DOC PREVIEW
UCF EEL 6788 - Drive-by Sensing of Road-Side Parking Statistics

This preview shows page 1-2-23-24 out of 24 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 24 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 24 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 24 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 24 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 24 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

Slide 1Slide 2Slide 3Slide 4Slide 5Slide 6Slide 7Slide 8Slide 9Slide 10Slide 11Slide 12Slide 13Slide 14Slide 15Slide 16Slide 17Slide 18Slide 19Slide 20Slide 21Slide 22Slide 23Slide 24ParkNetSutha Mathur, Tong Jin, Nikhil Kasturirangan,Janani Chandrashekharan, Wenzhi Xue, Marco Gruteser, Wade TrappeRutgers UniversityMichael BetancourtUCF - EEL 6788Dr. TurgutDrive-by Sensing of Road-Side Parking StatisticsOverview1.Introduction2.Design Goals and Requirements3.Prototype Development4.Parking Space Detection5.Occupancy Map6.Mobility Study7.Improvements8.ConclusionIntroduction - Problems•Traffic congestion costs tons of moneyo4.2 billion lost hourso2.9 billion gallons of gasoline wastedoLooking for parking contributes to these numbers•Lack of informationoHard to determine best prices for meters and where they should be placedoCurrent parking detection systems are costlyIntroduction - ParkNet•Drive-by Parking Monitoringo=Uses ultrasonic sensor attached to the side of carsoDetects parked cars and vacant spaces•Attaches to vehicles that comb through a city (taxi, police, etc.)•Location accuracy based on GPS and environmental fingerprintingIntroduction - Objectives•Demonstrating =the feasibility of the mobile sensing approach including the design, implementation and evaluation of the system•Proposing and evaluating a method of environmental fingerprinting to increase location accuracies•Showing that if the mobility system were currently attached to operating taxis, it would operate with enough samples to determine parking availabilityDesign Goals - Real-time Information•Improve traveler decisions with respect to mode of transportation•Suggesting parking spaces to users driving on the road•Allow parking garages to adjust their prices dynamically according to demmand•Improve efficiency of parking enforcement in systems that utilize single pay stations for multiple parking spotsDesign Goals - Parking Information•Space countoSufficient for most parking applications•Occupancy MapoUseful for parking enforcemenDesign Goals - Cost and Participation•Low-cost SensorsoTypical per spot parking management systems ranges from $250 to $800 per spotoCurrent systems are difficult to place in areas without marked parking spots•=Low Vehicle ParticipationoBe able to function without a lot of cars fittedoKeep costs downPrototype Development - Hardware•Moxbotix WR1 rangefinderoWaterproofoEmits every 50mso12-255 inches=•PS3 Eye webcamo20 fpsoUsed for ground truthoNot in production•Garmin GPSoReadings come at 5HzoErrors can be less than 3m•On-board PCo1GHz CPUo512 MB Ramo20 GB HDoPCI WiFi cardo6 USB portsPrototype Development - Deployment•System was placed on 3 vehicles•3 specific areas were marked off to be analyzed•Data was collected over a 2 month period•Drivers were oblivious to the data collection•All range sensor data is tagged with:Kernel-time, range, latitude, longitude, speedPrototype Development - Verification•PS3 EyeoMounted just above the rangefinderoTook pictures at 20fps that were time tagged•Each picture was manually checked to see if there was a car parked•This was used to verify the data collected from the systemParking Space Detection - Challenges•Ultrasonic sensor does not have a perfectly narrow-width•GPS Errors•False alarmsoOther impeding objects: Trees, people, recycling bins•Missed detectionsoParked vehicles classified to be something other than a parked carParking Space Detection - Dips•A "dip" is a change in the rangefinder readings which usually occurs when there is an object in viewTwo Cars Parked TogetherFar CloseParking Space Detection - Algorithms•Slotted ModeloDetermines which dips are classified as carsoSubtracts the total number of cars found with the total number of spaces available in the area•Unslotted ModeloDetermines which dips are classified as carsoMeasures the distance between dips to see if it is large enough to fit a car•Trainingo20% of the data is used for trainingo80% of the data is used for evaluating performanceParking Space Detection - SlottedSlotted Model AccuracyParking Space Detection - UnslottedUnslotted Model AccuracyOccupancy Map - GPS Error•Selected 8 objects and determined their absolute GPS position using Google Maps•Corresponded the GPS reading gathered from the trials to the objects•Used the reading from one object to correct the othersOccupancy Map - Environmental Fingerprinting•Fixed objects in the environment used to increase positional accuracy•Recognition Walkthrough1.GPS coordinates indicate system is near known object•Parses rangefinder readings•Determines what is not a parked car•Tries match the pattern with the known object•If object found, correct position if within 100mMobility Study - Taxicab Routes•Public dataset of 536 taxicabs GPS position every 60 seconds•Routes were approximated by linear interpolation•Found that taxicabs spend the most time in downtown areas where parking is scarce•Determined the mean time between cabs visiting a particular street.Mobility Study - Taxicab Mean TimeGreater San Francisco Downtown San FranciscoMobility Study - Cost Analysis•Current Cost:oParknet: (~$400 per sensing vehicle) x (number of vehicles needed to get desired rate of detection)oFixed Sensor: ($250-800 per space) x (number of spaces)•Uses opportunistic WiFi connections to transfer data•Easily managed due to the much smaller number of fixed sensors•Exampleo6000 parking spotsoParknet: 300 cabs, 80% coverage every 25 minutes, $0.12 millionoFixed Sensor: $1.5 millionImprovements•Multilane RoadsoMoving cars could be determined by long dipsoRangefinder would need to be longer•Speed LimitationsoSensors currently work best at speeds below 40mph•Obtaining Parking Spot MapsoDifficult for large areasoAlgorithms could determine location surroundings after data collection has been started•Using vehicles current proximity sensorsConclusion•Data collectedo500 miles over 2 months•Accuracyo95% accurate parking space counts=o90% accurate parking occupancy maps•Frequency and Coverageo536 vehicles equippedoCovers 85% every 25 minutes of a downtown areaoCovers 80% every 10 minutes=of a downtown area•Cost BenefitsoEstimated factor of 10-15 times cheaper than current systems•Questions?LinksFixed Parking System


View Full Document

UCF EEL 6788 - Drive-by Sensing of Road-Side Parking Statistics

Documents in this Course
Load more
Download Drive-by Sensing of Road-Side Parking Statistics
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view Drive-by Sensing of Road-Side Parking Statistics and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Drive-by Sensing of Road-Side Parking Statistics 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?