How to Evaluate all the Functions of Streets?
Nicolas Saunier
[email protected] March 27th 2017
Outline
Introduction Automated Video Analysis Road User Behaviour and Safety Analysis Studies Perspectives
2
Outline
Introduction Automated Video Analysis Road User Behaviour and Safety Analysis Studies Perspectives
3
What are traditionnally the functions of roads?
4
What are traditionnally the functions of roads? • Transit
4
What are traditionnally the functions of roads? • Transit • Access to land and buildings
4
How are streets different?
5
How are streets different? • Streets serve other functions and a larger variety of users with different abilities and needs
5
How are streets different? • Streets serve other functions and a larger variety of users with different abilities and needs • A “place” for social activities
5
6
Functions Impacts
Access
Socializing Playing
Movement
Strolling Movement
Public Health:
Respiratory Diseases, Road Safety, Physical Activity
)) Exercising Exercising
Environment:
Pollution, GHG Emissions
7
Long-term Objective To develop a framework and automated methods for the integrated evaluation of the functions of streets and the impacts of their use based on the naturalistic observation of all users
8
Outline
Introduction Automated Video Analysis Road User Behaviour and Safety Analysis Studies Perspectives
9
Processing Steps
1. Video data collection 2. Data preparation 3. Moving road user detection, tracking and classification
10
Step 1: Video Data Collection
11
Step 2: Data Preparation
In particular, camera calibration: homography, distortion, etc.
12
Step 2: Data Preparation
In particular, camera calibration: homography, distortion, etc.
12
Step 3: Road User Detection, Tracking and Classification
13
Step 3: Road User Detection, Tracking and Classification
13
Step 3: Road User Detection, Tracking and Classification
13
Step 3: Road User Detection, Tracking and Classification
ROC Curves
13
Step 3: Optimization of Tracking parameters
Calibration Urban Tracking Annotation
Traffic Intelligence Tracking
Quality Control Routines
MOTA
Local Maximum Not Found
Genetic Algorithm Local Maximum Found
Separate Dataset
Calibrated Parameters
14
Step 3: Optimization of Tracking parameters
Site S1S S1W S2 S3V1 S3V2
Default 0.719046 0.041073 0.703178 0.759758 0.750416
S1S 0.904502 0.114581 0.74025 0.797088 0.704989
Parameters optimized for S1W S2 S3V1 0.820976 0.817581 0.841254 0.709927 0.077883 0.044429 0.622532 0.766731 0.745787 0.778268 0.793216 0.817457 0.737339 0.776115 0.700151
Site S1S S1W S2 S3V1 S3V2
Default 0.719046 0.041073 0.703178 0.759758 0.750416
S1S 0.904502 0.114581 0.74025 0.797088 0.704989
Parameters optimized for S1W S2 S3V1 0.820976 0.817581 0.841254 0.709927 0.077883 0.044429 0.622532 0.766731 0.745787 0.778268 0.793216 0.817457 0.737339 0.776115 0.700151
S3V2 0.823145 0.050852 0.718321 0.799231 0.788521 S3V2 0.823145 0.050852 0.718321 0.799231 0.788521 14
Outline
Introduction Automated Video Analysis Road User Behaviour and Safety Analysis Studies Perspectives
15
Processing Steps
4. Motion pattern learning 5. Motion prediction 6. Safety indicators 7. Interpretation
16
Step 4: Motion Pattern Learning
17
