Discovering Object Instances from Scenes of Daily Living

Hongwen Kang, Martial Hebert, and Takeo Kanade
IEEE 13th International Conference on Computer Vision , November, 2011.


Download
  • Adobe portable document format (pdf) (6MB)
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract
We propose an approach to identify and segment objects from scenes that a person (or robot) encounters in Activities of Daily Living (ADL). Images collected in those cluttered scenes contain multiple objects. Each image provides only a partial, possibly very different view of each object. An object instance discovery program must be able to link pieces of visual information from multiple images and extract the consistent patterns. Most papers on unsupervised discovery of object models are concerned with object categories. In contrast, this paper aims at identifying and extracting regions corresponding to specific object instances, e.g., two different laptops in the laptop category. By focusing on specific instances, we enforce explicit constraints on geometric consistency (such as scale, orientation), and appearance consistency (such as color, texture and shape). Using multiple segmentations as the basic building block, our program processes a noisy “soup” of segments and extracts object models as groups of mutually consistent segments. Our approach was tested on three different types of image sets: two from indoor ADL environments and one from Flickr.com. The results demonstrate robustness of our program to severe clutter, occlusion, changes of viewpoint and interference from irrelevant images. Our approach achieves significant improvement over with two existing methods.

Keywords
Object instance discovery, object discovery, unsupervised

Notes
Sponsor: NSF
Associated Center(s) / Consortia: Quality of Life Technology Center

Text Reference
Hongwen Kang, Martial Hebert, and Takeo Kanade, "Discovering Object Instances from Scenes of Daily Living," IEEE 13th International Conference on Computer Vision , November, 2011.

BibTeX Reference
@inproceedings{Kang_2011_6912,
   author = "Hongwen Kang and Martial Hebert and Takeo Kanade",
   title = "Discovering Object Instances from Scenes of Daily Living",
   booktitle = "IEEE 13th International Conference on Computer Vision ",
   publisher = "IEEE",
   month = "November",
   year = "2011",
}