Difference between revisions of "Traffic Estimation From Vehicle Data"
(Created page with "{{StudentProjectTemplate |Summary=Estimate traffic density based on logged vehicle data |Keywords=Data Mining |TimeFrame=Spring 2014 |Prerequisites=Cooperating Intelligent Sys...") |
|||
| Line 2: | Line 2: | ||
|Summary=Estimate traffic density based on logged vehicle data | |Summary=Estimate traffic density based on logged vehicle data | ||
|Keywords=Data Mining | |Keywords=Data Mining | ||
| − | |TimeFrame=Spring | + | |TimeFrame=Spring 2016 |
|Prerequisites=Cooperating Intelligent Systems and Learning Systems courses | |Prerequisites=Cooperating Intelligent Systems and Learning Systems courses | ||
Some level of Matlab and/or Python programming knowledge is recommended | Some level of Matlab and/or Python programming knowledge is recommended | ||
Revision as of 12:56, 14 October 2015
| Title | Traffic Estimation From Vehicle Data |
|---|---|
| Summary | Estimate traffic density based on logged vehicle data |
| Keywords | Data Mining |
| TimeFrame | Spring 2016 |
| References | |
| Prerequisites | Cooperating Intelligent Systems and Learning Systems courses
Some level of Matlab and/or Python programming knowledge is recommended |
| Author | |
| Supervisor | Slawomir Nowaczyk, Iulian Carpatorea |
| Level | Master |
| Status | Open |
The goal of the project is to design a method for estimating traffic flow and density from a fixed set of sensors on-board Volvo trucks that include information about vehicle operation (such as speed, engine load, accelerator pedal position, etc.), GPS coordinates as well as environment characteristics (such as road geometry, ambient temperature, date, etc.)
Our intention is to use the results of this work within the Learning Fleet research project as part of research cooperation between Halmstad University and Volvo Technology in Göteborg.
Preliminary workplan:
WP1: Investigate available data in order to find suitable candidate signals for traffic flow and density estimation
WP2: Develop and test algorithms based on the previously selected signals (or their subsets)
WP3: Compare various algorithms and highlight the criteria of their applicability, as well as pros and cons of selected approaches
