Date post: | 19-Jun-2015 |
Category: |
Education |
Upload: | christos-boursinos |
View: | 363 times |
Download: | 0 times |
1
SignalGuru: Leveraging Mobile Phones for Collaborative Traffic Signal Schedule Advisory
Emmanouil Koukoumidis , Li- Shiuan Peh, Margaret MartonosiPrinceton University
MIT
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
2
Traffic signals despite that they are a safety control 1. Enforce a stop and go movement2. Increases fuel consumption3. Reduces traffic flow 4. Traffic jams
For all problems that we saw before we have some solutions5. Countdown timer at vehicular traffic signals ( Komotini,
Alexandroupoli)6. Countdown timers for pedestrian traffic signals(USA) 7. GLOSA
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
Traffic conditions
results from CAMBRIDGE and SINGAPORE.
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
3
We can alleviate this problem with computational devices3. GLOSA (Green Light Optimal Speed Advisory)
• detect current traffic signals with their camera • collaboratively communicate• Learn traffic signal results patterns• Predict their future schedule
AUDI recently prototyped a small scale DSRC-based GLOSA system for 25 traffic signals in Ingolstadt
It is expensive to equip all the cars with such technology.
4
Where we put our system in our car.
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
5
GLOSA faces several challenges:1. Lack of Loop detector information ( traffic signals based on
information from loop detectors embedded under every lane on roads close to the stop line governed by traffic signals)
2. Commodity cameras ( the quality of smart phones cameras)3. Limited processing power ( takes significant computational
resources)4. Uncontrolled environment composition and false detection
(no control over the composition of the content captured by their video cameras)
5. Variable ambient light conditions 6. Need for collaboration ( not be able to see a far-away traffic
signal, or may not be within view of the traffic signal for a long enough stretch of time)
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
6
GLOSAThe goal of GLOSA is to advise drivers on the optimal Speed they
should maintain so that the signal is green when they arrive at the next intersection.
What offers1. Decreased fuel consumption2. Smoothed and increased traffic flow3. Decrease environment impactNeed four pieces 4. The residual amount of time till the traffic signal changes5. The intersection location(map)6. Vehicles correct location( gps ) 7. The queue length of the traffic ahead.May improve an individual vehicles travel time.
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
7
Other Possible SignlaGuru-Enabled applications1. Traffic Signal-Adaptive Navigation(TSAN)2. Red Light Duration Advisory(RLDA)3. Imminent Red Light Advisory(ILVA)4. Red Light Violation Advisory (RLVA)
In the next slide we see the deference between TSAN and GLOSA.
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
8
Compare GLOSA-TSAN• The deference
is that in GLOSA we have the optimal speed and in TSAN we have a suggestion detour.
• Architecture of GLOSA
9
SIGNALGURU ARCHITECTUREDetection Module/ detection algorithm
• Which color qualify
• Best candidate to be a traffic signal
• BCC percentage of the pixels fall into the correct color range
• How many pixel are dark enough to qualify as traffic signal
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
10
How the device do the detection. COLOR FILTER
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
11
IMU-based Detection Window
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
12
IMU-based Detection Window
With what angles do the detection
• Angle θ=φ/(2-χ) angle χ =ψ-ω angle ψ=arctan(hs-hc)/d
13
Variable Ambient Light ConditionsOur program will not perform good in some cases1. Time of day2. Weather conditions
To solve this problem we change the sensitivity of the mobile camera to more sensitive.
We have some buttons to do this job in our program
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
14
Transition filtering module
filters
We filter RG transition using a two-stage filter:1. Low Pass Filter(LPF) in 1st stage2. Collocation filter in 2nd stage
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
LPF 1st stageIn 88% of the cases, false positive detections occur over a single
frame and do not spread over multiple consecutive frame:1. R…RGR…RWhen a car is waiting at the red light it correctly detects, then at a
specific instance it misdetects a passing object for a green traffic light.
15
LPF 1st stage
2. G…GRG…GWhen the vehicle misdetects an arbitrary object for a red light
between detections of the actual green light.3. NS…NSRGNS...NSWhen the view of the car is obstructed and there is no traffic
signal in sight. However in some point it misdetects an arbitrary object for a R and G light.
The LPF classifies only this transmission RRGG
Colocation filter 2nd stageChecks whether the green bulb that was just detected is close to
the red bulb detected in the previous frame.
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
16
Collaboration module
A node(cell phone) needs information about a traffic signal well before the signal comes into the node’s camera field.
The collaboration module allows participating SignalGuru nodes to opportunistically exchange their traffic signal information by periodically broadcasting UDP packets in 802.11 ad-hoc.
