3D Object Proposals using Stereo Imagery for Accurate Object Class Detection
This work improves 3D object detection accuracy for autonomous driving systems, though it is incremental as it builds on existing proposal and CNN-based methods.
The paper tackles 3D object detection for autonomous driving by generating high-quality 3D object proposals from stereo imagery and using a CNN for detection, achieving significant performance gains over existing methods on the KITTI benchmark and outperforming all prior results in detection and orientation estimation.
The goal of this paper is to perform 3D object detection in the context of autonomous driving. Our method first aims at generating a set of high-quality 3D object proposals by exploiting stereo imagery. We formulate the problem as minimizing an energy function that encodes object size priors, placement of objects on the ground plane as well as several depth informed features that reason about free space, point cloud densities and distance to the ground. We then exploit a CNN on top of these proposals to perform object detection. In particular, we employ a convolutional neural net (CNN) that exploits context and depth information to jointly regress to 3D bounding box coordinates and object pose. Our experiments show significant performance gains over existing RGB and RGB-D object proposal methods on the challenging KITTI benchmark. When combined with the CNN, our approach outperforms all existing results in object detection and orientation estimation tasks for all three KITTI object classes. Furthermore, we experiment also with the setting where LIDAR information is available, and show that using both LIDAR and stereo leads to the best result.