Jianyu (Jack) Zhou Advisor: Reginald Golledge Department of Geography University of California Santa Barbara, CA University of California Santa Barbara,

Slides:



Advertisements
Similar presentations
Pseudo-Relevance Feedback For Multimedia Retrieval By Rong Yan, Alexander G. and Rong Jin Mwangi S. Kariuki
Advertisements

AI Pathfinding Representing the Search Space
ADAPTIVE FASTEST PATH COMPUTATION ON A ROAD NETWORK: A TRAFFIC MINING APPROACH Hector Gonzalez, Jiawei Han, Xiaolei Li, Margaret Myslinska, John Paul Sondag.
An Interactive-Voting Based Map Matching Algorithm
Scheduling in Distributed Systems Gurmeet Singh CS 599 Lecture.
Native-Conflict-Aware Wire Perturbation for Double Patterning Technology Szu-Yu Chen, Yao-Wen Chang ICCAD 2010.
On Map-Matching Vehicle Tracking Data
Presented By- Sayandeep Mitra TH SEMESTER Sensor Networks(CS 704D) Assignment.
On the alternative approaches to ITRF formulation. A theoretical comparison. Department of Geodesy and Surveying Aristotle University of Thessaloniki Athanasios.
SLAW: A Mobility Model for Human Walks Lee et al..
Constructing Popular Routes from Uncertain Trajectories Ling-Yin Wei 1, Yu Zheng 2, Wen-Chih Peng 1 1 National Chiao Tung University, Taiwan 2 Microsoft.
Resource Management of Highly Configurable Tasks April 26, 2004 Jeffery P. HansenSourav Ghosh Raj RajkumarJohn P. Lehoczky Carnegie Mellon University.
A Generic Framework for Handling Uncertain Data with Local Correlations Xiang Lian and Lei Chen Department of Computer Science and Engineering The Hong.
Lecture 23 (mini-lecture): A Brief Introduction to Network Analysis Parts of the Network Analysis section of this lecture were borrowed from a UC Berkeley.
Clustered alignments of gene- expression time series data Adam A. Smith, Aaron Vollrath, Cristopher A. Bradfield and Mark Craven Department of Biosatatistics.
Jie Gao Joint work with Amitabh Basu*, Joseph Mitchell, Girishkumar Stony Brook Distributed Localization using Noisy Distance and Angle Information.
1 Learning to Detect Objects in Images via a Sparse, Part-Based Representation S. Agarwal, A. Awan and D. Roth IEEE Transactions on Pattern Analysis and.
Traffic Engineering With Traditional IP Routing Protocols
Localized Techniques for Power Minimization and Information Gathering in Sensor Networks EE249 Final Presentation David Tong Nguyen Abhijit Davare Mentor:
Personal Background  Name: Jianyu (Jack) Zhou  Undergraduate: Geography, Beijing University, P.R. China ( ) Economic geography.  Master’s:
Reduced Support Vector Machine
Multi-modal input interface GPS unit with antenna Multi-modal User-Device Interaction The data collection practice is enhanced from two perspectives: Text-to-speech.
Introduction to Evolutionary Computation  Genetic algorithms are inspired by the biological processes of reproduction and natural selection. Natural selection.
1 Techniques for Efficient Road- Network-Based Tracking of Moving Objects Speaker : Jia-Hui Huang Date : 2006/10/23.
EE 685 presentation Optimization Flow Control, I: Basic Algorithm and Convergence By Steven Low and David Lapsley Asynchronous Distributed Algorithm Proof.
Bioinformatics Challenge  Learning in very high dimensions with very few samples  Acute leukemia dataset: 7129 # of gene vs. 72 samples  Colon cancer.
Elaine Martin Centre for Process Analytics and Control Technology University of Newcastle, England The Conjunction of Process and.
Jianyu (Jack) Zhou Advisor: Reginald Golledge Department of Geography University of California Santa Barbara, CA University of California Santa Barbara,
Trip Planning Queries F. Li, D. Cheng, M. Hadjieleftheriou, G. Kollios, S.-H. Teng Boston University.
GIS Analysis. Questions to answer Position – what is here? Condition – where are …? Trends – what has changed? Pattern – what spatial patterns exist?
Network and Dynamic Segmentation Chapter 16. Introduction A network consists of connected linear features. Dynamic segmentation is a data model that is.
Reducing Uncertainty of Low-sampling-rate Trajectories Kai Zheng, Yu Zheng, Xing Xie, Xiaofang Zhou University of Queensland & Microsoft Research Asia.
Target Tracking with Binary Proximity Sensors: Fundamental Limits, Minimal Descriptions, and Algorithms N. Shrivastava, R. Mudumbai, U. Madhow, and S.