Step 4: Motion Pattern Learning
17
Step 5: Motion Prediction
A traffic conflict is “an observational situation in which two or more road users approach each other in space and time to such an extent that a collision is imminent if their movements remain unchanged”
18
Step 5: Motion Prediction
18
Step 5: Motion Prediction
18
Step 5: Motion Prediction
18
Step 6: Safety Indicators
t1
0.7 0.3
t2 0.4
2
0.6
1
19
Step 6: Safety Indicators
19
Step 6: Safety Indicators
4.0
Expected evolution Motion pattern prediction Normal adaptation prediction Constant velocity prediction
Time-to-collision (TTC) in seconds
3.5 3.0 2.5 2.0 1.5 1.0 0.5 0.0 0.0
0.5
1.0 1.5 2.0 Interaction-instant time in seconds
2.5
3.0 +1.02e3
19
Step 7: Interpretation
Collision Probability
For each interaction, we have 0.40 0.35 0.30 0.25 0.20 0.15 0.10 0.05 0.00
2
3
4 Time (second)
5
6
2
3
4 Time (second)
5
6
TTC (second)
3.0 2.5 2.0 1.5 1.0 0.5
20
Step 7: Interpretation
Collision Probability
How should data be aggregated? 0.40 0.35 0.30 0.25 0.20 0.15 0.10 0.05 0.00
2
3
4 Time (second)
5
6
2
3
4 Time (second)
5
6
TTC (second)
3.0 2.5 2.0 1.5 1.0 0.5
20
Step 7: Interpretation
Histogram of Before-and-After TTC Frequency of traffic events
600 TTC Before TTC After
500 400 300 200 100 0
0
2
4
6
8 TTC
min
10 12 in seconds
14
16
18
20
Histogram of Before-and-After PET ncy of traffic events
3000 2500
PET Before PET After
2000 1500 1000
20
Step 7: Interpretation Traffic Conflicts 72 64 56 48 40 32 24 16 8 0
20
Motion pattern
Normal adaptation
Cumulative Observations (%)
Constant velocity
Step 7: Interpretation 1.0 0.8 0.6 0.4 0.2 0.0 1.0 0.8 0.6 0.4 0.2 0.0 1.0 0.8 _cl_1 _cl_3 0.6 _cl_2 0.4 _cl_5 _cl_4 0.2 _cl_6 0.00 2 4 6 8 10 0 2 4 6 8 10 0 2 4 6 8 10 All instants Unique pair: minimum value Unique pair: 15th centile
TTC observations (seconds)
20
Step 7: Interpretation
Cycle Track on Right Cycle Track on Left Bicycle Flow for 5s before to 5s after Turning-Vehicle Flow for 5s before to 5s after Number of Lanes on the Main Road Number of Lanes on the Turning Road Cut-off 1 Cut-off 2 Cut-off 3 Number of Observations Log likelihood
Model I. Cycle track on the right vs. no cycle track
Model II. Cycle track on the left vs. no cycle track
Coef.
Std. Err.
Sig.
Coef.
Std. Err.
Sig.
Coef.
Std. Err.
Sig.
0.395 -
0.181 -
0.03 -
-
-
-
-0.513
0.131
0.00
Not Significant
-2.771
0.132
0.00
-0.151
0.078
0.05
Not Significant
-6.599 -4.233 -3.150
0.353 0.273 0.256 2880 -804
0.00 0.00 0.00
Not Significant
Model III. Cycle track on the right vs. cycle track on the left
0.088
0.038
0.02
0.066
0.034
0.05
-3.265
0.090
0.00
-3.131
0.080
0.00
Not Significant
Not Significant
0.324
0.146
0.03
0.457
0.178
0.01
-7.372 -3.807 -2.102
0.301 0.223 0.211 4803 -1876
0.00 0.00 0.00
-7.621 -4.125 -2.479
0.323 0.265 0.258 6567 -2330
0.00 0.00 0.00
20
Dist (m)
Dist (m)
50 Cluster 1 - 23.1%(28/121) 50 Cluster 2 - 42.7%(35/82) 40 40 30 30 20 20 10 10 0 2 0 2 4 6 8 10 12 14 0 2 0 2 4 6 8 10 12 14 Time (s) Time (s) Cluster 3 0 . 0%(0 / 8) Cluster 4 - 42.1%(8/19) 50 50 40 40 30 30 20 20 10 10 0 2 0 2 4 6 8 10 12 14 0 2 0 2 4 6 8 10 12 14 Time (s) Time (s) Cluster 5 38 . 5%(5 / 13) Cluster 6 - 11.5%(6/52) 50 50 40 40 30 30 20 20 10 10 0 2 0 2 4 6 8 10 12 14 0 2 0 2 4 6 8 10 12 14 Time (s) Time (s) Dist (m)
