Transcript The Pothole Patrol: Using a Mobile Sensor Network for Road

The Pothole Patrol: Using a
Mobile Sensor Network for
Road Surface Monitoring
Jakob Eriksson, Lewis Girod, Bret Hull, Ryan
Newton, Samuel Madden, Hari Balakrishnan
MIT Computer Science and Artificial Intelligence
Laboratory
Outline







Introduction
Architecture
Data Acquisition
Algorithm
Performance
Related Work
Discussion
P2 : A mobile road surface monitoring system







Hazardous to drivers and increasing repair costs due to
vehicle damage
Determine “which” roads need to be fixed
Static sensors will not do well – requires mobility!
P2 is first of its kind
Challenge : differentiate potholes from other road
anomalies (railroad crossings, expansion joints)
Challenge : coping with variations in detecting the same
pothole. (speed, sensor orientation)
P2 successfully detects most potholes
data)
(>90% accuracy on test
2
P

Architecture
Vehicles have GPS and 3-axis accelerometer



<time,location,speed,heading,3-axis acceleration>
Opportunistic WiFi/Cellular connections with dPipe
to cope network outages
Taxi Testbed






7 Toyota Priuses1
Soekris 48012 Embedded Linux
Wifi Card
Sprint EVDO Rev A3 Network card
GPS
Some numerical facts




9730 total kms
2492 distinct kms
7 cabs
174 km with >10 repeated passes
1
2
3
1.
2.
3.
http://www.carbuyersnotebook.com/archives/Toyota_Pruis_2006.jpg
http://www.pkgbox.org/Soekris-4801.jpg
http://gizmodo.com/gadgets/peripherals/two-new-sprint-evdo-rev-a-cards-pantech-px500-and-sierra-wireless-aircard-595-200423.php
2
P
Architecture
Pothole
Record
Clustering
Central Server
Cab 1
GPS
Location
Interpolator
3 Axis
Accelero
meter
Pothole
Detector
Cab 2
GPS
Location
Interpolator
3 Axis
Accelero
meter
Pothole
Detector
2
P
Architecture
Distance Traveled vs. Total Hours
Segments of roads that were
repeatedly covered
Across All Taxis
Lower line represents unique roads
258,021 unique road segments
DATA ACQUISITION

Accelerometer
placement




Dashboard
Windshield
Embedded Computer
GPS Accuracy

Standard deviation 3.3m
DATA ACQUISITION

Hand Labeled Data







Smooth Road
Crosswalks/Expansion
Joints
Railroad crossing
Potholes
Manholes
Hard Stop
Turn
DATA ACQUISITION

Loosely Labeled
Training Data



We know only types of
anomalies and their
rough frequencies
Exact numbers and
locations are unknown
Extends available
training set
ALGORITHM


Features of accelerometer data
High energy events are potholes?



Not really!
Rail road crossings, expansion joints, door
slamming are high energy events
Accelerometer data is processed by
embedded computer


256-sample windows
Pass through 5 different filters
ALGORITHM - Filtering
speed vs.
z ratio
OUT
Pothole
Detections
IN
Windows
of all event
classes

Speed
Input


Raw accelerometer data
256-sample windows
High-pass
xz-ratio
z-peak
ALGORITHM - Filtering
speed vs.
z ratio
OUT
Pothole
Detections
IN
Windows
of all event
classes

Speed
High-pass
Speed


Car is not moving or moving slowly
Rejects door slam and curb ramp events
xz-ratio
z-peak
ALGORITHM - Filtering
speed vs.
z ratio
OUT
Pothole
Detections
IN
Windows
of all event
classes

Speed
xz-ratio
High-pass
High-Pass


Removes low-freq components in x and z axes
Filters out events like turning, veering, braking.
z-peak
ALGORITHM - Filtering
speed vs.
z ratio
OUT
Pothole
Detections
IN
Windows
of all event
classes

Speed
High-pass
xz-ratio
z-peak
z-peak


Prime characteristic for significant anomalies
Rejects all windows with absolute z-acceleration < tz
ALGORITHM - Filtering
speed vs.
z ratio
OUT
Pothole
Detections
IN
Windows
of all event
classes

Speed
High-pass
xz-ratio
z-peak
xz- ratio

Assumes potholes impact only side of the vehicle
Identifies anomalies that span width of the road (rail crossings,
speed bumps)

