GAL: A Global-Attributes Assisted Labeling System for Outdoor Scenes
This work addresses labeling accuracy for outdoor scene understanding, but it is incremental as it builds on existing CRF methods with added global attributes.
The paper tackles the problem of geometric layout labeling in outdoor scenes by proposing the GAL system, which integrates global attributes like sky lines and ground lines into a CRF framework to improve initial labels from local features, resulting in more robust labeling as benchmarked against state-of-the-art algorithms on a popular dataset.
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.