Johannes Lehner, Andreas Mitterecker, Thomas Adler, Markus Hofmarcher, Bernhard Nessler, and Sepp Hochreiter

We introduce Patch Refinement a two-stage model for accurate 3D object detection and localization from point cloud data. Patch Refinement is composed of two independently trained Voxelnet-based networks, a Region Proposal Network (RPN) and a Local Refinement Network (LRN). We decompose the detection task into a preliminary Bird’s Eye View (BEV) detection step and a local 3D detection step. Based on the proposed BEV locations by the RPN, we extract small point cloud subsets (‘patches’), which are then processed by the LRN, which is less limited by memory constraints due to the small area of each patch. Therefore, we can apply encoding with a higher voxel resolution locally. The independence of the LRN enables the use of additional augmentation techniques and allows for an efficient, regression focused training as it uses only a small fraction of each scene. Evaluated on the KITTI 3D object detection benchmark, our submission from January 28, 2019, outperformed all previous entries on all three difficulties of the class car, using only 50% of the available training data and only LiDAR information.

Machine Learning for Autonomous Driving Workshop at NeurIPS 2019, Vancouver, 10-12 Dec 2019, or preprint arXiv, 1910.04093v1, Computer Vision and Pattern Recognition (cs.CV), 2019-10-09.

Download
View paper
IARAI Authors
Dr Sepp Hochreiter
Research
Traffic and Navigation
Keywords
3d Object Detection, Deep Learning

©2020 IARAI - INSTITUTE OF ADVANCED RESEARCH IN ARTIFICIAL INTELLIGENCE

Imprint | Privacy Policy

Stay in the know with developments at IARAI

We can let you know if there’s any

updates from the Institute.
You can later also tailor your news feed to specific research areas or keywords (Privacy)

Log in with your credentials

Forgot your details?

Create Account