Temporal Enhanced Floating Car Observers

TL;DR

This work demonstrates that even a small penetration rate of FCOs can identify a significant amount of vehicles at a given intersection, and develops a data-driven strategy, utilizing sequences of Bird’s Eye View representations of detected vehicles and deep learning models to bring currently undetected vehicles into view in the present moment.

Abstract

Floating Car Observers (FCOs) are an innovative method to collect traffic data by deploying sensor-equipped vehicles to detect and locate other vehicles. We demonstrate that even a small penetration rate of FCOs can identify a significant amount of vehicles at a given intersection. This is achieved through the emulation of detection within a microscopic traffic simulation. Additionally, leveraging data from previous moments can enhance the detection of vehicles in the current frame. Our findings indicate that, with a 20-second observation window, it is possible to recover up to 20\% of vehicles that are not visible by FCOs in the current timestep. To exploit this, we developed a data-driven strategy, utilizing sequences of Bird's Eye View (BEV) representations of detected vehicles and deep learning models. This approach aims to bring currently undetected vehicles into view in the present moment, enhancing the currently detected vehicles. Results of different spatiotemporal architectures show that up to 41\% of the vehicles can be recovered into the current timestep at their current position. This enhancement enriches the information initially available by the FCO, allowing an improved estimation of traffic states and metrics (e.g. density and queue length) for improved implementation of traffic management strategies.

Figures (12)

• Figure 1: SUMO digital twin of the traffic network of Ingolstadt created by harth2021automated with a highlight set for the intersection investigated in this work (left) and an example BEV representation as input for the BEV detection approach (right).
• Figure 2: Sequential visualization of FCOs (blue), detected vehicles (green), and undetected vehicles (red) across scenarios at one-second intervals. The BEV emulation approach is utilized to determine the 3D detectability of vehicles.
• Figure 3: Distribution of $V_{d,t}$ relative to $V_t$ at varying penetration rates of FCOs across the investigated intersection over the specified time frame. Vertical dotted lines denote mean values.
• Figure 4: Mean difference in $V_{s,t}$ and $V_{d,t}$ relative to $V_t$ across various FCO penetration rates and sequence lengths showing the temporal enhancing potential.
• Figure 5: Examplary sequence $S \in {\{0,1\}}^{6 \times 512 \times 512}$ showing $V_{d,t-5s}$ to $V_{d,t}$ in BEV representation. The sequence serves as the input to the spatiotemporal models.