3D fully convolutional network for vehicle detection in point cloud
B. Li. 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), page 1513-1518. (September 2017)
DOI: 10.1109/IROS.2017.8205955
Abstract
2D fully convolutional network has been recently successfully applied to the object detection problem on images. In this paper, we extend the fully convolutional network based detection techniques to 3D and apply it to point cloud data. The proposed approach is verified on the task of vehicle detection from lidar point cloud for autonomous driving. Experiments on the KITTI dataset shows significant performance improvement over the previous point cloud based detection approaches.
Description
3D fully convolutional network for vehicle detection in point cloud - IEEE Conference Publication
%0 Conference Paper
%1 8205955
%A Li, B.
%B 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
%D 2017
%K convnets dnn lidar vehicle
%P 1513-1518
%R 10.1109/IROS.2017.8205955
%T 3D fully convolutional network for vehicle detection in point cloud
%U https://ieeexplore.ieee.org/document/8205955
%X 2D fully convolutional network has been recently successfully applied to the object detection problem on images. In this paper, we extend the fully convolutional network based detection techniques to 3D and apply it to point cloud data. The proposed approach is verified on the task of vehicle detection from lidar point cloud for autonomous driving. Experiments on the KITTI dataset shows significant performance improvement over the previous point cloud based detection approaches.
@inproceedings{8205955,
abstract = {2D fully convolutional network has been recently successfully applied to the object detection problem on images. In this paper, we extend the fully convolutional network based detection techniques to 3D and apply it to point cloud data. The proposed approach is verified on the task of vehicle detection from lidar point cloud for autonomous driving. Experiments on the KITTI dataset shows significant performance improvement over the previous point cloud based detection approaches.},
added-at = {2020-10-16T17:24:47.000+0200},
author = {{Li}, B.},
biburl = {https://www.bibsonomy.org/bibtex/26dee39030b3fa52f8581d3c01ab77447/sohnki},
booktitle = {2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
description = {3D fully convolutional network for vehicle detection in point cloud - IEEE Conference Publication},
doi = {10.1109/IROS.2017.8205955},
interhash = {3fee4e288bbe0320eafb0cc979b5b52e},
intrahash = {6dee39030b3fa52f8581d3c01ab77447},
issn = {2153-0866},
keywords = {convnets dnn lidar vehicle},
month = {Sep.},
pages = {1513-1518},
timestamp = {2020-10-16T17:24:47.000+0200},
title = {3D fully convolutional network for vehicle detection in point cloud},
url = {https://ieeexplore.ieee.org/document/8205955},
year = 2017
}