The Intelligent Mobility Meter (IMM) is a portable data acquisition and analysis platform for the collection of fine-grained statistics on pedestrian, cyclist and vehicular traffic. As the capabilities of the Intelligent Mobility Meter (IMM) mature, it has the potential to reach partners beyond the City of Pittsburgh and the State of Pennsylvania. The objective of this project is to create modern tools for the IMM to engage with state, industry, and non-profit organizations throughout the whole of the US. In particular, this project will focus on 1) the creation of a modern data portal, where participating organizations will be able to submit video data and download the statistics compiled by the IMM algorithms; and 2) further refinement and automation of the IMM tools to support the new data portal.
The objective of the Intelligent Mobility Meter (IMM) project is to provide actionable data on pedestrian, cyclist and motor vehicle traffic. The IMM has grown out of three UTC-sponsored projects (“Automatic Counting of Pedestrians and Cyclists”, “Measuring Pedestrian Wait-Time at Intersections”, and “The Intelligent Mobility Meter – Portable Fine-Grained Data Collection and Analysis of Pedestrian, Cyclist, and Motor Vehicle Traffic”) to create automatic and human-assisted tools for counting and analyzing car, bike, and pedestrian traffic. The IMM project recently won Mobility21’s Smart Mobility Challenge Award to provide its traffic measuring tools for use in two real-world traffic studies for partner entities in the Southwestern Pennsylvania area (Municipality of Bethel Park and City of Greensburg). Exposure from this award as well as outreach work by the IMM’s PI has led to a number of other organizations showing interest in submitting their data for counting and analysis. These organizations, which include the Virginia DOT, City of Boulder, CO, and industry member Alta Planning + Design, already possess video data recording equipment, but are looking for cost-effective ways to analyze it. Because these possible partners are not local to the Pittsburgh area, transferring and organizing their data (which, in one exemplar case, included 24x7 video data for a week at multiple locations), as well as effectively communicating results is the primary bottleneck for a successful partnership. The objective of this project is to remove such bottlenecks and significantly increase number of possible partnerships with organizations outside the local Pittsburgh area. These national-level partnerships will dramatically increase the visibility of the IMM project as well as the Mobility21 UTC. Using the relationship with the City of Boulder, CO as an example, we intend to develop a modern web portal where entities can: 1. Upload their video data, organized by projects and data-collection locations; 2. Add notes to their data so as to inform the IMM team on the relevant statistics to compile; 3. Receive messages from the IMM team and review the status of the data analysis; 4. Download the analysis results In tandem with the development of the data portal, this project will also support the further refinement of the IMM tools, including using the submitted data to improve the detection, classification and tracking algorithms in the IMM, as well as the development of algorithms to automate and support the operation of the web portal. We expect the entities using the data portal will upload significant datasets, possibly featuring heavy vehicular, bicycle, and pedestrian traffic. The compilation and study of such datasets is likely to improve the computer vision methods used by the IMM, pushing forward the state of the art in automatic car, bike and pedestrian detection.
July 1, 2018 – Project Start Date July 1 – October 31, 2018 – Preliminary data portal design and specifications November 1, 2018 – January 31, 2019 – Implementation of preliminary data portal design February 1 – April 31, 2019 – Testing of all website functionality with selected partner (tentatively, City of Boulder, CO), identification of areas of improvement and redesign for final data portal version May 1 – June 30, 2019 – Implementation of final data portal version June 30, 2019 – Project End Date, Availability of data portal opened to all US partners
The expected deployment of the data portal is to occur in two phases. All data portal functionality will be present for both phases, including the following capabilities: a. Partner video data upload, b. Partner ability to organize data into projects and data-collection locations; c. Partner ability to add notes to each data collection event; d. Partner ability to receive notes form the IMM team; e. Partner ability to review status of data analysis f. Partner ability to download results of data analysis The schedule for both phases will be: - On or before January 31, 2019: Preliminary data portal deployment for selected partners - On or before June 30, 2019: Deployment of data portal for all US partners
For the data portal itself: - Implementation of all functionality mentioned in this proposal; - Deployment of preliminary data portal version at half-way point in the project and final data portal version at the end of the project. For the partners using the portal - At least one entity outside the Southwestern PA region successfully using the data portal; - Upload of no less than 10 hours of new traffic data by at least one partner; - Analysis of all uploaded data and delivery of relevant statistics to project partners; - Use of uploaded data to refine the performance of IMM’s detection, classification and tracking algorithms.
Name | Affiliation | Role | Position | |
---|---|---|---|---|
bpires@cmu.edu | Pires, Bernardo | Robotics Institute | PI | Other |
Type | Name | Uploaded |
---|---|---|
Data Management Plan | FY19_UTC_DMP_Pires_IMM-Data-Portal.docx | Jan. 15, 2018, 12:14 a.m. |
Progress Report | 189_Progress_Report_2019-03-30 | March 27, 2019, 6:30 a.m. |
Final Report | Final_Report_-_189.pdf | Jan. 4, 2021, 5:30 a.m. |
No match sources!
No partners!