Project: #318 Determining segment and network traffic volumes from video data obtained from transit buses in regular service: Developments and evaluation of approaches for ongoing use across urban networks Progress Report - Reporting Period Ending: March 31, 2023 Principal Investigator: Mark McCord Status: Active Start Date: June 1, 2020 End Date: June 30, 2023 Research Type: Advanced Grant Type: Research Grant Program: FAST Act - Mobility National (2016 - 2022) Grant Cycle: Mobility21 - The Ohio State University Progress Report (Last Updated: April 7, 2023, 8:41 a.m.) % Project Completed to Date: 98 % Grant Award Expended: 97 % Match Expended & Document: 99 USDOT Requirements Accomplishments Goals and Objectives • Refine approaches to determine traffic volumes and related network measures in urban areas from video sensors mounted on transit buses in operational service • Demonstrate performance of the method • Motivate practical use of the method and begin applications • Expand method to an approach for ongoing monitoring of traffic measures Accomplishments • One new undergraduate student was recruited and trained in vehicle digitization by a current graduate student. • A large empirical data collection of concurrent manually observed and video data on the campus of The Ohio State University (OSU) was undertaken on November 1, 2022. The data were subsequently processed and analyzed for research, education, and outreach purposes. The data collection and processing were used in a term project of a Civil Engineering class consisting of a mix of 28 undergraduate and graduate students. The vehicle miles travelled estimated (see below) are presented to OSU transportation planning and operations managers. • Regarding the data collection on 11/1/2022 and the subsequent processing: o Approximately 140 hours of bus-based video imagery from OSU Campus Area Bus Service (CABS) busses while in regular service were obtained on 3 different bus routes and preprocessed into time- and location-specific vehicle observations. Vehicle observations were then processed into 420 segment-direction-hours of traffic volumes. o Fifty-six (56) segment-direction-hours of manually collected traffic volumes on the OSU roadway network were obtained and processed • Regarding analysis of the processed data from the 11/1/2022 data collection: o An estimate of vehicle miles traveled (VMT) during a 10-hour period (8 am- 6 pm) over a network of 6.1 direction-miles of OSU roadways was determined from the hourly volumes derived from the bus video imagery data o VMT values over a subset of the roadway network and time-of-day period that is common among the 2022 study conducted during this reporting period and the previously conducted 2021, 2020, 2019, and 2018 studies were determined and compared to indicate reduced travel during the COVID lockdown (2020) period, increases in 2021 and 2022 periods, and stability of the highest VMT values obtained in the pre-COVID (2018 and 2019) periods o Hourly VMT estimates on the common network for the five different years were determined and analyzed to investigate time-of-day traffic (TOD) patterns. TOD patterns during the COVID lockdown (2020) and 2021 periods were similar and different from the TOD patterns in the pre-COVID (2018, 2019) periods, which were similar to each other. The TOD patterns in the 2022 period appear to be “between” those of the pre-COVID periods (2018 and 2019) and the COVID lockdown (2020) and 2021 periods. • Until December 2022, bus-based video imagery files were downloaded on a weekly basis for one segment-direction for two different hours on different days of the week while traffic volumes were manually observed for the same segment-direction-hours to serve as ground truth. The downloaded video-based imagery is being processed to estimate segment-direction-hour traffic volumes, which are being compared to the manually collected ground truth to investigate accuracy in estimating an average-day volume from bus-based video imagery over multiple days. Empirical results based on the manual and video data processed thus far show that differences between video-based and ground-truth volumes estimates decrease appreciably when estimating traffic volumes on an “average day” compared to an individual day. The ability to capture day-to-day and hourly variations in traffic volumes from bus-based imagery is also being investigated. • Preliminary investigations demonstrated the potential of obtaining improved accuracy in video-based volume estimates by accounting for queues of vehicles observed in the imagery in various ways. Training and professional development • Three graduate students, three undergraduate students, and one research engineer were involved with various efforts of this project. • A graduate student continued to take responsibility for training students on various video imagery processing tasks and supervising data collection efforts. Dissemination • A presentation based on project results was made at the January 2023 annual meeting of the Transportation Research Board. The presentation focused on the good accuracy in estimating VMT and time-of-day patterns in traffic volumes across networks when using video-based traffic volume estimated with methods developed in this project and the much better accuracy in these estimates compared to commercially available estimates determined from Location Based Services data. • A submission, “Evaluating the use of bus-based video imagery to monitor VMT on an urban network,” was accepted for presentation at the World Conference on Transport Research in Montreal, Canada, July 2023. • Investigators continued to meet regularly with administrators from The Ohio State University’s Transportation and Traffic Management (TTM) to update them on this and other projects that address practical issues of interest to TTM operations. The November 2022 VMT estimates were provided to TTM as part of these updates. Upon request of the investigators, TTM provides the video imagery used for the research, outreach, and educational tasks in this project. Plans for upcoming period • Process additional video imagery into digital location- and time-specific vehicle observations • Determine volume estimates from additional processed video imagery • Continue to validate the benefits of estimating average-day traffic volumes in a time-of-day period relative to estimating single day traffic volumes in the time-of-day period • Continue to investigate the ability to determine daily and hourly variations in traffic volumes from bus-based video for use in ongoing traffic monitoring • Continue interactions with OSU Transportation and Traffic Management (TTM) • Write and submit a paper on the recent developments for possible publication • Write and submit final report Impacts • Regular meetings with The Ohio State University (OSU) Transportation and Traffic Management (TTM) office continue to generate interest in the empirical traffic flow estimates being produced and motivate ongoing collaboration in project research and outreach efforts • Presentation of project results in various conferences emphasize the much better accuracy in estimated traffic volumes and network travel measures that can be obtained from bus-based video imagery compared to Location Based Services data used in practice. Other Physical collections: During the period video imagery and manually collected data were obtained Curricula: During the period, the motivation for traffic volume estimation using bus-based video and general data collection approach used in this study were presented in a required, undergraduate Civil Engineering with approximately 70 students. The traffic volume estimation using bus-based video and the empirical data collection and volume estimations served as the basis of a term project in one undergraduate/graduate Civil Engineering class consisting of 28 students. Outcomes New Partners Investigators continued to work closely with Transportation and Traffic Management (TTM) at The Ohio State University (OSU). TTM oversees all OSU transportation operations, other than parking, and operates the Campus Area Bus Service (CABS), with a fleet of approximately fifty 40-foot transit buses serving close to 3.5 million passengers per year (approximately 5 million per year, pre-pandemic) on fixed route scheduled services. Issues None