Cooperative Tracking of Cyclists Based on Smart Devices and Infrastructure

Abstract

In future traffic scenarios, vehicles and other traffic participants will be interconnected and equipped with various types of sensors, allowing for cooperation based on data or information exchange. This article presents an approach to cooperative tracking of cyclists using smart devices and infrastructure-based sensors. A smart device is carried by the cyclists and an intersection is equipped with a wide angle stereo camera system. Two tracking models are presented and compared. The first model is based on the stereo camera system detections only, whereas the second model cooperatively combines the camera based detections with velocity and yaw rate data provided by the smart device. Our aim is to overcome limitations of tracking approaches based on single data sources. We show in numerical evaluations on scenes where cyclists are starting or turning right that the cooperation leads to an improvement in both the ability to keep track of a cyclist and the accuracy of the track particularly when it comes to occlusions in the visual system. We, therefore, contribute to the safety of vulnerable road users in future traffic.

The IMPTC Dataset: An Infrastructural Multi-Person Trajectory and Context Dataset

“…Ko-PER investigates prediction behavior models for VRUs crossing the street, DeCoInt 2 covers VRU intention detection under the cooperative aspect between intelligent infrastructure and mobile research vehicles. For motion anticipation, Reitberger et al [11] provided a cooperative tracking algorithm for cyclists, and Bieshaar et al [12] used Convolutional Neural Networks to detect starting movements of cyclists. Zernetsch et al [13] developed a probabilistic VRU trajectory forecasting method.…”

“…The procedure for all sub-classes is the same. We describe the method for cyclists in [11], going further in detail about how we initialize tracks and assign measurements.…”

Economic analysis of vehicle infrastructure cooperation for driving automation

“…Given the challenges inherent to this vehicle-centric approach, researchers, investors, and the public sector have realized that placing some sensors and algorithms on the infrastructure may be a more effective way to enable automated driving. Thus, researchers have devoted themselves to the design, modeling and assessment of sensor networks to aid with vehicle perception and planning (Rebsamen et al, 2012;Jun and Markel, 2017;Leone et al, 2017;Bieshaar et al, 2017;Eilbrecht et al, 2017;Reitberger et al, 2018;Jayaweera et al, 2019;Kong, 2020) and improve a number of traffic performance metrics (Dey et al, 2016;Xie and Wang, 2018;Yu et al, 2019;Yang et al, 2021). Public agencies also see the future of transportation as closely tied to a vehicle-infrastructure cooperative approach.…”