So they predict the schedule by using a database of the traffic signal settings for a period of time.
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
17
PREDICTION MODULE
We have two main categories of traffic signal:1. Pre-timed traffic signals2. Traffic-adaptive traffic signals
Because their operation is very different , SignalGuru uses different prediction schemes for each category
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
18
Pre-timed traffic signals
SignalGuru’s prediction module maintains a database of the traffic signal settings.
This means that SignalGuru knows how long each phase lasts.The Challenge is to synchronize the SygnalGuru clock with the
time of phase transition of a traffic signal.
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
19
Pre-timed traffic signals
Light switch to red (phase A) switch to Green (phase B)Phase A will follow after phase B.If we have a false detection the synchronize needs to be
reestablished.
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
20
Traffic-adaptive traffic signals
SignalGuru predicts future transitions by detecting past transitions and predicting the length of the current of next phases.
The key different from the prediction of pre-timed traffic signals lies in the prediction of the phase length, as opposed to looking it up from a database.
SignalGuru predicts the length of a phase by measuring and collaboratively collecting the prior traffic signal transition history and feeding it to a Support Vector Regression(SVR) prediction model.
We evaluate the prediction performance of different Prediction Schemes(PS) by training the SVR with different sets of features.
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
21
Traffic-adaptive traffic signals
One-week-history long of data is enough to train the SVR model.Furthermore the SVR model does not need to get continuously
re-trained. Re-training the model every 4 to 8 months is frequent enough in order to keep the prediction errors small.
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
22
CAMBRIDGE DEPLOYMENT• 5 cars with i-phone and
the drivers follow the rout.
• One more device P2 pedestrian.
• P2 was the ad-hoc data relay node.
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
METHODOLOGY
23
SINGAPORE DEPLOYMENT• 2 cars following two
routs.• 8 i-phones in taxis• 5 mobile in rout A• 3 mobile in rout B• One more device P2
pedestrian.• P2 was the ad-hoc data
relay node. Also recording the ground truth when the traffic signals status transitioned.
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
METHODOLOGY
24
SIGNALGURU EVALUATION
TRAFFIC SIGNAL DETECTION
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
We evaluate the performance of two deployments.
• 5959 frames Cambridge• 1352 frames Singapore
• False 7,8% Cambridge• False 12,4% Singapore
• Correctly 92,2% Cambridge
• Correctly 87,6% Singapore
25
SIGNALGURU EVALUATION
IMU-based Detection Window
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
We evaluate the benefits that IMU-based detection window offers.
• The IMU reduces significantly the number of red false positives.
• Often confuses vehicles for a light.
• Reduces the average processing time by 41%
26
SIGNALGURU EVALUATION
Transition Filtering
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
The performance of the transition Filtering.
The False Positive(FP) in Cambridge is smaller than in Singapore
1. Rate of FP traffic signal detection is smaller in Cambridge
2. The average waiting time at red traffic signals is only 19,7s in C. vs 47,6s in S.
27
SIGNALGURU EVALUATION
Schedule Prediction
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
Cambridge deployment• Pre-timed with average
error 0,66s• Video frame every T=2sec• Εmax=T/2 • EXP=T/4=o,5 sec • Can effectively support
the accuracy requirements of all applications.
28
SIGNALGURU EVALUATION
Schedule Prediction
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
Singapore deployment• Average error 2,45 sec
29
SIGNALGURU EVALUATION
GLOSA Fuel Efficiency
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
• From OBD-LINK
• FROM P1P2• Reducing fuel
consumption on average by 20,3%
• Improves the vehicle’s mileage on average by 24,5%
30
Related works
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
• In Lee “et al” propose an application that lets police track the movement of suspicious vehicles based on information sensed by camera-equipped vehicles.
• Other works proposed to equip vehicles with specialized cameras and detect traffic signals with the ultimate goal of enabling autonomous driving , assisting the driver, detecting the location of intersection and overlaying navigation information.
• Our System GLOSA putting the IMU and also it has safe results. It use DLT certificates or a TPM in order to ensure trust in the exchange of traffic signal data.
31
Conclusions
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH
• In order to predict traffic signals future schedule and support a set of novel applications is a fully distributed and grassroots approach.
• Our proposed schemes improve traffic detection filter noisy traffic signal data and predict traffic signal schedule.
• SignalGuru can effectively predict the schedule for not only pre-timed but also state of the art traffic-adaptive traffic signals.
• Fuel efficiency
We hope for a motivation from you.
32
The End
BOURSINOS CHRISTOS/DISTRIBUTED SYSTEMS/ Msc CS FALL 2011/V. KALOGERAKH