Foreground Object Segmentation in RGB–D Data Implemented on GPU

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 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 real-time image processing. In addition, the system has been adapted to work with two RGB–D sensors: RealSense D415 and D435 from Intel.