Using Inductive Loop Signature Re-Identification for Travel Time
Transcription
Using Inductive Loop Signature Re-Identification for Travel Time
commeaT.E.C. traffic engineering & consulting Using Inductive Loop Signature Re-Identification for Travel Time Measurement – Use Case Bremerhaven Jonas Lüßmann – TU München, Chair of Traffic Engineering and Control (TUM-vt) Florian Schimandl – TUM-vt Friedrich Maier – commeaT.E.C. – traffic engineering & consulting Fritz Busch – TUM-vt 6th International Symposium “Networks for Mobility” Stuttgart, September 27, 2012 0 Friedrich Maier: Using Inductive Loop Signature Re-identification for Travel Time Measurement Networks for Mobility, September 27, 2012 Inductive loops, vehicle signatures commeaT.E.C. traffic engineering & consulting 60 Detuning %o Verstimmung in %o 50 50 40 30 20 10 0 49800 0 0 1 49850 2 49900 3 49950 4 50000 5 50050 6 50100 7 50150 8 50200 9 50250 Time [s] Num m erierung der Stützstellen (unnorm iert) ISAR: Inductive loops – Signature Analysis for vehicle Re-identifcation and travel time measurement – project at TUM-vt 2004-2006 1 Friedrich Maier: Using Inductive Loop Signature Re-identification for Travel Time Measurement Networks for Mobility, September 27, 2012 ISAR-Method – basics commeaT.E.C. traffic engineering & consulting Standardised signatures !!! Relevant signature features: 2 › Signature derivative › maximum detuning Filter criteria: › Vehicle „class“ › Temporal distance › Small similarity Friedrich Maier: Using Inductive Loop Signature Re-identification for Travel Time Measurement Networks for Mobility, September 27, 2012 ISAR-Method – basics commeaT.E.C. traffic engineering & consulting yA yB y‘A y‘B U… uniformness, similarity cal… calibration factor > x Matching equation: U A,B xEnd min( y , n; y ) min(max y A cal A ; max y B cal B ) 1 A ,n B, n max(max y cal ; max y cal ) ( x End x Start 1 ) max( y ; y ) n xStart A A B B A ,n B, n Matching of the max. detuning (Signatures not standardised) 3 Matching of the signature derivatives‘ shapes Friedrich Maier: Using Inductive Loop Signature Re-identification for Travel Time Measurement Networks for Mobility, September 27, 2012 Field test Munich 2006 commeaT.E.C. traffic engineering & consulting › >2.000 vehicles at each cross section › ~250 vehicle crossing both cross sections › 38 correct reidentifications, 7 errors Error Examples 4 Friedrich Maier: Using Inductive Loop Signature Re-identification for Travel Time Measurement Networks for Mobility, September 27, 2012 Project AMONES commeaT.E.C. traffic engineering & consulting Aim: › a Evaluation of different methods of network control by analysing simulation results and collected data Test site Bremerhaven (Northern Germany): › 9 intersections controlled by traffic lights › Intersections equipped with inductive loops › Some ANPR-systems temporarilly installed Side effects of collecting inductive signatures: › Evaluation of the ISAR-method using ANPRdata as reference › If the ISAR-method works fine: additional data to evaluate the traffic light control algorithms Adapted from Openstreetmap 5 Friedrich Maier: Using Inductive Loop Signature Re-identification for Travel Time Measurement Networks for Mobility, September 27, 2012 Test site installations commeaT.E.C. traffic engineering & consulting (1) (2) (3) (4) Picture: Example from Munich (1) Control box with detectors and electric power supply (2) Computer to collect the loop detuning (10 PCs in Bremerhaven placed in the control boxes and connected to 20 detectors, sampling rate 125 Hz) (3) ANPR-Camera with (4) Camera computer (in Bremerhaven integrated in the camera body, supervised by the Institute of Road and Transportation Science of the University of Stuttgart) 6 Friedrich Maier: Using Inductive Loop Signature Re-identification for Travel Time Measurement Networks for Mobility, September 27, 2012 AMONES: data collection reality commeaT.E.C. traffic engineering & consulting › Signature analysis for