1 Techniques to control noise and fading l Noise and fading are the primary sources of distortion in communication channels l Techniques to reduce noise.
Stochastic Algorithms Some of the fastest known algorithms for certain tasks rely on chance Stochastic/Randomized Algorithms Two common variations – Monte.
FlowString: Partial Streamline Matching using Shape Invariant Similarity Measure for Exploratory Flow Visualization Jun Tao, Chaoli Wang, Ching-Kuang Shene.
Knowledge Discovery and Delivery Lab (ISTI-CNR & Univ. Pisa)‏ www-kdd.isti.cnr.it Anna Monreale Fabio Pinelli Roberto Trasarti Fosca Giannotti A. Monreale,
Visibility Graph. Voronoi Diagram Control is easy: stay equidistant away from closest obstacles.
Glasgow 02/02/04 NN k networks for content-based image retrieval Daniel Heesch.
A Graph-based Friend Recommendation System Using Genetic Algorithm
Hub Location Problems Chapter 12
Use of GIS Methodology for Online Urban Traffic Monitoring German Aerospace Center Institute of Transport Research M. Hetscher S. Lehmann I. Ernst A. Lippok.
Jun-Won Suh Intelligent Electronic Systems Human and Systems Engineering Department of Electrical and Computer Engineering Speaker Verification System.
Clustering Moving Objects in Spatial Networks Jidong Chen, Caifeng Lai, Xiaofeng Meng, Renmin University of China Jianliang Xu, and Haibo Hu Hong Kong.
Discovering Deformable Motifs in Time Series Data Jin Chen CSE Fall 1.
Easiest-to-Reach Neighbor Search Fatimah Aldubaisi.
Preserving Privacy in GPS Traces via Uncertainty- Aware Path Cloaking Baik Hoh, Marco Gruteser, Hui Xiong, Ansaf Alrabady Presented by Joseph T. Meyerowitz.
Chapter 18: Searching and Sorting Algorithms. Objectives In this chapter, you will: Learn the various search algorithms Implement sequential and binary.
EE 685 presentation Optimization Flow Control, I: Basic Algorithm and Convergence By Steven Low and David Lapsley.
NR 143 Study Overview: part 1 By Austin Troy University of Vermont Using GIS-- Introduction to GIS.
University “Ss. Cyril and Methodus” SKOPJE Cluster-based MDS Algorithm for Nodes Localization in Wireless Sensor Networks Ass. Biljana Stojkoska.
L3-Network Algorithms L3 – Network Algorithms NGEN06(TEK230) – Algorithms in Geographical Information Systems by: Irene Rangel, updated Nov by Abdulghani.
Trajectory Data Mining Dr. Yu Zheng Lead Researcher, Microsoft Research Chair Professor at Shanghai Jiao Tong University Editor-in-Chief of ACM Trans.
1 Minimum Error Rate Training in Statistical Machine Translation Franz Josef Och Information Sciences Institute University of Southern California ACL 2003.
LIMITATIONS OF ALGORITHM POWER
2010 IEEE Fifth International Conference on networking, Architecture and Storage (NAS), pp , 2010 作者: Filip Cuckov and Min Song 指導教授:許子衡 教授 報告學生:馬敏修.
Identifying “Best Bet” Web Search Results by Mining Past User Behavior Author: Eugene Agichtein, Zijian Zheng (Microsoft Research) Source: KDD2006 Reporter:
1 Travel Times from Mobile Sensors Ram Rajagopal, Raffi Sevlian and Pravin Varaiya University of California, Berkeley Singapore Road Traffic Control TexPoint.
Exploratory Spatial Optimization in Site Search: A Neighborhood Operator Approach Thomas J. Cova Department of Geography University of Utah and Richard.
The Minimum Label Spanning Tree Problem: Illustrating the Utility of Genetic Algorithms Yupei Xiong, Univ. of Maryland Bruce Golden, Univ. of Maryland.
GEOG 2007A An Introduction to Geographic Information SystemsFall, 2004 C. Earl Queries can be used: to check data correctness to obtain info as steps in.
Curve Simplification under the L 2 -Norm Ben Berg Advisor: Pankaj Agarwal Mentor: Swaminathan Sankararaman.
Tree and Forest Classification and Regression Tree Bagging of trees Boosting trees Random Forest.
GIS Project1 Physical Structure of GDB Geodatabase Feature datasets Object classes, subtypes Features classes, subtypes Relationship classes Geometric.
Network Analyst. Network A network is a system of linear features that has the appropriate attributes for the flow of objects. A network is typically.
Computing and Compressive Sensing in Wireless Sensor Networks
Cristian Ferent and Alex Doboli
Real-time Wall Outline Extraction for Redirected Walking
Globally Optimal Generalized Maximum Multi Clique Problem (GMMCP) using Python code for Pedestrian Object Tracking By Beni Mulyana.
Presentation transcript:

