A critical view of context

Lior Wolf*, Stanley Bileschi

*Corresponding author for this work

Research output: Contribution to journalReview articlepeer-review

Abstract

In this study, a discriminative detector for object context is designed and tested. The context-feature is simple to implement, feed-forward, and effective across multiple object types in a street-scenes environment. Using context alone, we demonstrate robust detection of locations likely to contain bicycles, cars, and pedestrians. Furthermore, experiments are conducted so as to address several open questions regarding visual context. Specifically, it is demonstrated that context may be determined from low level visual features (simple color and texture descriptors) sampled over a wide receptive field. At least for the framework tested, high level semantic knowledge, e.g, the nature of the surrounding objects, is superfluous. Finally, it is shown that when the target object is unambiguously visible, context is only marginally useful.

Original languageEnglish
Pages (from-to)251-261
Number of pages11
JournalInternational Journal of Computer Vision
Volume69
Issue number2
DOIs
StatePublished - Aug 2006
Externally publishedYes

Funding

FundersFunder number
Honda Research Institute USA, Inc.
Komatsu Ltd.
Merrill-Lynch
Sumitomo Metal Industries
National Science FoundationEIA-0218506
National Institutes of Health1 P20 MH66239-01A1
Office of Naval Research
Defense Advanced Research Projects AgencyN00014-02-1-0915, MDA972-04-1-0037
Eastman Kodak
Eugene McDermott Foundation
Toyota Motor Corporation
Central Research Institute of Electric Power Industry

    Keywords

    • Context
    • Learning
    • Object detection
    • Scene understanding
    • Streetscenes

    Fingerprint

    Dive into the research topics of 'A critical view of context'. Together they form a unique fingerprint.

    Cite this