Catching the ghost: the digital gaze of motion capture

2019 ◽  
Vol 18 (3) ◽  
pp. 305-326
Author(s):  
Vanessa Chang

Created with digital motion capture, or mocap, the virtual dances Ghostcatching and as.phyx.ia render movement abstracted from choreographic bodies. These depictions of gestural doubles or ‘ghosts’ trigger a sense of the uncanny rooted in mocap’s digital processes. Examining these material processes, this article argues that this digital optical uncanny precipitates from the intersubjective relationship of performer, technology, and spectator. Mocap interpolates living bodies into a technologized visual field that parses these bodies as dynamic data sets, a process by which performing bodies and digital capture technologies coalesce into the film’s virtual body. This virtual body signals a computational agency at its heart, one that choreographs the intersubjective embodiments of real and virtual dancers, and spectators. Destabilizing the human body as a locus of perception, movement, and sensation, mocap triggers uncanny uncertainty in human volition. In this way, Ghostcatching and as.phyx.ia reflect the infiltration of computer vision technologies, such as facial recognition, into numerous aspects of contemporary life. Through these works, the author hopes to show how the digital gaze of these algorithms, imperceptible to the human eye, threatens individual autonomy with automation.

2019 ◽  
Vol 31 (6) ◽  
pp. 844-850 ◽  
Author(s):  
Kevin T. Huang ◽  
Michael A. Silva ◽  
Alfred P. See ◽  
Kyle C. Wu ◽  
Troy Gallerani ◽  
...  

OBJECTIVERecent advances in computer vision have revolutionized many aspects of society but have yet to find significant penetrance in neurosurgery. One proposed use for this technology is to aid in the identification of implanted spinal hardware. In revision operations, knowing the manufacturer and model of previously implanted fusion systems upfront can facilitate a faster and safer procedure, but this information is frequently unavailable or incomplete. The authors present one approach for the automated, high-accuracy classification of anterior cervical hardware fusion systems using computer vision.METHODSPatient records were searched for those who underwent anterior-posterior (AP) cervical radiography following anterior cervical discectomy and fusion (ACDF) at the authors’ institution over a 10-year period (2008–2018). These images were then cropped and windowed to include just the cervical plating system. Images were then labeled with the appropriate manufacturer and system according to the operative record. A computer vision classifier was then constructed using the bag-of-visual-words technique and KAZE feature detection. Accuracy and validity were tested using an 80%/20% training/testing pseudorandom split over 100 iterations.RESULTSA total of 321 total images were isolated containing 9 different ACDF systems from 5 different companies. The correct system was identified as the top choice in 91.5% ± 3.8% of the cases and one of the top 2 or 3 choices in 97.1% ± 2.0% and 98.4 ± 13% of the cases, respectively. Performance persisted despite the inclusion of variable sizes of hardware (i.e., 1-level, 2-level, and 3-level plates). Stratification by the size of hardware did not improve performance.CONCLUSIONSA computer vision algorithm was trained to classify at least 9 different types of anterior cervical fusion systems using relatively sparse data sets and was demonstrated to perform with high accuracy. This represents one of many potential clinical applications of machine learning and computer vision in neurosurgical practice.


2016 ◽  
Vol 24 (1) ◽  
pp. 143-182 ◽  
Author(s):  
Harith Al-Sahaf ◽  
Mengjie Zhang ◽  
Mark Johnston

In the computer vision and pattern recognition fields, image classification represents an important yet difficult task. It is a challenge to build effective computer models to replicate the remarkable ability of the human visual system, which relies on only one or a few instances to learn a completely new class or an object of a class. Recently we proposed two genetic programming (GP) methods, one-shot GP and compound-GP, that aim to evolve a program for the task of binary classification in images. The two methods are designed to use only one or a few instances per class to evolve the model. In this study, we investigate these two methods in terms of performance, robustness, and complexity of the evolved programs. We use ten data sets that vary in difficulty to evaluate these two methods. We also compare them with two other GP and six non-GP methods. The results show that one-shot GP and compound-GP outperform or achieve results comparable to competitor methods. Moreover, the features extracted by these two methods improve the performance of other classifiers with handcrafted features and those extracted by a recently developed GP-based method in most cases.


