arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2003.10670cs.CVcs.RO
收藏

有限处理资源下的实时的3D对象建议生成和分类

Real-time 3D object proposal generation and classification under limited processing resources

University of New South Wales(新南威尔士大学)

Xuesong Li, Jose Guivant, Subhan Khan

摘要:

检测3D物体的任务对于各种机器人应用是重要的。现有的基于深度学习的检测技术已经取得了令人印象深刻的性能。然而,这些技术限于在实时的【形】环境中与图形处理单元(GPU)一起运行。为了在机器人有限的计算资源下实现实时的【形】3D目标检测,提出了一种由3D建议生成和分类组成的高效检测方法.建议生成主要基于点分割,而建议分类由轻量级卷积神经网络(CNN)模型执行。为了验证我们的方法,使用KITTI数据集。实验结果表明,提出的实时的【形】三维目标检测方法的能力,从点云具有竞争力的性能,目标召回和分类。

英文摘要:

The task of detecting 3D objects is important to various robotic applications. The existing deep learning-based detection techniques have achieved impressive performance. However, these techniques are limited to run with a graphics processing unit (GPU) in a real-time environment. To achieve real-time 3D object detection with limited computational resources for robots, we propose an efficient detection method consisting of 3D proposal generation and classification. The proposal generation is mainly based on point segmentation, while the proposal classification is performed by a lightweight convolution neural network (CNN) model. To validate our method, KITTI datasets are utilized. The experimental results demonstrate the capability of proposed real-time 3D object detection method from the point cloud with a competitive performance of object recall and classification.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