Classification for Safety-Critical Car-Cyclist Scenarios Using Machine Learning

Cara, Irene; Gelder, Erwin de

doi:10.1109/itsc.2015.323

Cited by 18 publications

(17 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zernetsch et al (2016) collected data at a single intersection for path prediction of a starting cyclists, and Hubert et al (2017) used the same data to find indicators of cyclist starting behavior. Some studies have used naturalistic data to detect and classify critical vehicle-cyclist interactions at intersections (Sayed et al 2013;Vanparijs et al 2015;Cara and de Gelder 2015), while others use simulations to study bicycle motion at intersections Zhang et al 2017).…”

Section: Context Cues For Vru Behaviorsmentioning

confidence: 99%

Context-Based Path Prediction for Targets with Switching Dynamics

et al. 2018

View full text Add to dashboard Cite

Anticipating future situations from streaming sensor data is a key perception challenge for mobile robotics and automated vehicles. We address the problem of predicting the path of objects with multiple dynamic modes. The dynamics of such targets can be described by a Switching Linear Dynamical System (SLDS). However, predictions from this probabilistic model cannot anticipate when a change in dynamic mode will occur. We propose to extract various types of cues with computer vision to provide context on the target's behavior, and incorporate these in a Dynamic Bayesian Network (DBN). The DBN extends the SLDS by conditioning the mode transition probabilities on additional context states. We describe efficient online inference in this DBN for probabilistic path prediction, accounting for uncertainty in both measurements and target behavior. Our approach is illustrated on two scenarios in the Intelligent Vehicles domain concerning pedestrians and cyclists, so-called Vulnerable Road Users (VRUs). Here, context cues include the static environment of the VRU, its dynamic environment, and its observed actions. Experiments using stereo vision data from a moving vehicle demonstrate that the proposed approach results in more accurate path prediction than SLDS at the relevant short time horizon (1 s). It slightly outperforms a computationally more demanding state-of-the-art method.

show abstract

Section: Context Cues For Vru Behaviorsmentioning

confidence: 99%

Context-Based Path Prediction for Targets with Switching Dynamics

et al. 2018

View full text Add to dashboard Cite

show abstract

“…[1] indicates that pedestrian tracking is becoming increasingly robust, and research is shifting to highlevel tasks of predicting future traffic situations to inform automated decision making in ADAS. Besides pedestrians, a review of severe and fatal car-cyclist accidents showed that cyclists at crossings are another important safety case [2].…”

Section: Related Workmentioning

confidence: 99%

“…For pedestrians, various approaches focus first on classifying current traffic behavior [2], [4], [13], which can inform future behavioral events [6]. But predictive models of a pedestrian's path must represent spatial uncertainty too.…”

Section: Related Workmentioning

confidence: 99%

“…Cyclists at crossings are an especially important safety case for moving vehicles [2], which means it is important to study the problem from a vehicle's point of view. There has been work on how cyclist motion evolves at a crossing [7], [8], but this was from static viewpoints outside of the vehicle.…”

Section: Related Workmentioning

confidence: 99%

“…This is especially important in the urban environment with many Vulnerable Road Users (VRUs). For automated driving however, the system should not only detect VRUs, but also predict their trajectories to anticipate and avoid potentially dangerous situations [1], [2]. Most literature on VRU path prediction focuses on pedestrians (e.g.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Using road topology to improve cyclist path prediction

Pool

Kooij

Gavrila

2017

2017 IEEE Intelligent Vehicles Symposium (IV)

View full text Add to dashboard Cite

Abstract-We learn motion models for cyclist path prediction on real-world tracks obtained from a moving vehicle, and propose to exploit the local road topology to obtain better predictive distributions. The tracks are extracted from the Tsinghua-Daimler Cyclist Benchmark for cyclist detection, and corrected for vehicle egomotion. Tracks are then spatially aligned to local curves and crossings in the road. We study a standard approach for path prediction in the literature based on Kalman Filters, as well as a mixture of specialized filters related to specific road orientations at junctions. Our experiments demonstrate an improved prediction accuracy (up to 20% on sharp turns) of mixing specialized motion models for canonical directions, and prior knowledge on the road topology. The new track data complements the existing video, disparity and annotation data of the original benchmark, and will be made publicly available.

show abstract