首页|基于多尺度注意力机制的实时激光雷达点云语义的分割

基于多尺度注意力机制的实时激光雷达点云语义的分割

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
为既能提高分割精度,又能克服车载计算资源局限,提出一种面向移动机器人平台的车载实时点云语义分割方法,并进行了综合实验.该方法采用基于投影的激光雷达语义分割方法,将三维点云投影到球面图像,并结合二维卷积进行分割.引入多头注意力机制(MHSA),实现轻量级语义分割模型,以一种全新的方式,将一种深度学习模型架构Transformer映射到卷积.将Transformer的MHSA迁移至卷积,以形成多尺度自注意力机制(MSSA).结果表明:与当前主流方法CENet、FIDNet、PolarNet相比,本方法在NVIDIA JETSON AGX Xavier计算平台上保持了较高的分割精度(平均交并比为63.9%)及较高的检测速率(41 帧/s),从而证明了其对移动机器人平台的适用性.
Semantic segmentation of real-time LiDAR point clouds based on multi-scale self-attention
A real-time point cloud semantic segmentation method was proposed for mobile robot platforms through digital experiments,to enhance segmentation accuracy within the constraints of in-vehicle computing resources.The approach used a projection-based LiDAR technique,projecting the 3-D point cloud onto a spherical image and applying 2-D convolution.The approach integrated the multi-head self-attention(MHSA)mechanism,adapting the Transformer,a software semantic segmentation,architecture into convolution operations to build a multi-scale self-attention(MSSA)framework.The results show that on the NVIDIA JETSON AGX Xavier computing platform,the proposed method achieves a high segmentation accuracy with the mean ratio of Intersection to Union(mIoU)being 63.9%,and a fast detection speed of 41 frame/s,compared to state-of-the-art methods like the CENet,the FIDNet,and the PolarNet,therefore,demonstrating the effectiveness of the mobile robot platforms.

mobile robot platformslight detection and ranging(LiDAR)point cloudmulti-scale self-attention(MSSA)semantic segmentation TRANSFORMERconvolutional neural networks

张晨、刘畅、赵津、王广玮、许庆

展开 >

贵州大学 机械工程学院,贵阳 550025,中国

清华大学车辆与运载学院,北京 100084,中国

移动机器人平台 激光雷达(LiDAR) 点云 多尺度注意力机制(MSSA) 语义分割方法TRANSFORMER 卷积神经网络

国家自然科学基金地区项目贵州省科技支撑计划项目贵州省创新人才团队项目

52265070黔科合支撑[2022]一般045CXTD2022-009

2024

10.3969/j.issn.1674-8484.2024.04.016

汽车安全与节能学报
清华大学

汽车安全与节能学报

CSTPCD北大核心
影响因子：0.748
ISSN：1676-8484
年,卷(期)：2024.15(4)