Organizational Unit:

Institute for Robotics and Intelligent Machines (IRIM)

Permanent Link

https://hdl.handle.net/1853/70657

Includes Organization(s)

Organizational Unit

Biorobotics and Human Modeling Lab

Organizational Unit

Humanoid Robotics Laboratory

Full item page

Publication Search Results

Now showing 1 - 10 of 16

Increasing Super Pop VR™ Users' Intrinsic Motivation by Improving the Game's Aesthetics

(Georgia Institute of Technology, 2015-08) García-Vergara, Sergio ; Li, Hongfei ; Howard, Ayanna M.

During physical therapy intervention protocols, it's important to consider the individual's intrinsic motivation to perform in-home recommended exercises. Physical therapy exercises can become tedious thus limiting the individual's progress. Not only have researchers developed serious gaming systems to increase user motivation, but they have also worked on the design aesthetics since results have shown positive effects on the users' performance for attractive models. As such, we improved the aesthetics of a previously developed serious game called Super Pop VR™. Namely, we improved the game graphics, added new game features, and allowed for more game options to provide users the opportunity to tailor their own experience. The conducted user studies show that participants rank the version of the game with the improved aesthetics higher in terms of the amount of interest/enjoyment it generates, thus allowing for an increase in intrinsic motivation when interacting with the system.
Automated Assessment of Surgical Skills Using Frequency Analysis

(Georgia Institute of Technology, 2015) Zia, Aneeq ; Sharma, Yachna ; Bettadapura, Vinay ; Sarin, Eric L. ; Clements, Mark A. ; Essa, Irfan

We present an automated framework for visual assessment of the expertise level of surgeons using the OSATS (Objective Structured Assessment of Technical Skills) criteria. Video analysis techniques for extracting motion quality via frequency coefficients are introduced. The framework is tested on videos of medical students with different expertise levels performing basic surgical tasks in a surgical training lab setting. We demonstrate that transforming the sequential time data into frequency components effectively extracts the useful information differentiating between different skill levels of the surgeons. The results show significant performance improvements using DFT and DCT coefficients over known state-of-the-art techniques.
Joint Semantic Segmentation and 3D Reconstruction from Monocular Video

(Georgia Institute of Technology, 2014-09) Kundu, Abhijit ; Li, Yin ; Dellaert, Frank ; Li, Fuxin ; Rehg, James M.

We present an approach for joint inference of 3D scene structure and semantic labeling for monocular video. Starting with monocular image stream, our framework produces a 3D volumetric semantic + occupancy map, which is much more useful than a series of 2D semantic label images or a sparse point cloud produced by traditional semantic segmentation and Structure from Motion(SfM) pipelines respectively. We derive a Conditional Random Field (CRF) model defined in the 3D space, that jointly infers the semantic category and occupancy for each voxel. Such a joint inference in the 3D CRF paves the way for more informed priors and constraints, which is otherwise not possible if solved separately in their traditional frameworks. We make use of class specific semantic cues that constrain the 3D structure in areas, where multiview constraints are weak. Our model comprises of higher order factors, which helps when the depth is unobservable. We also make use of class specific semantic cues to reduce either the degree of such higher order factors, or to approximately model them with unaries if possible. We demonstrate improved 3D structure and temporally consistent semantic segmentation for diffcult, large scale, forward moving monocular image sequence.
Three-Dimensional Fitt’s Law Model Used to Predict Movement Time in Serious Games for Rehabilitation

(Georgia Institute of Technology, 2014-06) García-Vergara, Sergio ; Howard, Ayanna M.

Virtual reality serious game platforms have been developed to enhance the effectiveness of rehabilitation protocols for those with motor skill disorders. Such systems increase the user’s motivation to perform the recommended in-home therapy exercises, but typically don’t incorporate an objective method for assessing the user’s outcome metrics. We expand on the commonly used human modeling method, Fitt’s law, used to predict the amount of time needed to complete a task, and apply it as an assessment method for virtual environments. During game-play, we compare the user’s movement time to the predicted value as a means for assessing the individual’s kinematic performance. Taking into consideration the structure of virtual gaming environments, we expand the nominal Fitt’s model to one that makes accurate time predictions for three-dimensional movements. Results show that the three-dimensional refinement made to the Fitt’s model makes better predictions when interacting with virtual gaming platforms than its two-dimensional counterpart.
Movement Pattern Histogram for Action Recognition and Retrieval

(Georgia Institute of Technology, 2014) Ciptadi, Arridhana ; Goodwin, Matthew S. ; Rehg, James M.

