Learning RGB-D salient object detection using background enclosure, depth contrast, and top-down features

Riku Shigematsu, David Feng, Shaodi You, Nick Barnes

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    66 Citations (Scopus)

    Abstract

    In human visual saliency, top-down and bottom-up information are combined as a basis of visual attention. Recently, deep Convolutional Neural Networks (CNN) have demonstrated strong performance on RGB salient object detection, providing an effective mechanism for combining top-down semantic information with low level features. Although depth information has been shown to be important for human perception of salient objects, the use of top-down information and the exploration of CNNs for RGB-D salient object detection remains limited. Here we propose a novel deep CNN architecture for RGB-D salient object detection that utilizes both top-down and bottom-up cues. In order to produce such an architecture, we present novel depth features that capture the ideas of background enclosure, depth contrast and histogram distance in a manner that is suitable for a learned approach. We show improved results compared to state-of-The-Art RGB-D salient object detection methods. We also show that the low-level and mid-level depth features both contribute to improvements in results. In particular, the F-Score of our method is 0.848 on RGBD1000, which is 10.7% better than the current best.

    Original languageEnglish
    Title of host publicationProceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages2749-2757
    Number of pages9
    ISBN (Electronic)9781538610343
    DOIs
    Publication statusPublished - 1 Jul 2017
    Event16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017 - Venice, Italy
    Duration: 22 Oct 201729 Oct 2017

    Publication series

    NameProceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017
    Volume2018-January

    Conference

    Conference16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017
    Country/TerritoryItaly
    CityVenice
    Period22/10/1729/10/17

    Fingerprint

    Dive into the research topics of 'Learning RGB-D salient object detection using background enclosure, depth contrast, and top-down features'. Together they form a unique fingerprint.

    Cite this