Search

One of the most widely used motion capture (MoCap) methods depends on retroreflective markers placed on an object. Through cameras, the MoCap system captures the moving prop's (3D object) motion. However, noise in MoCap data caused by the shape of the captured volume, motion between frames, ghost points, and markers' self-occlusion could impact the quality of the captured data. To improve the quality of capturing the motion of props, we tackle the problem of finding an optimal marker set configuration for a given input prop while considering various constraints. By "props," we mean any objects or handheld items of different shapes and sizes on which markers can be precisely placed to reduce MoCap errors. We propose an approach to optimize the placement of optical (retroreflective) markers over props while encountering various constraints, such as the visibility of markers, the number of makers used, the symmetry of the marker set, and markers' overlapping. We solve the marker set configuration problem using an optimization-based method, the reversible-jump Markov chain Monte Carlo. We provide marker set configurations for various props and constraints obtained through several simulations we ran to evaluate the performance of our method. [Display omitted] • We propose a method that finds optimal marker set configurations for an input prop. • We define a total cost function that encodes various constraints as cost terms. • Our method can provide optimal marker set configurations for 3D props. • We measured our method's performance based on the total optimization time. • We conducted several evaluations of our method to understand its performance. [ABSTRACT FROM AUTHOR]

Considering the problem of recognizing non-verbal cues in Human–Robot Interaction applications, this paper proposes a novel real-time unsupervised spike timing neural network for recognition and early detection of spatio-temporal human gestures. Two spiking network classifiers one based on Izhikevich neuron model, and the other one based on Integrate-and-Fire-or-Burst neuron model have been implemented in CUDA, and allow the classification to be performed in real-time. To evaluate the performance of this proposal, we test the case of a physical robot observing air-handwritings of human gesture. The proposed approaches run in real-time, thus they are suitable for human–robot applications; they allow real-time early classifying human gestures and actions while they require a very small number of training samples. In comparing to other prominent techniques, our approaches demonstrate superior accuracy and are suitable for early classification of different types of human actions in time-sensitive mobile applications such as robotics. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel unsupervised learning approach for spatio-temporal pattern classification. We use a spike timing neural network with axonal conductance delays to learn the structure of spatio-temporal patterns from a small set of training samples and then use this network for classifying unseen patterns. The method also enables early classification of patterns, before they are completely observed. To transform a spatio-temporal pattern into a suitable form for the spiking network, we create a mapping process that transforms it into a spike train that can be used to train the network through spike-timing-dependent plasticity. Based on the trained network, we build models of the training samples as strings of characters in which each character represents a set of neurons that fire at a particular time step, in response to the pattern. For classification, we compute the longest common subsequence between the model strings corresponding to the input and training samples and choose the class of the training sample with highest similarity. This method is evaluated on a handwritten digits dataset with spatio-temporal information. We show that this method is robustly detecting the correct class early on. Comparison with one unsupervised and eight other supervised approaches shows that our proposed approach could compete or has better performance rather than all of them. Further analysis show that even for misclassified samples, our system can detect the correct class among the top three class labels. [ABSTRACT FROM AUTHOR]

Delineating accurate flowlines using digital elevation models is a critical step for overland flow modeling. However, extracting surface flowlines from high‐resolution digital elevation models (HRDEMs) can be biased, partly due to the absence of information on the locations of anthropogenic drainage structures (ADS) such as bridges and culverts. Without the ADS, the roads may act as "digital dams" that prevent accurate delineation of flowlines. However, it is unclear what variables for terrain‐based hydrologic modeling can be used to mitigate the effect of "digital dams." This study assessed the impacts of ADS locations, spatial resolution, depression processing methods, and flow direction algorithms on hydrologic connectivity in an agrarian landscape of Nebraska. The assessment was conducted based on the offset distances between modeled drainage crossings and actual ADS on the road. Results suggested that: (a) stream burning in combination with the D8 or D‐Infinity flow direction algorithm is the best option for modeling surface flowlines from HRDEMs in an agrarian landscape; (b) increasing the HRDEM resolution was found significant for facilitating accurate drainage crossing near ADS locations; and (c) D8 and D‐Infinity flow direction algorithms resulted in similar patterns of drainage crossing at ADS locations. This research is expected to result in improved parameter settings for HRDEMs‐based hydrologic modeling. [ABSTRACT FROM AUTHOR]

We have evaluated four locomotion interfaces, namely natural walking (NW), omnidirectional treadmill (OT), walk-in-place (WiP), and joystick (JS). In this within-group study, an avoidance movement task with a virtual character was performed by all participants for each examined interface. Our study considers that natural walking is the most realistic method for navigating in a virtual environment and explores the differences across the examined locomotion interfaces by collecting avoidance movement measurements (clearance distance, trajectory length, and trajectory curvature) and self-reported subjective ratings (simulation sickness, usefulness, satisfaction, ease of use, and task load). The results suggest that, despite the fact that the avoidance movement measurements of the WiP, JS, and NW interfaces share similarities, they, more often than not, differ from the measurements of the OT interface, which makes the OT interface unable to provide precise avoidance movement data for our participants. Moreover, the OT interface was rated lower by participants in terms of learning, usability, efficacy, satisfaction, physical demand, and effort. Our study shows that NW, OT, WiP, and JS as locomotion interfaces present several benefits and drawbacks concerning their application in avoidance movement behavior tasks with a virtual character. [ABSTRACT FROM AUTHOR]