Login

Project

#59 Applied Vehicle, Bicycle and Pedestrian Automated Counting Technologies for the Intelligent Mobility Meter


Principal Investigator
Bernardo Pires
Status
Active
Start Date
Sept. 1, 2017
End Date
Aug. 30, 2019
Research Type
Applied
Grant Type
Research
Grant Program
Private Funding
Grant Cycle
2017 Smart Mobility Challenge
Visibility
Public

Abstract

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. This project proposes to further improve the IMM performance while tackling challenges that affect the local governments in Southwestern Pennsylvania. Specifically, we propose to: 1) collect novel real-world large-scale datasets of visual data that will help further improve the automated detection, classification and tracking algorithms of the IMM; and 2) provide real-world valuable traffic studies and actionable information to local government entities. To achieve this goals the project is partnering with the Municipality of Bethel Park and the City of Greensburg, and with leading engineering firm Michael Baker International. The local governments will guide the deployment of the meter to the locations that are most critical for infrastructure decision making and pledge to deploy the portable meters as necessary for the collection of the data. The CMU research group will use the data to improve the IMM algorithms and to analyze the specific traffic needs and challenges as requested by the municipalities. Finally, Michael Baker International will provide the necessary traffic engineering expertise and guidance so that the project’s output will be useful and actionable for the municipalities.    
Description
The Intelligent Mobility Meter (IMM) is a technological response to the need for more and better traffic information. It started as a bike and pedestrian counter on the UTC-supported project “Automatic Counting of Pedestrians and Cyclists”. The project “Measuring Pedestrian Wait-Time at Intersections” expanded the IMM’s capabilities to include wait-time measurement, something that is not possible with other counters. The ongoing project, “The Intelligent Mobility Meter – Portable Fine-Grained Data Collection and Analysis of Pedestrian, Cyclist, and Motor Vehicle Traffic” is expanding the IMM’s capabilities to include motor vehicle counting as well as traffic flow measurements.

In this project, we propose to continue developing the IMM and to, for the first time, apply its capabilities to produce two traffic studies for partner entities using data collected and parsed by the meter. The studies will be conducted by CMU students in partnership with Michael Baker Corporation and will be supervised by the Co-PI, Greg Cerminara (CMU Adjunct Professor, Vice-President and Pittsburgh Surface Transportation Principal, Michael Baker Corporation). Each study will target key infrastructure for the government partners: The Municipality of Bethel Park and the City of Greensburg. The final target sites for the studies have not been concluded, and will be dependent on level of funding. At this point, we intend to target the Central Business District in Bethel Park and the midblock crosswalk in front of the Westmoreland County Building and Courthouse in Greensburg. 

The initial plan is for the study in Bethel Park to target the unofficial Central Business District were a number of infrastructure is already established.  Namely, the West Library Avenue has two lanes of traffic, there are central light rail tracks, and Brightwood Road has two lanes of traffic. These thoroughfares have traffic from vehicles, bicycles, pedestrians, and transit riders. The traffic study proposed for Bethel Park would attempt to answer the question of whether the Central Business District would benefit from converting West Library Avenue and Brightwood Road each into alternate one-way streets and using the extra lanes on each side to accommodate bicycle lanes or additional on-street parking on West Library Avenue and bicycle lanes or a better sidewalk network along Brightwood Road.

Similarly, the initial plan is for the study in Greensburg to target the midblock crosswalk in front of the Westmoreland County Building and Courthouse. The crosswalk is located along the very busy and congested Main Street (State Route 66) and is heavily utilized by employees and visitors. Even though the crosswalk is marked and signed, it still is an unsafe crossing due to the number of vehicles that conflict with the heavy pedestrian movements. The City is requesting CMU to study this midblock crosswalk and to develop SMART Mobility solutions to this problem.

In addition to the production of the studies for the municipalities, the collected data will be fundamental in improving the detection, classification and tracking algorithms in the IMM. Since the areas targeted will feature heavy vehicular, bicycle, and pedestrian traffic, it is likely that state of the art computer vision methods will be necessary for analyzing and interpreting the collected imagery. In this way, the study and collected datasets will not only help the targeted municipalities, but also push forward the state of the art in automatic car, bike and pedestrian detection.    
Timeline
October 1, 2017 – Project Start Date
October 1 – 31, 2017 – Decision of exact locations and times for data collection
November 1 – January 31, 2017 – Data Collection
February 1 – April 31, 2018 – Data Analysis and Counting Results
May 1 – August 31, 2018 – Preparation of Traffic Studies
September 1 – September 31, 2018 – Traffic studies are shared with municipalities
September 30, 2018 – Project End Date
    
Deployment Plan
Expected deployment of mobile Intelligent Mobility Meters in the Municipality of Bethel Park and the City of Greensburg during the months of November ’17, December ’17 and January ’18. 

Deployments will target:
- Then Central Business District in the Municipality of Bethel Park; and
- The mid-block crosswalk in front of the Westmoreland County Building and Courthouse in Greensburg.     
Expected Accomplishments and Metrics
For the improvement of the IMM’s algorithms:

- Collection of no less than 20 hours of new traffic data;
- Collection significant amount of both vehicle and pedestrian data (expected at least 1,000 vehicles and 100 pedestrians);
- Analysis of the data and incorporation of findings to refine the performance of IMM’s detection, classification and tracking algorithms.

For the Municipalities:

- Production of a traffic study targeting the Central Business District in Bethel Park;
- Production of a traffic study targeting the midblock crosswalk in front of the Westmoreland County Building and Courthouse in Greensburg.
    

Individuals Involved

Email Name Affiliation Role Position
GCerminara@mbakerintl.com Cerminara, Greg CEE Co-PI Other
bpires@cmu.edu Pires, Bernardo Robotics Institute PI Other

Budget

Amount of UTC Funds Awarded
$99838.00
Total Project Budget (from all funding sources)
$

Documents

Type Name Uploaded
Data Management Plan IMM_-_Pires_-_Data_Management_Plan_e0aTF7U.docx Oct. 16, 2017, 8:39 a.m.
Presentation How Innovative Technology Can Improve Mobility, Featuring the Awardees from the Smart Mobility Challenge March 30, 2018, 11:25 p.m.
Progress Report 59_Progress_Report_2018-03-30 March 30, 2018, 11:25 p.m.

Match Sources

No match sources!

Partners

No partners!