Vision Based Lane Change Detection Using True Flow Features

Zeisler, Jöran; Schonert, Fabian; Johne, M.; Haltakov, Vladimir

doi:10.1109/itsc.2017.8317954

Cited by 5 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zeisler et al [15] followed a different scheme by using raw video data instead of high-level features. Lane changes are predicted using optical flow of observed vehicles.…”

Section: Related Workmentioning

confidence: 99%

Attention-based Lane Change Prediction

Scheel

Nagaraja

Schwarz

et al. 2019

2019 International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Lane change prediction of surrounding vehicles is a key building block of path planning. The focus has been on increasing the accuracy of prediction by posing it purely as a function estimation problem at the cost of model understandability. However, the efficacy of any lane change prediction model can be improved when both corner and failure cases are humanly understandable. We propose an attentionbased recurrent model to tackle both understandability and prediction quality. We also propose metrics which reflect the discomfort felt by the driver. We show encouraging results on a publicly available dataset and proprietary fleet data.

show abstract

“…Zeisler et al [15] followed a different scheme by using raw video data instead of high-level features. Lane changes are predicted using optical flow of observed vehicles.…”

Section: Related Workmentioning

confidence: 99%

Attention-based Lane Change Prediction

Scheel

Nagaraja

Schwarz

et al. 2019

2019 International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

show abstract

“… Good detection  Good localization of edge points  Only one response to a single edge In [16] True flow as an addition to conventional optical flow is introduced. Translational and rotational influence of ego motion is eliminated, allowing to estimate the observed object behaviour.…”

Section: Asian Journal Of Convergence In Technologymentioning

confidence: 99%

Vehicle Lane Detection and Tracking System for Car Safety

Yelwande¹,

Jahagirdar²

2019

AJCT

View full text Add to dashboard Cite

Advanced DrivingAssistance Systems(ADASs) is important technology for safety of car as well as car driver and lane detection is a main purpose of current Advanced Driving Assistance Systems (ADASs). Most of the previous results focuses on the study of vision-based methods. In this paper, previous lane detection methods and algorithms are reviewed. Further, the limitations are studied and analyzed to evaluate the more robust detection systems and to improve the accuracy of detection system.

show abstract