Foreground object segmentation in RGB-D data implemented on GPU
From MaRDI portal
Publication:6204073
DOI10.1007/978-3-030-50936-1_68arXiv2002.00250OpenAlexW3003796417MaRDI QIDQ6204073FDOQ6204073
Authors: Piotr Janus, Tomasz Kryjak, Marek Gorgoń 
Publication date: 9 April 2024
Published in: Advances in Intelligent Systems and Computing (Search for Journal in Brave)
Abstract: 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 to improve segmentation accuracy, especially in case of colour camouflage, illumination changes and occurrence of shadows. Three GPUs were used to accelerate calculations: 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 to get real-time image processing. In addition, the system has been adapted to work with two RGB-D sensors: RealSense D415 and D435 from Intel.
Full work available at URL: https://arxiv.org/abs/2002.00250
This page was built for publication: Foreground object segmentation in RGB-D data implemented on GPU
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6204073)
