Poster
3D Object Proposals for Accurate Object Class Detection
Xiaozhi Chen · Kaustav Kundu · Yukun Zhu · Andrew G Berneshawi · Huimin Ma · Sanja Fidler · Raquel Urtasun

Mon Dec 7th 07:00 -- 11:59 PM @ 210 C #12 #None
in Poster Session »

The goal of this paper is to generate high-quality 3D object proposals in the context of autonomous driving. Our method exploits stereo imagery to place proposals in the form of 3D bounding boxes. We formulate the problem as minimizing an energy function encoding object size priors, ground plane as well as several depth informed features that reason about free space, point cloud densities and distance to the ground. Our experiments show significant performance gains over existing RGB and RGB-D object proposal methods on the challenging KITTI benchmark. Combined with convolutional neural net (CNN) scoring, our approach outperforms all existing results on all three KITTI object classes.

Author Information

Xiaozhi Chen (Tsinghua University)
Kaustav Kundu (University of Toronto)
Yukun Zhu (University of Toronto)
Andrew G Berneshawi (University of Toronto)
Huimin Ma (Tsinghua University)
Sanja Fidler (University of Toronto)
Raquel Urtasun (University of Toronto)

More from the Same Authors