Organizational Unit:
Institute for Robotics and Intelligent Machines (IRIM)

Permanent Link
https://hdl.handle.net/1853/70657
Research Organization Registry ID
Description
Previous Names
Parent Organization
Parent Organization
Includes Organization(s)
Organizational Unit
Organizational Unit
ArchiveSpace Name Record

Filters

2005 - 2009 2 2010 - 2014 1
3
2 1
3
3
Reset filters

Settings
search.filters.applied.f.isSeriesOfPublicationTitle: College of Computing Technical Report Series ×

Publication Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Deep Segments: Comparisons between Scenes and their Constituent Fragments using Deep Learning
    (Georgia Institute of Technology, 2014-09) Doshi, Jigar ; Mason, Celeste ; Wagner, Alan ; Kira, Zsolt
    We examine the problem of visual scene understanding and abstraction from first person video. This is an important problem and successful approaches would enable complex scene characterization tasks that go beyond classification, for example characterization of novel scenes in terms of previously encountered visual experiences. Our approach utilizes the final layer of a convolutional neural network as a high-level, scene specific, representation which is robust enough to noise to be used with wearable cameras. Researchers have demonstrated the use of convolutional neural networks for object recognition. Inspired by results from cognitive and neuroscience, we use output maps created by a convolutional neural network as a sparse, abstract representation of visual images. Our approach abstracts scenes into constituent segments that can be characterized by the spatial and temporal distribution of objects. We demonstrate the viability of the system on video taken from Google Glass. Experiments examining the ability of the system to determine scene similarity indicate ρ (384) = ±0:498 correlation to human evaluations and 90% accuracy on a category match problem. Finally, we demonstrate high-level scene prediction by showing that the system matches two scenes using only a few initial segments and predicts objects that will appear in subsequent segments.
  • Thumbnail Image
    Item
    Automatic Landmark Detection for Topological Mapping Using Bayesian Surprise
    (Georgia Institute of Technology, 2008) Ranganathan, Ananth ; Dellaert, Frank
    Topological maps are graphical representations of the environment consisting of nodes that denote landmarks, and edges that represent the connectivity between the landmarks. Automatic detection of landmarks, usually special places in the environment such as gateways, in a general, sensor-independent manner has proven to be a difficult task. We present a landmark detection scheme based on the notion of “surprise” that addresses these issues. The surprise associated with a measurement is defined as the change in the current model upon updating it using the measurement. We demonstrate that surprise is large when sudden changes in the environment occur, and hence, is a good indicator of landmarks. We evaluate our landmark detector using appearance and laser measurements both qualitatively and quantitatively. Part of this evaluation is performed in the context of a topological mapping algorithm, thus demonstrating the practical applicability of the detector.
  • Thumbnail Image
    Item
    Segmental Switching Linear Dynamic Systems
    (Georgia Institute of Technology, 2005) Oh, Sang Min ; Rehg, James M. ; Dellaert, Frank
    We introduce Segmental Switching Linear Dynamic Systems (S-SLDS), which improve on standard SLDSs by explicitly incorporating duration modeling capabilities. We show that S-SLDSs can adopt arbitrary finite-sized duration models that describe data more accurately than the geometric distributions induced by standard SLDSs. We also show that we can convert an S-SLDS to an equivalent standard SLDS with sparse structure in the resulting transition matrix. This insight makes it possible to adopt existing inference and learning algorithms for the standard SLDS models to the S-SLDS framework. As a consequence, the more powerful S-SLDS model can be adopted with only modest additional effort in most cases where an SLDS model can be applied. The experimental results on honeybee dance decoding tasks demonstrate the robust inference capabilities of the proposed S-SLDS model.