Author(s):  
Binbin Zhao ◽  
Shihong Liu

AbstractComputer vision recognition refers to the use of cameras and computers to replace the human eyes with computer vision, such as target recognition, tracking, measurement, and in-depth graphics processing, to process images to make them more suitable for human vision. Aiming at the problem of combining basketball shooting technology with visual recognition motion capture technology, this article mainly introduces the research of basketball shooting technology based on computer vision recognition fusion motion capture technology. This paper proposes that this technology first performs preprocessing operations such as background removal and filtering denoising on the acquired shooting video images to obtain the action characteristics of the characters in the video sequence and then uses the support vector machine (SVM) and the Gaussian mixture model to obtain the characteristics of the objects. Part of the data samples are extracted from the sample set for the learning and training of the model. After the training is completed, the other parts are classified and recognized. The simulation test results of the action database and the real shot video show that the support vector machine (SVM) can more quickly and effectively identify the actions that appear in the shot video, and the average recognition accuracy rate reaches 95.9%, which verifies the application and feasibility of this technology in the recognition of shooting actions is conducive to follow up and improve shooting techniques.


2021 ◽  
Author(s):  
Pawel Kozlowski ◽  
Yong Kim ◽  
Brian Haines ◽  
Thomas Day ◽  
Thomas Murphy ◽  
...  

Author(s):  
Leanne Findlay ◽  
Elizabeth Beasley ◽  
Jungwee Park ◽  
Dafna Kohen ◽  
Yann Algan ◽  
...  

IntroductionLinked administrative data sets are an emerging tool for studying the health and well-being of the population. Previous papers have described methods for linking Canadian data, although few have specifically focused on children, nor have they described linkage between tax outcomes and a cohort of children who are particularly at risk for poor financial outcomes. Objective and methodsThis paper describes a probabilistic linkage performed by Statistics Canada linking the Montreal Longitudinal Experimental Study (MLES) and the Quebec Longitudinal Study of Kindergarten Children (QLSKC) survey cohorts and administrative tax data from 1992 through 2012. ResultsThe number of valid cases in the original cohort file with valid tax records was approximately 84\%. Rates of false positives, false negatives, sensitivity, and specificity of the linkage were all acceptable. Using the linked file, the relationship of childhood behavioural indicators and adult income can be investigated in future studies. ConclusionsInnovative methods for creating longitudinal datasets on children will assist in examining long-term outcomes associated with early childhood risk and protective factors as well as an evidence base for interventions that promote child well-being and positive outcomes.


2009 ◽  
Vol 34 (3) ◽  
pp. 580-594 ◽  
Author(s):  
Anthony R. Magee ◽  
Ben-Erik van Wyk ◽  
Patricia M. Tilney ◽  
Stephen R. Downie