Dist (m)
Dist (m)
Dist (m)
Step 7: Interpretation
20
4.5 Cluster 2 - 38.2%(55/144) 4.0 3.5 3.0 2.5 2.0 1.5 1.0 0.5 0.01 2 3 4 5 6 7 8 9 Time (s)
Cluster 3 - 33.3%(3/9) 4.5 4.0 3.5 3.0 2.5 2.0 1.5 1.0 0.5 0.01 2 3 4 5 6 7 8 9 Time (s)
Cluster 4 - 5.0%(1/20) 4.5 4.0 3.5 3.0 2.5 2.0 1.5 1.0 0.5 0.01 2 3 4 5 6 7 8 9 Time (s)
TTC (s)
TTC (s)
TTC (s)
4.5 Cluster 1 - 19.4%(13/67) 4.0 3.5 3.0 2.5 2.0 1.5 1.0 0.5 0.01 2 3 4 5 6 7 8 9 Time (s)
TTC (s)
Step 7: Interpretation
20
Outline
Introduction Automated Video Analysis Road User Behaviour and Safety Analysis Studies Perspectives
21
Dangerous Pedestrian Crossings and Violations at Signalized Intersections
22
Dangerous Pedestrian Crossings and Violations at Signalized Intersections
22
Analysis of Bicycle Facilities in Montreal
• Bicycle boxes • video data collected at 2 sites, before and after the installation of a bicycle box, and 2 control sites without
23
Analysis of Bicycle Facilities in Montreal
• Bicycle boxes • video data collected at 2 sites, before and after the installation of a bicycle box, and 2 control sites without
• Cycle tracks Cycle track on the right Cycle track on the left No cycle track Total
# intersections 8 intersections 7 intersections 8 intersections 23 intersections
Duration 37 h 22 h 31 h 90 h
23
Analysis of Bicycle Facilities in Montreal
• Bicycle boxes • video data collected at 2 sites, before and after the installation of a bicycle box, and 2 control sites without
• Cycle tracks Cycle track on the right Cycle track on the left No cycle track Total
# intersections 8 intersections 7 intersections 8 intersections 23 intersections
Duration 37 h 22 h 31 h 90 h
• Cycling discontinuities
23
Model of Dangerous Interactions at Bicycle Boxes
Explanatory variables Constant Bicycle Flow during 30s before Vehicle Flow 1 during 30s before Vehicle Flow 2 during 30s before Presence of Bicycle Box Observations Percentage of positive obs. Log-likelihood Pseudo R2 *
Interaction Type 1 Dangerous Interaction (PET < 1.5s) Elas. Coef. p-val. Elas.
Coef.
p-val.
Coef.
Interaction Type 2 Dangerous Interaction (PET < 1.5s) p-val. Elas. Coef. p-val. Elas.
-0.559
0.00
-
-1.954
0.00
-
-2.994
0.00
-
-4.354
0.00
-
0.423
0.00
7.7 %
0.434
0.00
2.1 %
-
-
-
-
-
-
0.091
0.00
1.6 %
0.040
0.04
0.2 %
0.063
0.00
0.4 %
-
-
-
-0.086
0.00
-1.6 %
-0.082
0.01
-0.4 %
0.117
0.00
0.8 %
0.097
0.00
0.1 %
0.00
*
0.00
*
0.00
*
-2.050
0.00
-2 %*
Interaction (PET < 5s)
-0.739
-14 %
-1.226
-7 %
Interaction (PET < 5s)
-0.726
1054
-5 %
1054
27.6 %
7.5 %
9.8 %
1.3 %
-544.00 0.133
-251.48 0.109
-299.85 0.117
-66.44 0.110
Elasticity for discrete change of dummy variable from 0 to 1
24
Turning Vehicle Interactions with Cycle Tracks
25
Three PET Ordered Logit Models
Cycle Track on Right Cycle Track on Left Bicycle Flow for 5s before to 5s after Turning-Vehicle Flow for 5s before to 5s after Number of Lanes on the Main Road Number of Lanes on the Turning Road Cut-off 1 Cut-off 2 Cut-off 3 Number of Observations Log likelihood
Model I. Cycle track on the right vs. no cycle track
Model II. Cycle track on the left vs. no cycle track
Coef.
