Dealing with sequences in the RGBDT space

TL;DR

This paper introduces a probabilistic non-parametric model that leverages temporal information from RGBDT sequences to improve moving object segmentation, demonstrating the importance of prior data for accuracy.

Contribution

It presents a novel model and dataset for segmenting moving objects in RGBDT sequences, emphasizing the role of temporal cues in segmentation accuracy.

Findings

Using previous information improves segmentation accuracy.

The model effectively detects human regions in RGBDT sequences.

The dataset enables evaluation of temporal segmentation methods.

Abstract

Most of the current research in computer vision is focused on working with single images without taking in account temporal information. We present a probabilistic non-parametric model that mixes multiple information cues from devices to segment regions that contain moving objects in image sequences. We prepared an experimental setup to show the importance of using previous information for obtaining an accurate segmentation result, using a novel dataset that provides sequences in the RGBDT space. We label the detected regions ts with a state-of-the-art human detector. Each one of the detected regions is at least marked as human once.