arXiv (Cornell University)· 2016· Preprint
Vehicle Detection from 3D Lidar Using Fully Convolutional Network
- 275citations
- 2016year
Short summary
A novel method uses a 2D fully convolutional network (FCN) to detect vehicles from 3D Lidar point cloud data by encoding it into a 2D point map, achieving state-of-the-art performance on the KITTI dataset.
AI-generated from the title and abstract; the full text is not read.
Key points
- A 2D fully convolutional network (FCN) is proposed for 3D vehicle detection from Lidar data.
- 3D Lidar point cloud data is represented as a 2D point map for processing.
- The FCN simultaneously predicts objectness confidence and 3D bounding boxes.
- A novel bounding box encoding enables 3D prediction from a 2D network.
- The method achieves state-of-the-art performance on the KITTI dataset.
AI-generated from the title and abstract; the full text is not read.
Abstract
Convolutional network techniques have recently achieved great success in vision based detection tasks. This paper introduces the recent development of our research on transplanting the fully convolutional network technique to the detection tasks on 3D range scan data. Specifically, the scenario is set as the vehicle detection task from the range data of Velodyne 64E lidar. We proposes to present the data in a 2D point map and use a single 2D end-to-end fully convolutional network to predict the objectness confidence and the bounding boxes simultaneously. By carefully design the bounding box encoding, it is able to predict full 3D bounding boxes even using a 2D convolutional network. Experiments on the KITTI dataset shows the state-of-the-art performance of the proposed method.
The authors' abstract, as published at the source. arXiv (Cornell University), 2016 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Instrumentation
InstrumentationPhysics and Astronomy