Std. Err.
Sig.
Coef.
Std. Err.
Sig.
Coef.
Std. Err.
Sig.
0.395 -
0.181 -
0.03 -
-
-
-
-0.513
0.131
0.00
Not Significant
-2.771
0.132
0.00
-0.151
0.078
0.05
Not Significant
-6.599 -4.233 -3.150
0.353 0.273 0.256 2880 -804
0.00 0.00 0.00
Not Significant
Model III. Cycle track on the right vs. cycle track on the left
0.088
0.038
0.02
0.066
0.034
0.05
-3.265
0.090
0.00
-3.131
0.080
0.00
Not Significant
Not Significant
0.324
0.146
0.03
0.457
0.178
0.01
-7.372 -3.807 -2.102
0.301 0.223 0.211 4803 -1876
0.00 0.00 0.00
-7.621 -4.125 -2.479
0.323 0.265 0.258 6567 -2330
0.00 0.00 0.00
26
Cyclist Behaviour at Cycling Discontinuities
FIGURE 5.a: End of bike facility facility type
FIGURE 5.c: Change in side of bicycle facility
FIGURE 5.e: Change of the number of lanes along a bicycle facility
FIGURE 5.b: Change of bike
FIGURE 5.d: Intersections on bike facilities
FIGURE 5.f: Change in road class along a bike facility
27
Cyclist Behaviour at Cycling Discontinuities 7. 5.
6.
8.
1.
2. 3.
4.
Maisonneuve boulevard west and Sainte-Catherine street Discontinuity: change in cycling facility side 2.
1.
27 Maisonneuve boulevard west and Prince Albert avenue: control site
Safety of Pedestrian Crossings at Night
28
0.1
1
Cumulative percentage (%)
Percentage (%)
Safety of Pedestrian Crossings at Night
0.08 0.06 0.04 0.02 0 0
10
20
30
40
50
Day
Approach Speed
60
0.04 0.02 0
Approach Speed
30
0.2 0 0
1
2
3
PET value
Cumulative percentage (%)
Percentage (%)
0.06
20
0.4
4
Day
5
Night
b) Accumulative conflict distribution – du Fort
0.08
10
0.6
Night
a) Speed distribution – du Fort
0
0.8
40
Day
c) Speed distribution – st-Laurent
50
60
Night
1 0.8 0.6 0.4 0.2 0 0
1
2
PET value
3
4
Day
5
Night
d) Accumulative conflict distribution – st-Laurent
28
Outline
Introduction Automated Video Analysis Road User Behaviour and Safety Analysis Studies Perspectives
29
Conclusion
• Lots of work on safety, less on behaviour • Video analysis can provide high quality trajectories, but analyzing automatically open urban traffic scenes in all conditions is still an open problem • Video analysis for transportation applications is big data • many challenges: data organization, processing and interpretation
30
Perspectives
• Integrated framework of indicators to measure the different dimensions (functions and impacts) of streets • Automated methods for activity recognition • Systematic visualization of the dimensions of streets • Case studies on shared spaces (official or informal)
31
32
• Collaboration with Tarek Sayed (UBC), Karim Ismail (Carleton), Mohamed Gomaa Mohamed, Paul St-Aubin, ´ Matin Nabavi Niaki (Polytechnique Montreal), Luis Miranda-Moreno, Sohail Zangenehpour, Ting Fu (McGill), Aliaksei Laureshyn (Lund) • Funded by the Natural Sciences and Engineering ´ Research Council of Canada (NSERC), the Quebec Research Fund for Nature and Technology (FRQNT) and ´ the Quebec Ministry of Transportation (MTQ), City of Montreal
Questions?
33