Spatially Constrained Location Prior for Scene Parsing

TL;DR

This paper introduces a novel Spatially Constrained Location Prior (SCLP) that models both relative and absolute spatial relationships of objects to improve scene parsing accuracy in complex natural images.

Contribution

The study proposes SCLP, a general method combining relative and absolute location priors, enhancing semantic context modeling for scene parsing.

Findings

SCLP improves scene parsing accuracy on Stanford background dataset.

SCLP outperforms state-of-the-art methods on SIFT Flow dataset.

SCLP can be integrated with various visual prediction models.

Abstract

Semantic context is an important and useful cue for scene parsing in complicated natural images with a substantial amount of variations in objects and the environment. This paper proposes Spatially Constrained Location Prior (SCLP) for effective modelling of global and local semantic context in the scene in terms of inter-class spatial relationships. Unlike existing studies focusing on either relative or absolute location prior of objects, the SCLP effectively incorporates both relative and absolute location priors by calculating object co-occurrence frequencies in spatially constrained image blocks. The SCLP is general and can be used in conjunction with various visual feature-based prediction models, such as Artificial Neural Networks and Support Vector Machine (SVM), to enforce spatial contextual constraints on class labels. Using SVM classifiers and a linear regression model, we demonstrate that the incorporation of SCLP achieves superior performance compared to the state-of-the-art methods on the Stanford background and SIFT Flow datasets.