The Pothole Patrol: Using a Mobile Sensor Network for Road Surface Monitoring - PowerPoint PPT Presentation

1 / 30
About This Presentation
Title:

The Pothole Patrol: Using a Mobile Sensor Network for Road Surface Monitoring

Description:

The Pothole Patrol: Using a Mobile Sensor Network for. Road Surface Monitoring ... Firmly attached to dashboard inside car's glove box. 9. Soekris 4801. P2 ... – PowerPoint PPT presentation

Number of Views:457
Avg rating:3.0/5.0
Slides: 31
Provided by: LAW360
Category:

less

Transcript and Presenter's Notes

Title: The Pothole Patrol: Using a Mobile Sensor Network for Road Surface Monitoring


1
The Pothole Patrol Using a Mobile Sensor Network
forRoad Surface Monitoring
  • Jakob Eriksson, Lewis Girod, Bret Hull,
  • Ryan Newton, Samuel Madden, Hari Balakrishnan
  • MIT Computer Science and Artificial Intelligence
    Laboratory
  • Mobisys 2008
  • Speaker Lawrence

2
Outline
  • Introduction
  • P2 Architecture
  • Data Acquisition
  • Algorithm
  • Evaluation
  • Conclusion
  • QA

3
Outline
  • Introduction
  • P2 Architecture
  • Data Acquisition
  • Algorithm
  • Evaluation
  • Conclusion
  • QA

4
Introduction
  • Motivation
  • Maintain roadways spend millions of dollars, but
    few feel comfortable.
  • There are cause of expensive lawsuits and claim.

5
Introduction (cont.)
  • Goal
  • Detecting and reporting the surface condition of
    roads.

6
Introduction (cont.)
  • Pothole Patrol (P2 )
  • Deploy P2 on 7 taxis running in the Boston.
  • P2 uses the inherent mobility of the
    participating vehicles.
  • Opportunistically gather data from accelerometer
    and GPS sensors.
  • Process the data by using machine learning to
    assess road surface condition.

7
Introduction (cont.)
Accelerometer GPS
TAXI
7 cabs are able to cover 2492 distinct kilometers
during their normal driving in 10 days
8
Outline
  • Introduction
  • P2 Architecture
  • Data Acquisition
  • Algorithm
  • Evaluation
  • Conclusion
  • QA

9
P2 Architecture (cont.)
Testbed Soekris 4801 embedded computer(Linux)
WiFi card Network card GPS 3-axis
accelerometer
Soekris 4801
Placement (Consider by accelerometer ) Firmly
attached to dashboard inside cars glove box
10
P2 Architecture
Client (Cars)
Server
11
P2 Architecture (cont.)
Combine Filter
Sensing
121E31 25N02
121E31 25N02
Upload Store
Final Report
Clustering
12
P2 Architecture (cont.)
13
Outline
  • Introduction
  • P2 Architecture
  • Data Acquisition
  • Algorithm
  • Evaluation
  • Conclusion
  • QA

14
Data Acquisition
  • The distribution of coverage density across all
    the lengths of road encountered.

15
Data Acquisition (cont.)
  • Accelerometer Placement

Good
16
Data Acquisition (cont.)
  • GPS Accuracy
  • GPS accuracy in our deployment is important.
  • Measure accuracy
  • Placed a thick metal bar across a road, and
    repeatedly drove over it.
  • standard deviation of the positions reported for
    the bar to be 3.3 meters.

17
Data Acquisition (cont.)
  • Hand-labeled Training Data
  • Collect the data by repeatedly driving down
    several known stretches of road in the Boston.

Event Class
18
Data Acquisition (cont.)
  • Loosely Labeled Training Data
  • Hand-labeled less coverage non-pothole type
  • With types and rough frequency of anomalies
  • Without exact number and location

Example
19
Outline
  • Introduction
  • P2 Architecture
  • Data Acquisition
  • Algorithm
  • Evaluation
  • Conclusion
  • QA

20
Algorithm
  • Main Concept Various road conditions introduce
    high z-axis acceleration.
  • It is less sufficient to only use accelerometer
    to identify the real pothole!
  • Use filter to reject non-pothole even type.

21
Filtering stage
22
Filter
Smaller highway anomalies
Xlttx Z
Speed vs Z ratio
OUT pothole detection
  • tx

ts
Expansion joint ,rail crossings
ZlttS V
XZ-ratio
IN windows of all event type
Z-peak
tz
Minor anomalies
Zlttz
23
Tuning the parameter
  • Goal minimizing false positive rate
  • Corr is the number of correct detections of
    pothole
  • Incorr is the number of incorrect detection of
    pothole (false positive)

t tz ,tx ,ts
s(t)corr-incorr2
Arg max s(t) t
minimizing false positive rate
24
Outline
  • Introduction
  • P2 Architecture
  • Data Acquisition
  • Algorithm
  • Evaluation
  • Conclusion
  • QA

25
Performance of labeled data
Class before after
Pothole 88.9 92.4
Manhole 0.3 0.3
Exp. Joint 2.7 0.0
Railroad Crossing 8.1 7.3
Test data of listed class that was reported as
potholes by our algorithm, before and after
training on additional loosely labeled data.
False positive rate 7.6
26
Impact of features and thresholds
Z-peark filter only
Z-peak, xz ratio
Z-peak, xz ratio, speed vs z ratio
27
Performance on uncontrolled cab data
  • Using 7 taxis running through the Boston
    downtown to collect data
  • Clustering the detections that requiring 4 trace
    before reporting them as a detection

28
48 detections with cluster size 4
29
Outline
  • Introduction
  • P2 Architecture
  • Data Acquisition
  • Algorithm
  • Evaluation
  • Conclusion
  • QA

30
Conclusion
  • Studied an application of mobile sensing
    detecting and reporting the surface conditions of
    roads.
  • By using GPS and accelerometer, the P2 system is
    able to detect adverse road conditions.
  • The false positive rate is very low in
    uncontrolled taxis experiment.

31
QA
  • Thanks for listening
Write a Comment
User Comments (0)
About PowerShow.com