Rejects all windows with

xpeak within Δw (=32) samples from zpeak < tx X zpeak
Or, ( Xpeak/ zpeak )< tx
ALGORITHM - Filtering
speed vs.
z ratio
OUT
Pothole
Detections
IN
Windows
of all event
classes

Speed
High-pass
xz-ratio
z-peak
speed vs. z ratio


At high speeds, small anomalies cause high peak accelerations
Rejects windows where Zpeak < ts X speed
or, (Zpeak /speed ) < ts
ALGORITHM – Sample Traces
ALGORITHM - Training


Tuning parameters t={tz,tx,ts} are computed
using exhaustive search over a set of values
For each set t, we compute detector score
s(t) = corr – incorr2



Corr is no. of pothole detections when
sample was labeled as “pothole”
Maximize s(t)
Include loosely labeled data
s(t) = corr – incorr2labeled – max(0,incorrloose – countr)
ALGORITHM - Clustering



Improve accuracy
Cluster of at least k events must happen in the
same location with small margin of error(Δd)
Clustering algorithm





Place each detection in Δd X Δd grid.
Compute pairwise distances in same or neighboring grid
cells
Iteratively merge pairs of distances in order of distance
Max intra cluster distance < Δt
Reported location is the centroid of the locations within it
ALGORITHM – Blacklisting &
False Negatives

Well-known anomalies like bridges, railroad
crossings, speed bumps etc can be located
from GIS sources and blacklisted

GPS errors
Pothole avoidance
Biased detection will focus on critical
anomalies


PERFORMANCE EVALUATION
Goals

Minimize false negative rate for smooth roads



Never a flag a smooth road as anomaly
Missing a few potholes is acceptable
Evaluation

1.
2.
3.
4.
Classification accuracy on hand-labeled data
Performance improvement using loosely labeled
data
Performance on loosely labeled roads
Spot-checks
PERFORMANCE EVALUATION

Performance on Labeled Data



Randomly divided into training set and test set
Class
Hand Labeled
w/ Loosely Labeled
Pothole
88.9%
92.4%
Manhole
0.3%
0.0%
Expansion joints
2.7%
0.3%
Railroad Crossing
8.1%
7.3%
False positive rate is 7.6%
Not accurate
PERFORMANCE EVALUATION

Estimating the false-positive rate

Ran the detector on loosely labeled roads
Road
# potholes
# windows
# detections
rate
Storrow Dr.
few
1865
3
0.16%
Memorial Dr.
few
1781
2
0.12%
Hwy I-93
few
2877
5
0.17%
Binney St.
some
6887
25
0.63%
Beacham St.
many
1643
231
14%

Helps set upper bound on false positive rate (at most 0.15%)
on good roads.
PERFORMANCE EVALUATION

Impact of features and thresholds
1. Only Z peak
2. w. xz-ratio filter
3. w. speed vs.
z ratio
tx=1.5
tx=2.5
ts=5
PERFORMANCE EVALUATION

Performance under uncontrolled conditions





Slamming doors
Fiddling with the sensor equipment
Driving behaviors
Deliberately avoiding potholes
Use clustering

k=4
PERFORMANCE EVALUATION

Spot Checks
Typical pothole
Manhole
Expansion joint
RELATED WORK





Surveys
Falling weight deflectometer
Machine vision – cameras, robots
Accelerometer
Microsoft Trafficsense – smartphones
DISCUSSION

This is what I think




Innovative
Ground truth establishment is tedious, expensive in dense
road networks
Will it work in hilly areas ,slopes?
Future work?



Driver feedback – Interactive embedded computers
Smartphones – Cheaper solution, greater coverage
Comments/Questions ???
REFERENCES

The Pothole Patrol: Using a Mobile Sensor Network for
Road Surface Monitoring Jakob Eriksson, Lewis Girod, Bret Hull, Ryan Newton,
Samuel Madden, Hari Balakrishnan MIT Computer Science and Artificial Intelligence
Laboratory

U. Lee, E. Magistretti, B. Zhou, M. Gerla, P. Bellavista, and A. Corradi. MobEyes:
Smart Mobs for Urban Monitoring with a Vehicular Sensor Network. IEEE Wireless
Communications, 2006.

TrafficSense: Rich Monitoring of Road and Traffic Conditions using Mobile
Smartphones Prashanth Mohan, Venkata N. Padmanabhan, and Ramachandran
Ramjee {prmohan,padmanab,ramjee}@microsoft.com Microsoft Research India,
Bangalore

http://research.microsoft.com/apps/pubs/default.aspx?id=70573