(Created page with " == Abstract == utonomous driving requires 3D perception of vehicles and other objects in the in environment. Much of the current methods support 2D vehicle detection. This p...") |
m (Scipediacontent moved page Draft Content 267599182 to Ang et al 2018a) |
(No difference)
|
utonomous driving requires 3D perception of vehicles and other objects in the in environment. Much of the current methods support 2D vehicle detection. This paper proposes a flexible pipeline to adopt any 2D detection network and fuse it with a 3D point cloud to generate 3D information with minimum changes of the 2D detection networks. To identify the 3D box, an effective model fitting algorithm is developed based on generalised car models and score maps. A two-stage convolutional neural network (CNN) is proposed to refine the detected 3D box. This pipeline is tested on the KITTI dataset using two different 2D detection networks. The 3D detection results based on these two networks are similar, demonstrating the flexibility of the proposed pipeline. The results rank second among the 3D detection algorithms, indicating its competencies in 3D detection.
Comment: Accepted at ICRA 2018
The different versions of the original document can be found in:
Published on 01/01/2018
Volume 2018, 2018
DOI: 10.1109/icra.2018.8461232
Licence: CC BY-NC-SA license
Are you one of the authors of this document?