Jianyu (Jack) Zhou Advisor: Reginald Golledge Department of Geography University of California Santa Barbara, CA University of California Santa Barbara, CA UCGIS Summery Assembly, June 28 - July 1, 2005 A Three-Step General Map Matching Method in the GIS Environment: A Travel/Transportation Study Perspective A Three-Step General Map Matching Method in the GIS Environment: A Travel/Transportation Study Perspective

Outline Outline 1.Introduction 2.Problem Statement 3.A general three-step map matching methodology that combines heterogeneous techniques: a) data processing; b) curve- to-curve mapping; c) noise and off-road travel discernment. 4.Conclusion and future research

Introduction Map matching: the process of correlating two sets of geographical positional information.Map matching: the process of correlating two sets of geographical positional information. Application area: travel behavior/transport study, car navigation, car tracking, spatial data conflation, etc.Application area: travel behavior/transport study, car navigation, car tracking, spatial data conflation, etc. Point-to-point matching, point-to-curve matching, curve-to-curve matchingPoint-to-point matching, point-to-curve matching, curve-to-curve matching On-line matching and Off-line matchingOn-line matching and Off-line matching

Map Matching in Travel Study Perspective In travel/transportation studies, map matching is used as a means to transfer the road network attributes to the mapping travel route in order to derive certain travel behavior.In travel/transportation studies, map matching is used as a means to transfer the road network attributes to the mapping travel route in order to derive certain travel behavior. Map matching in travel/transportation studies aims at: 1) identifying the correct road links traversed by the traveler; 2) ensuring that the identified links form a meaningful travel route; and 3) expect to help answer queries beyond the direct matching result.Map matching in travel/transportation studies aims at: 1) identifying the correct road links traversed by the traveler; 2) ensuring that the identified links form a meaningful travel route; and 3) expect to help answer queries beyond the direct matching result.

Problem Statement -matching factor selection Proximity, Heading and others:Proximity, Heading and others: –“GPS position relative to the road link” ; – “average distance traveled on current link” and; – “large distance traveled on current road link” Different select criteria could also result in conflicting matching conclusions.Different select criteria could also result in conflicting matching conclusions. Combine the selecting factorsCombine the selecting factors –A weighting scheme –Bayesian Belief Theory and Dempster-Shafter’s rule

Problem Statement - matching integrity Selection criteria helps identify a series of the matched road segments from the pool of candidate links. They might show up as a group of disconnected “paths.”Selection criteria helps identify a series of the matched road segments from the pool of candidate links. They might show up as a group of disconnected “paths.” Curve-to-curve matching: connecting the GPS points in sequence to form piece-wise linear curvesCurve-to-curve matching: connecting the GPS points in sequence to form piece-wise linear curves Improvement on point-to-point point-to-curve matching: topology relations to guide the search for the next matching candidate and eliminate unreachable links.Improvement on point-to-point point-to-curve matching: topology relations to guide the search for the next matching candidate and eliminate unreachable links.

