Local Label Descriptor for Example Based Semantic Image Labeling

  • Yiqing Yang
  • Zhouyuan Li
  • Li Zhang
  • Christopher Murphy
  • Jim Ver Hoeve
  • Hongrui Jiang
Conference paper

DOI: 10.1007/978-3-642-33786-4_27

Part of the Lecture Notes in Computer Science book series (LNCS, volume 7578)
Cite this paper as:
Yang Y., Li Z., Zhang L., Murphy C., Ver Hoeve J., Jiang H. (2012) Local Label Descriptor for Example Based Semantic Image Labeling. In: Fitzgibbon A., Lazebnik S., Perona P., Sato Y., Schmid C. (eds) Computer Vision – ECCV 2012. ECCV 2012. Lecture Notes in Computer Science, vol 7578. Springer, Berlin, Heidelberg

Abstract

In this paper we introduce the concept of local label descriptor, which is a concatenation of label histograms for each cell in a patch. Local label descriptors alleviate the label patch misalignment issue in combining structured label predictions for semantic image labeling. Given an input image, we solve for a label map whose local label descriptors can be approximated as a sparse convex combination of exemplar label descriptors in the training data, where the sparsity is regularized by the similarity measure between the local feature descriptor of the input image and that of the exemplars in the training data set. Low-level image over-segmentation can be incorporated into our formulation to improve efficiency. Our formulation and algorithm compare favorably with the baseline method on the CamVid and Barcelona datasets.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Yiqing Yang
    • 1
  • Zhouyuan Li
    • 1
  • Li Zhang
    • 1
  • Christopher Murphy
    • 2
  • Jim Ver Hoeve
    • 1
  • Hongrui Jiang
    • 1
  1. 1.University of Wisconsin-MadisonUSA
  2. 2.University of CaliforniaDavisUSA

Personalised recommendations