Next Article in Journal
Investigating Semantic Augmentation in Virtual Environments for Image Segmentation Using Convolutional Neural Networks
Next Article in Special Issue
A Fast and Accurate Approach to Multiple-Vehicle Localization and Tracking from Monocular Aerial Images
Previous Article in Journal
Data Augmentation Using Background Replacement for Automated Sorting of Littered Waste
 
 
Article

Real-Time 3D Multi-Object Detection and Localization Based on Deep Learning for Road and Railway Smart Mobility

1
Normandie Univ, UNIROUEN, ESIGELEC, IRSEEM, 76000 Rouen, France
2
Haddad is with SEGULA Technologies, 19 rue d’Arras, 92000 Nanterre, France
3
Normandie Univ, UNIROUEN, UNILEHAVRE, INSA Rouen, LITIS, 76000 Rouen, France
*
Authors to whom correspondence should be addressed.
These authors contributed equally to this work.
J. Imaging 2021, 7(8), 145; https://doi.org/10.3390/jimaging7080145
Received: 25 June 2021 / Revised: 22 July 2021 / Accepted: 9 August 2021 / Published: 12 August 2021
(This article belongs to the Special Issue Visual Localization)
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. View Full-Text
Keywords: object detection; localization; distance estimation; object dimensions; object orientation; 3D bounding box estimation; 3D multi-object detection; multi-modal dataset; deep learning; smart mobility object detection; localization; distance estimation; object dimensions; object orientation; 3D bounding box estimation; 3D multi-object detection; multi-modal dataset; deep learning; smart mobility
Show Figures

Figure 1

MDPI and ACS Style

Mauri, A.; Khemmar, R.; Decoux, B.; Haddad, M.; Boutteau, R. Real-Time 3D Multi-Object Detection and Localization Based on Deep Learning for Road and Railway Smart Mobility. J. Imaging 2021, 7, 145. https://doi.org/10.3390/jimaging7080145

AMA Style

Mauri A, Khemmar R, Decoux B, Haddad M, Boutteau R. Real-Time 3D Multi-Object Detection and Localization Based on Deep Learning for Road and Railway Smart Mobility. Journal of Imaging. 2021; 7(8):145. https://doi.org/10.3390/jimaging7080145

Chicago/Turabian Style

Mauri, Antoine, Redouane Khemmar, Benoit Decoux, Madjid Haddad, and Rémi Boutteau. 2021. "Real-Time 3D Multi-Object Detection and Localization Based on Deep Learning for Road and Railway Smart Mobility" Journal of Imaging 7, no. 8: 145. https://doi.org/10.3390/jimaging7080145

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop