article · 2007

A Bayesian Network Framework for Vision Based Semantic Scene Understanding

Seung-Bin Im, Keum-Sung Hwang, Sung-Bae Cho

Cited by 2Abstract and details only

Abstract

For a robot to understand a scene, we have to infer and extract meaningful information from vision sensor data. Since scene understanding consists in recognizing several visual contexts, we have to extract these contextual cues and understand their relationships. However, context extraction from visual information is difficult due to uncertain information in variable environments, imperfect nature of the feature extraction methods and high computational complexity of reasoning from the complex relationship. In order to manage the uncertainties effectively, in this paper, we adopted Bayesian probabilistic approach, and proposed a Bayesian network framework that synthesizes the low level features and the high level semantic cues. It contains how to develop and utilize an integrated Bayesian network model. In the experimental results of two applications, the efficacy of the proposed framework is shown.

Cite this paper

APA 7

Im, S.-B., Hwang, K.-S., & Cho, S.-B. (2007). A Bayesian Network Framework for Vision Based Semantic Scene Understanding. https://doi.org/10.1109/roman.2007.4415201

MLA 9

Im, Seung-Bin, et al. “A Bayesian Network Framework for Vision Based Semantic Scene Understanding.” vol. 16, 2007, pp. 839–44, https://doi.org/10.1109/roman.2007.4415201.

Chicago

Im, Seung-Bin, Keum-Sung Hwang, and Sung-Bae Cho. 2007. “A Bayesian Network Framework for Vision Based Semantic Scene Understanding.” https://doi.org/10.1109/roman.2007.4415201.

Harvard

Im, S.-B., Hwang, K.-S. and Cho, S.-B. (2007) ‘A Bayesian Network Framework for Vision Based Semantic Scene Understanding’. Available at: https://doi.org/10.1109/roman.2007.4415201.

BibTeX

@article{im2007bayesian,
  title = {{A Bayesian Network Framework for Vision Based Semantic Scene Understanding}},
  author = {Im, Seung-Bin and Hwang, Keum-Sung and Cho, Sung-Bae},
  volume = {16},
  pages = {839--844},
  year = {2007},
  doi = {10.1109/roman.2007.4415201}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.