3 code implementations • 12 Apr 2021 • Dongfang Yang, Haolin Zhang, Ekim Yurtsever, Keith Redmill, Ümit Özgüner
This work addresses the above limitations by introducing a novel neural network architecture to fuse inherently different spatio-temporal features for pedestrian crossing intention prediction.
no code implementations • 18 Jan 2021 • Fatema T. Johora, Dongfang Yang, Jörg P. Müller, Ümit Özgüner
The results indicate that our model can realistically simulate a wide range of motion behaviors and interaction scenarios, and that adding different motion patterns of pedestrians into our model improves its performance.
1 code implementation • 3 Nov 2020 • Haolin Zhang, Dongfang Yang, Ekim Yurtsever, Keith A. Redmill, Ümit Özgüner
The main strategy is to depend solely on the 2D vision for recognizing object class, as object shape does not change drastically with an increase in depth, and use pointcloud data for object localization in the 3D space for faraway objects.
1 code implementation • 7 Jul 2020 • Dongfang Yang, Ekim Yurtsever, Vishnu Renganathan, Keith A. Redmill, Ümit Özgüner
If a violation is detected, a non-intrusive audio-visual warning signal is emitted without targeting the individual who breached the social distancing measure.
2 code implementations • 1 Feb 2019 • Dongfang Yang, Linhui Li, Keith Redmill, Ümit Özgüner
The final trajectories of pedestrians and vehicles were refined by Kalman filters with linear point-mass model and nonlinear bicycle model, respectively, in which xy-velocity of pedestrians and longitudinal speed and orientation of vehicles were estimated.