We present a novel action representation based on encoding the global temporal movement of an action. We represent an action as a set of movement pattern histograms that encode the global temporal dynamics of an action. Our key observation is that temporal dynamics of an action are robust to variations in appearance and viewpoint changes, making it useful for action recognition and retrieval. We pose the problem of computing similarity between action representations as a maximum matching problem in a bipartite graph. We demonstrate the effectiveness of our method for cross-view action recognition on the IXMAS dataset. We also show how our representation complements existing bag- of-features representations on the UCF50 dataset. Finally we show the power of our representation for action retrieval on a new real-world dataset containing repetitive motor movements emitted by children with autism in an unconstrained classroom setting.
Engaging Children in Play Therapy: The Coupling of Virtual Reality (VR) Games With Social Robotics

(Georgia Institute of Technology, 2014-01) García-Vergara, Sergio ; Brown, LaVonda ; Park, Hae Won ; Howard, Ayanna M.

Individuals who have impairments in their motor skills typically engage in rehabilitation protocols to improve the recovery of their motor functions. In general, engaging in physical therapy can be tedious and difficult, which can result in demotivating the individual. This is especially true for children who are more susceptible to frustration. Thus, different virtual reality environments and play therapy systems have been developed with the goal of increasing the motivation of individuals engaged in physical therapy. However, although previously developed systems have proven to be effective for the general population, the majority of these systems are not focused on engaging children. Given this motivation, we discuss two technologies that have been shown to positively engage children who are undergoing physical therapy. The first is called the Super Pop VR™ game; a virtual reality environment that not only increases the child’s motivation to continue with his/her therapy exercises, but also provides feedback and tracking of patient performance during game play. The second technology integrates robotics into the virtual gaming scenario through social engagement in order to further maintain the child’s attention when engaged with the system. Results from preliminary studies with typically-developing children have shown their effectiveness. In this chapter, we discuss the functions and advantages of these technologies, and their potential for being integrated into the child’s intervention protocol.
Weakly Supervised Learning of Object Segmentations from Web-Scale Video

(Georgia Institute of Technology, 2012-10) Hartmann, Glenn ; Grundmann, Matthias ; Hoffman, Judy ; Tsai, David ; Kwatra, Vivek ; Madani, Omid ; Vijayanarasimhan, Sudheendra ; Essa, Irfan ; Rehg, James M. ; Sukthankar, Rahul

We propose to learn pixel-level segmentations of objects from weakly labeled (tagged) internet videos. Specifically, given a large collection of raw YouTube content, along with potentially noisy tags, our goal is to automatically generate spatiotemporal masks for each object, such as "dog", without employing any pre-trained object detectors. We formulate this problem as learning weakly supervised classifiers for a set of independent spatio-temporal segments. The object seeds obtained using segment-level classifiers are further refined using graphcuts to generate high-precision object masks. Our results, obtained by training on a dataset of 20,000 YouTube videos weakly tagged into 15 classes, demonstrate automatic extraction of pixel-level object masks. Evaluated against a ground-truthed subset of 50,000 frames with pixel-level annotations, we confirm that our proposed methods can learn good object masks just by watching YouTube.
Categorizing Turn-Taking Interactions

(Georgia Institute of Technology, 2012-10) Prabhakar, Karthir ; Rehg, James M.

We address the problem of categorizing turn-taking interactions between individuals. Social interactions are characterized by turn-taking and arise frequently in real-world videos. Our approach is based on the use of temporal causal analysis to decompose a space-time visual word representation of video into co-occuring independent segments, called causal sets [1]. These causal sets then serves the input to a multiple instance learning framework to categorize turn- taking interactions. We introduce a new turn-taking interactions dataset consisting of social games and sports rallies. We demonstrate that our formulation of multiple instance learning (QP-MISVM) is better able to leverage the repetitive structure in turn-taking interactions and demonstrates superior performance relative to a conventional bag of words model.
The Bayes Tree: An Algorithmic Foundation for Probabilistic Robot Mapping

(Georgia Institute of Technology, 2010-12) Kaess, Michael ; Ila, Viorela ; Roberts, Richard ; Dellaert, Frank

We present a novel data structure, the Bayes tree, that provides an algorithmic foundation enabling a better understanding of existing graphical model inference algorithms and their connection to sparse matrix factorization methods. Similar to a clique tree, a Bayes tree encodes a factored probability density, but unlike the clique tree it is directed and maps more naturally to the square root information matrix of the simultaneous localization and mapping (SLAM) problem. In this paper, we highlight three insights provided by our new data structure. First, the Bayes tree provides a better understanding of batch matrix factorization in terms of probability densities. Second, we show how the fairly abstract updates to a matrix factorization translate to a simple editing of the Bayes tree and its conditional densities. Third, we apply the Bayes tree to obtain a completely novel algorithm for sparse nonlinear incremental optimization, that combines incremental updates with fluid relinearization of a reduced set of variables for efficiency, combined with fast convergence to the exact solution. We also present a novel strategy for incremental variable reordering to retain sparsity.We evaluate our algorithm on standard datasets in both landmark and pose SLAM settings.
Sensing and estimation

(Georgia Institute of Technology, 2008-05) Christensen, Henrik I. ; Hager, G.