CQUniversity
Browse
Author Accepted Manuscript_Non-parametric spatially constrained local prior for scene parsing on real-world data.pdf (3.6 MB)

Non-parametric spatially constrained local prior for scene parsing on real-world data

Download (3.6 MB)
Version 2 2022-10-05, 03:50
Version 1 2022-02-10, 00:17
journal contribution
posted on 2022-10-05, 03:50 authored by Ligang ZhangLigang Zhang
Scene parsing aims to recognize the object category of every pixel in scene images, and it plays a central role in image content understanding and computer vision applications. However, accurate scene parsing from unconstrained real-world data is still a challenging task. In this paper, we present the non-parametric Spatially Constrained Local Prior (SCLP) for scene parsing on realistic data. For a given query image, the non-parametric SCLP is learnt by first retrieving a subset of most similar training images to the query image and then collecting prior information about object co-occurrence statistics between spatial image blocks and between adjacent superpixels from the retrieved subset. The SCLP is powerful in capturing both long- and short-range context about inter-object correlations in the query image and can be effectively integrated with traditional visual features to refine the classification results. Our experiments on the SIFT Flow and PASCAL-Context benchmark datasets show that the non-parametric SCLP used in conjunction with superpixel-level visual features achieves one of the top performance compared with state-of-the-art approaches.

History

Volume

93

Start Page

1

End Page

10

Number of Pages

10

eISSN

1873-6769

ISSN

0952-1976

Publisher

Elsevier

Language

en

Peer Reviewed

  • Yes

Open Access

  • No

Acceptance Date

2020-05-10

Era Eligible

  • Yes

Journal

Engineering Applications of Artificial Intelligence

Article Number

103708