首页> 外文会议>Polish Control Conference >Foreground Object Segmentation in RGB-D Data Implemented on GPU
【24h】

Foreground Object Segmentation in RGB-D Data Implemented on GPU

机译:在GPU上实现的RGB-D数据中的前景对象分段

获取原文

摘要

This paper presents a GPU implementation of two foreground object segmentation algorithms: Gaussian Mixture Model (GMM) and Pixel Based Adaptive Segmenter (PBAS) modified for RGB-D data support. The simultaneous use of colour (RGB) and depth (D) data allows one to improve segmentation accuracy, especially in case of colour camouflage, illumination changes and shadow occurrence. Three GPUs were used to accelerate computations: embedded NVIDIA Jetson TX2 (Maxwell architecture), mobile NVIDIA GeForce GTX 1050m (Pascal architecture) and efficient NVIDIA RTX 2070 (Turing architecture). Segmentation accuracy comparable to previously published works was obtained. Moreover, the use of a GPU platform allowed us to get realtime image processing. In addition, the system has been adapted to work with two RGB-D sensors: RealSense D415 and D435 from Intel.
机译:本文介绍了两个前景对象分段算法的GPU实现:修改了RGB-D数据支持的高斯混合模型(GMM)和基于像素的自适应分段器(PBA)。 同时使用颜色(RGB)和深度(d)数据允许一个提高分割精度,特别是在彩色伪装的情况下,照明变化和阴影发生。 三个GPU用于加速计算:嵌入式NVIDIA Jetson TX2(Maxwell架构),移动NVIDIA GeForce GTX 1050M(Pascal Architecture)和高效的NVIDIA RTX 2070(图灵架构)。 获得与先前公布的作品相当的分割准确性。 此外,使用GPU平台允许我们获得实时图像处理。 此外,该系统还适用于两个RGB-D传感器:来自英特尔的RealSense D415和D435。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号