Erik Jonsson School of Engineering and Computer Science
Permanent URI for this communityhttps://hdl.handle.net/10735.1/1527
Treasures metadata is created using UTF-8 (Unicode) characters. It is suggested that for best viewing of items a font with a large amount of unicode characters (e.g. Arial Unicode MS, FreeSerif, or NotoSerif) be made the default font in your browser. When scientific formulas cannot be rendered in unicode, they will be coded in LaTeX.
Browse
Browsing Erik Jonsson School of Engineering and Computer Science by Subject "3-D video (Three-dimensional imaging)"
Now showing 1 - 2 of 2
- Results Per Page
- Sort Options
Item Multi-Temporal Depth Motion Maps-Based Local Binary Patterns for 3-D Human Action Recognition(IEEE Electrical Electronics Engineers Inc) Chen, Chen; Liu, Mengyuan; Liu, Hong; Zhang, Baochang; Han, Jungong; Kehtarnavaz, Nasser; Kehtarnavaz, NasserThis paper presents a local spatio-temporal descriptor for action recognistion from depth video sequences, which is capable of distinguishing similar actions as well as coping with different speeds of actions. This descriptor is based on three processing stages. In the first stage, the shape and motion cues are captured from a weighted depth sequence by temporally overlapped depth segments, leading to three improved depth motion maps (DMMs) compared with the previously introduced DMMs. In the second stage, the improved DMMs are partitioned into dense patches, from which the local binary patterns histogram features are extracted to characterize local rotation invariant texture information. In the final stage, a Fisher kernel is used for generating a compact feature representation, which is then combined with a kernel-based extreme learning machine classifier. The developed solution is applied to five public domain data sets and is extensively evaluated. The results obtained demonstrate the effectiveness of this solution as compared with the existing approaches.Item VOTE: A Ray-Casting Study of Vote-Oriented Technique Enhancements(Academic Press) Moore, Alec G.; Hatch, John G.; Kuehl, Stephen; McMahan, Ryan P.; 2758150470089704330006 (McMahan, RP); Moore, Alec G.; Hatch, John G.; Kuehl, Stephen; McMahan, Ryan P.When making selections within 3D user interfaces (3DUIs), a user can fail to select a desired target despite indicating that target during most of the interaction process. This is due to numerous factors that can negatively impact which object is being indicated during the final confirmation step. In this paper, we present a novel vote-oriented technique enhancement (VOTE) for 3D selection that votes for indicated object each interaction frame and then selects the object with the most votes during confirmation. VOTE can be applied to nearly any 3D selection technique, as it does not require additional user input and does not require any prior knowledge of the environment or task. To demonstrate the effectiveness of VOTE, we present a ray-casting selection study that compared traditional, Snap-To, and VOTE ray-casting techniques for a standard multidirectional selection task. The results of our study show that VOTE afforded faster selections than traditional ray-casting and resulted in fewer incorrect selections than the Snap-To enhancement. Additionally, VOTE yielded significantly better effective throughput than traditional ray-casting and the Snap-To enhancement for selections within clustered environments. ©2018 Elsevier Ltd. All Rights Reserved.