaviors (cont’d)

  • By sketch
slide-14
SLIDE 14

2013/10/24 14

Case II – Find Patterns and Violations (cont’d)

  • Micro behavior: violation detection

Case II – Find Patterns and Violations (cont’d)

  • Pattern discovery

T l i di it d t t ffi li ht l ti – Temporal periodicity due to traffic light regulation – Volume comparison, may guide the optimization of traffic light control

slide-15
SLIDE 15

2013/10/24 15

Case III – Discover Hidden Information

  • Discover exceptional trajectory cases by multi-

di i l l i dimensional analysis

– Angle change of the trajectory may reflect some dangerous cases

Angle Change

Case III – Discover Hidden Information (cont’d)

slide-16
SLIDE 16

2013/10/24 16

Case III – Discover Hidden Information (cont’d) Case III – Discover Hidden Information (cont’d)

  • Similar patterns detected by the relative

ti d t ti l ith motion detection algorithm

Jun 16th, 11:22am Jun 16th, 12:06pm Jun 16th, 3:12pm Jun 22nd, 7:27pm Jun 22nd, 6:54pm

However, when speed is considered, none of them are really dangerous.

slide-17
SLIDE 17

2013/10/24 17

Results

  • Case I: Investigate specific behaviors
  • Case II: Find patterns and violations
  • Case III: Discover hidden information

Conclusions

  • TripVista, a visual analytics system for

i i t ffi t j t d t microscopic traffic trajectory data

  • A coordinated visualization based on the triple

perspective design philosophy

  • Capacity to reveal traffic patterns as well as

abnormal behavior abnormal behavior

slide-18
SLIDE 18

2013/10/24 18

Future Works

  • Incorporate more automatic algorithms
  • Extend our system to more complex trajectory

dataset, e.g. road network

  • Integrate videos to the system

Acknowledgements

  • Funding:

– NSFC No. 60903062, BNSF No. 4092021, 973 No.2009CB320903, 863 NSFC No. 60903062, BNSF No. 4092021, 973 No.2009CB320903, 863 2010AA012400, MOE Key Project No. 109001 and IIPL-09-016

  • Anonymous reviewers for comments
  • Jie Sha for data preprocessing and feedbacks

http://vis.pku.edu.cn