Accurate 3D Object Detection from Point Cloud Data using Bird’s Eye View Representations
Authors: David Montero Guus Engels Ignacio Arganda
Date: 25.10.2021
Abstract
In this paper, we show that accurate 3D object detection is possible using deep neural networks and a Bird’s Eye View (BEV) representation of the LiDAR point clouds. Many recent approaches propose complex neural network architectures to process directly the point cloud data. The good results obtained by these methods have left behind the research of BEV-based approaches. However, BEV-based detectors can take advantage of the advances in the 2D object detection field and need to handle much less data, which is important in real-time automotive applications. We propose a two-stage object detection deep neural network, which takes BEV representations as input and validate it in the KITTI BEV benchmark, outperforming state-of-the-art methods. In addition, we show how additional information can be added to our model to improve the accuracy of the smallest and most challenging object classes. This information can come from the same point cloud or an additional sensor’s data, such as the camera.
BIB_text
title = {Accurate 3D Object Detection from Point Cloud Data using Bird’s Eye View Representations},
pages = {246-253},
keywds = {
Point Cloud, Object Detection, Deep Neural Networks, LiDAR
}
abstract = {
In this paper, we show that accurate 3D object detection is possible using deep neural networks and a Bird’s Eye View (BEV) representation of the LiDAR point clouds. Many recent approaches propose complex neural network architectures to process directly the point cloud data. The good results obtained by these methods have left behind the research of BEV-based approaches. However, BEV-based detectors can take advantage of the advances in the 2D object detection field and need to handle much less data, which is important in real-time automotive applications. We propose a two-stage object detection deep neural network, which takes BEV representations as input and validate it in the KITTI BEV benchmark, outperforming state-of-the-art methods. In addition, we show how additional information can be added to our model to improve the accuracy of the smallest and most challenging object classes. This information can come from the same point cloud or an additional sensor’s data, such as the camera.
}
isbn = {978-989-758-534-0},
date = {2021-10-25},
}
