The objective of this project is to develop an inductive loop based technology for monitoring the travel time and origin-destination performance of vehicles that augments a Bluetooth-based travel time system now under development. To their advantage, loop signatures characterize almost 100 percent of the vehicles traveling over them while Bluetooth technology characterizes none of them. Bluetooth always correctly re-identifies vehicles while loops may mismatch or miss signature matches. In Phase I, field tests must demonstrate that the technology can sense and track vehicles between two points with vehicle classification. Statistical characterizations of the number of vehicles that can be identified at the first location and then re-identified at the second location must be made. These should be compared to ground truth against the total vehicle population traveling between the two points. This will demonstrate the potential of the new technology. The loop signature sensor hardware may be a device previously developed by the Small Business Innovation Research proposer, or one of its partners, or may be developed or developed further under this project. Standard loop detector controller cards sample traffic at a rate of 60 hertz (Hz); however, they frequently do not push detailed information back to the traffic management center. Instead, they calculate and then aggregate values, such as volumes and occupancies, at up to 30-second intervals before sending this data back to the central processing system. Past approaches to loop-based vehicle re-identification have focused on creating more sophisticated controller card hardware. These approaches aim to create higher-frequency controller cards that sample at rates of 20 kilohertz (kHz) to 100 kHz. While these approaches can create high-resolution signatures of vehicles for matching, they are extremely difficult to deploy at large scales because they require the replacement of controller cards with new, expensive hardware. This hardware deployment in and of itself may make a loop-based vehicle re-identification scheme more expensive than a Bluetooth-based solution. This research proposes to use 60 Hz samples and data fusion techniques to create a software-based signature-matching algorithm. The core strength of this approach is that it creates a clear path toward widespread deployment: it can be implemented in software at a centralized location. Thus, agencies will be able to leverage their existing loop and controller infrastructure for re-identification.
This phase I project was successful and established the possibility of obtaining travel time data using high frequency conventional loop data. A phase II followup project was recommended.