driving direction south: › 2 PCs at (1) – 2 approaches – and (5) › 1 PC at (3), (8) and (9) X › 3 PCs at (4), 2 approaches › ANPR-detection at (1), (5) and (9) › wrong volumes and useless signatures at (8) › High in- and outflow rate between (5) and (9) due to large parking decks › Bad prospects for vehicle re-identification › ~ 25 re-identifications at (5)-(9) per day › Between 80 and 90 re-identifications on the other sections › No improvements with the data from (4) Let‘s see the results from (1)-(3) and (3)-(5) X X X Adapted from Openstreetmap 7 Friedrich Maier: Using Inductive Loop Signature Re-identification for Travel Time Measurement Networks for Mobility, September 27, 2012 AMONES: Route (1,3) commeaT.E.C. traffic engineering & consulting Travel time [s] Travel times at route R(1,3) on February 17th 2009 Time of day 8 › No ANPR-Installation at (3) › Qualitatively similar results on route (3,5) Friedrich Maier: Using Inductive Loop Signature Re-identification for Travel Time Measurement Networks for Mobility, September 27, 2012 AMONES: Route (1,5) commeaT.E.C. traffic engineering & consulting Travel time [s] Travel times at route R(1,5) on February 17th 2009 Time of day › 9 ISAR travel times: addition of routes (1,3) and (3,5) Friedrich Maier: Using Inductive Loop Signature Re-identification for Travel Time Measurement Networks for Mobility, September 27, 2012 AMONES: Re-ident. frequency commeaT.E.C. traffic engineering & consulting 10 Friedrich Maier: Using Inductive Loop Signature Re-identification for Travel Time Measurement Networks for Mobility, September 27, 2012 Potential of travel times commeaT.E.C. v/v0 [-] traffic engineering & consulting ANPR-travel time [min] (route with many links) Function to estimate link-related v/v0: 11 › Using a segemented regression approach › Using ANPR travel times as input data Friedrich Maier: Using Inductive Loop Signature Re-identification for Travel Time Measurement Networks for Mobility, September 27, 2012 Potential of travel times commeaT.E.C. traffic engineering & consulting Temporal offset Temporal offset Functions to estimate link-related v/v0 [-]: Functions to estimate travel times on a route [min]: 12 › Using ANPR-travel times [min] as input data › Using local occupancy [%] as input data › With different temporal offsets › With different temporal offsets Friedrich Maier: Using Inductive Loop Signature Re-identification for Travel Time Measurement Networks for Mobility, September 27, 2012 Potential of travel times commeaT.E.C. traffic engineering & consulting › Estimation of link-related v/v0 with ANPR-travel times as input data Sun,24:00 v/v0 Mon, 0:00 A9 B13 13 A99 Friedrich Maier: Using Inductive Loop Signature Re-identification for Travel Time Measurement Networks for Mobility, September 27, 2012 Last slide commeaT.E.C. traffic engineering & consulting › There is more information in vehicle signatures than only classification: they also allow the collection of travel time data to a certain extend › These travel times can enrich the data basis for the evaluation of traffic management measures › But: the data collection with our algorithm and equipment is still difficult › Travel times include more than only travel times between two cross sections: in combination with historic fleet data they also offer estimations of the current spatial distribution of travel time loss on the detected route There is still a lot of information covered in the data we already collect – we just have to elaborate it! 14 Friedrich Maier: Using Inductive Loop Signature Re-identification for Travel Time Measurement Networks for Mobility, September 27, 2012 The end. commeaT.E.C. traffic engineering & consulting Contact information: 15 › jonas.luessmann@vt.bv.tum.de › florian.schimandls@vt.bv.tum.de › friedrich.maier@commea-tec.de › fritz.busch@vt.bv.tum.de Friedrich Maier: Using Inductive Loop Signature Re-identification for Travel Time Measurement Networks for Mobility, September 27, 2012