TechRxiv
2020_kka_jkg.pdf (524.76 kB)
0/0

Foreground object segmentation in RGB-D data implemented on GPU

Download (524.76 kB)
preprint
posted on 03.02.2020 by Piotr Janus, Tomasz Kryjak, Marek Gorgon
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.

History

Email Address of Submitting Author

tomasz.kryjak@agh.edu.pl

ORCID of Submitting Author

0000-0001-6798-4444

Submitting Author's Institution

AGH University of Science and Technology

Submitting Author's Country

Poland

Licence

Exports

Licence

Exports