Abstract
For smart mobility, autonomous vehicles, and advanced driver-assistance systems (ADASs), perception of the environment is an important task in scene analysis and understanding. Better perception of the environment allows for enhanced decision making, which, in turn, enables very high-precision actions. To this end, we introduce in this work a new real-time deep learning approach for 3D multi-object detection for smart mobility not only on roads, but also on railways. To obtain the 3D bounding boxes of the objects, we modified a proven real-time 2D detector, YOLOv3, to predict 3D object localization, object dimensions, and object orientation. Our method has been evaluated on KITTI’s road dataset as well as on our own hybrid virtual road/rail dataset acquired from the video game Grand Theft Auto (GTA) V. The evaluation of our method on these two datasets shows good accuracy, but more importantly that it can be used in real-time conditions, in road and rail traffic environments. Through our experimental results, we also show the importance of the accuracy of prediction of the regions of interest (RoIs) used in the estimation of 3D bounding box parameters.
Highlights
To improve safety in intelligent mobility and to make driving more autonomous, vehicles must have a better perception of their environment
We trained our method on the KITTI dataset dedicated to 3D detection on the same training split used by the authors of [10] containing half of the samples and we performed the evaluation on the other samples
We have introduced a new method of real-time 3D multi-object detection and localization for both road and railway smart mobility
Summary
To improve safety in intelligent mobility and to make driving more autonomous, vehicles must have a better perception of their environment. This perception must guarantee good detection of objects, but more generally good interpretation of the scenes. The problem is quite similar to that in the road sector In these two types of environment, the objects of interest are vehicles, pedestrians, buses, cyclists, trees, etc. While the road sector is widely covered in the scientific literature, this is not the case for the rail sector This is in part due to the lack of specific datasets. The estimation of those parameters is an important task that should be performed by an advanced driver-assistance systems (ADAS)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
