GAL: A Global-Attributes Assisted Labeling System for Outdoor Scenes

TL;DR

This paper introduces GAL, a system that enhances outdoor scene labeling by integrating global attributes like sky and ground lines into a CRF framework, improving accuracy over existing methods.

Contribution

The novel contribution is the integration of global attributes extracted from outdoor images into a CRF-based labeling system, improving scene layout accuracy.

Findings

GAL outperforms state-of-the-art algorithms on outdoor scene datasets.

Global attributes significantly improve labeling robustness.

The system effectively combines local features with global cues.

Abstract

An approach that extracts global attributes from outdoor images to facilitate geometric layout labeling is investigated in this work. The proposed Global-attributes Assisted Labeling (GAL) system exploits both local features and global attributes. First, by following a classical method, we use local features to provide initial labels for all super-pixels. Then, we develop a set of techniques to extract global attributes from 2D outdoor images. They include sky lines, ground lines, vanishing lines, etc. Finally, we propose the GAL system that integrates global attributes in the conditional random field (CRF) framework to improve initial labels so as to offer a more robust labeling result. The performance of the proposed GAL system is demonstrated and benchmarked with several state-of-the-art algorithms against a popular outdoor scene layout dataset.