Defects with Existing Map Matching Methods Weight-based map matching (Yin and Wolfson,2004), Fuzzy-logic based map matching (Syed and Cannon, 2004), General map matching (Quddus et al, 2003)Weight-based map matching (Yin and Wolfson,2004), Fuzzy-logic based map matching (Syed and Cannon, 2004), General map matching (Quddus et al, 2003) Examinations of several map matching methods revealed:Examinations of several map matching methods revealed: –Ignore global information, matching to branch. –Position of the street node and GPS sampling frequency affects matching results. –Doesn’t allow repetitive visit of street links.

Example: Overshoot and Gap

A Three-step General Map Matching Methodology (1) Data Preprocessing - Cluster reduction: –Reduce the systematic noise in the data. Clusters phantom the slow moving speed and random travel directions of the GPS carrier. –DBSCAN (Ester et al., 1996) clustering algorithm for cluster searching since it doesn’t need assumption on the number and shape of the clusters in the input data.

Cluster of GPS points Recovered via DBSCAN Algorithm

A Three-step General Map Matching Methodology (1) Data preprocessing - Density leverage: –Dynamically adjust the GPS data sampling frequency against the model resolution of the base street map. –Generating pseudo GPS points when GPS sampling interval is greater than the length of a traversed street link

Density Leverage

A Three-step General Map Matching Methodology (2) Matching procedure -Curve-to-curve Matching:Matching procedure -Curve-to-curve Matching: –GPS recorded travel trace is treated as a translated and rotated version of the matching route. Dual selection criteria: accumulated 2-norm distance (A2ND) and rotational variation metric (RVM).Dual selection criteria: accumulated 2-norm distance (A2ND) and rotational variation metric (RVM). –Develop a pool of the best candidates simultaneously and incrementally. –A2ND and RVM both serve to constrain the match search in the street network space. Two ranked solution pools are derived in terms of A2ND and RVM separately.

A Three-step General Map Matching Methodology (2) Topological completeness: determine potential turning action around a street intersection:Topological completeness: determine potential turning action around a street intersection: The projection of current GPS point falls on or out of the end point of the current link,The projection of current GPS point falls on or out of the end point of the current link, The projection of the current GPS point comes near to the end point of the current link, but the point’s position is getting away from the current link,The projection of the current GPS point comes near to the end point of the current link, but the point’s position is getting away from the current link, The candidate set of next traversed link: the topologically connected links to the intersection node. Filtered with Prohibited maneuver and turn restriction info.The candidate set of next traversed link: the topologically connected links to the intersection node. Filtered with Prohibited maneuver and turn restriction info.

A Three-step General Map Matching Methodology (2) Use the rank aggregation method to combine the ranking solution list in A2ND and RVM to obtain a combined ordering:Use the rank aggregation method to combine the ranking solution list in A2ND and RVM to obtain a combined ordering: –Kemeny ordering minimizes the sum of the “bubble sort” distances and thus generates the best compromise ranking. It is a NP-hard problem. –Borda’s method: Each candidate in the list is assigned a score of the number of candidates ranked blow it. Its total score across the different ranking list is finally sorted in a descending order. –Footrule optimal aggregation:Given n lists of same set of elements, generate the median permutation of the candidates in the lists.

Sample Match Results

A Three-step General Map Matching Methodology (1) (3) Off-Road Travel/Noise Discernment Dempter-Shafter theory (Shafer, 1976) Yes No Perhaps m30m Yes No Perhaps  Heading AssignmentProximity Assignment

Sample Match Results

Conclusion The method is unique inThe method is unique in –1) data preprocessing with point cluster reduction and density leverage, –2) offering the candidate solution within a pool of “the best” –3) balancing of matching results from multiple matching factors with rank aggregation –4) intelligently utilizing the basic network constraint attributes with “expert rules” to increase the matching accuracy –5) and Dempster belief test to discern the noise and off- road travel