Accurate Monocular 3D Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving

Xinzhu Ma, Zhihui Wang, Haojie Li, Pengbo Zhang, Wanli Ouyang, Xin Fan; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 6851-6860

Abstract


In this paper, we propose a monocular 3D object detection framework in the domain of autonomous driving. Unlike previous image-based methods which focus on RGB feature extracted from 2D images, our method solves this problem in the reconstructed 3D space in order to exploit 3D contexts explicitly. To this end, we first leverage a stand-alone module to transform the input data from 2D image plane to 3D point clouds space for a better input representation, then we perform the 3D detection using PointNet backbone net to obtain objects' 3D locations, dimensions and orientations. To enhance the discriminative capability of point clouds, we propose a multi-modal feature fusion module to embed the complementary RGB cue into the generated point clouds representation. We argue that it is more effective to infer the 3D bounding boxes from the generated 3D scene space (i.e., X,Y, Z space) compared to the image plane (i.e., R,G,B image plane). Evaluation on the challenging KITTI dataset shows that our approach boosts the performance of state-of-the-art monocular approach by a large margin.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Ma_2019_ICCV,
author = {Ma, Xinzhu and Wang, Zhihui and Li, Haojie and Zhang, Pengbo and Ouyang, Wanli and Fan, Xin},
title = {Accurate Monocular 3D Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}