Generic circumscriptions and phylogenetic relationships of the Cape genera Capnophyllum, Dasispermum, and Sonderina are explored through parsimony and Bayesian inference analyses of nrDNA ITS and cpDNA rps16 intron sequences, morphology, and combined molecular and morphological data. The relationship of these genera with the North African genera Krubera and Stoibrax is also assessed. Analyses of both molecular data sets place Capnophyllum, Dasispermum, Sonderina, and the only southern African species of Stoibrax (S. capense) within the newly recognized Lefebvrea clade of tribe Tordylieae. Capnophyllum is strongly supported as monophyletic and is distantly related to Krubera. The monotypic genus Dasispermum and Stoibrax capense are embedded within a paraphyletic Sonderina. This complex is distantly related to the North African species of Stoibrax in tribe Apieae, in which the type species, Stoibrax dichotomum, occurs. Consequently, Dasispermum is expanded to include both Sonderina and Stoibrax capense. New combinations are formalized for Dasispermum capense, D. hispidum, D. humile, and D. tenue. An undescribed species from the Tanqua Karoo in South Africa is also closely related to Capnophyllum and the Dasispermum–Sonderina complex. The genus Scaraboides is described herein to accommodate the new species, S. manningii. This monotypic genus shares the dorsally compressed fruit and involute marginal wings with Capnophyllum, but is easily distinguished by its erect branching habit, green leaves, scabrous umbels, and fruit with indistinct median and lateral ribs, additional solitary vittae in each marginal wing, and parallel, closely spaced commissural vittae. Despite the marked fruit similarities with Capnophyllum, analyses of DNA sequence data place Scaraboides closer to the Dasispermum–Sonderina complex, with which it shares the erect habit, green (nonglaucous) leaves, and scabrous umbels.


Author(s):  
Audri Phillips

This chapter examines the relationships between technology, the human mind, and creativity. The chapter cannot possibly cover the whole spectrum of the aforementioned; nonetheless, it covers highlights that especially apply to new immersive technologies. The nature of creativity, creativity studies, the tools, languages, and technology used to promote creativity are discussed. The part that the mind and the senses—particularly vision—play in immersive media technology, as well as robotics, artificial intelligence (AI), computer vision, and motion capture are also discussed. The immersive transmedia project Robot Prayers is offered as a case study of the application of creativity and technology working hand in hand.


Author(s):  
Marta Dopieralski

This article aims to outline the distributed agency within the creation of computer-generated characters for live-action movies that use Motion Capture techniques. This technique requires a tight interplay between human actors, technical artefacts and digital processes. With the help of ANT the relationships within this heterogeneous collective can be presented more precisely in order to assign agency to human and non-human participants. Considerations concerning a combined interplay of humans and computer-driven actions result in the figure of the hybrid actor. Gollum, a computer-generated character from Peter Jackson's adaptation of the Lord of the Rings, serves as case example to carve out the attributes of this composite agent. The aim of the article is to show how these types of agents tackle the film industry's inherent ontology revolving around human actors and their products. The article contributes an insight how the mentioned network reacts to the emerging problem of crediting in the context of Motion Capture as technical innovation and how the involved community preserves their notion of artistry.


Geophysics ◽  
2016 ◽  
Vol 81 (5) ◽  
pp. IM109-IM118
Author(s):  
Dimitrios Economou ◽  
Behzad Alaei

Numerous publications have dealt with estimations of resistivity from elastic parameters and vice versa. Attempts have been made in the cross-property relationship of elastic and electric properties, in particular, velocity to resistivity using different parameters, such as porosity and water saturation. These types of transforms are currently used to predict background seismic velocities and resistivities, or even start models for seismic or controlled source electromagnetic (CSEM) inversions. However, they are not reliable predictors because they depict the regional elastic or electric variations with limited accuracy. We present a novel approach for the development of models capable of estimating the regional subsurface resistivity based on information from regional wells and seismic inversions. We apply multivariate nonlinear regression on data derived from regional wells and seismic inversions and subsequently produced an estimation of subsurface horizontal resistivity that could be either used as a direct hydrocarbon indicator or provide a constraint on the horizontal resistivity in anisotropic CSEM inversions. We have verified the validity of the approach using two data sets from the Norwegian continental shelf. We found very good agreement between the borehole-measured and predicted resistivity.


1994 ◽  
Vol 165 (3) ◽  
pp. 353-356 ◽  
Author(s):  
E. O'Callaghan ◽  
P. C. Sham ◽  
N. Takei ◽  
G. Murray ◽  
G. Glover ◽  
...  

BackgroundRecently, several investigators have reported an association between influenza epidemics and increased birth rates of ‘preschizophrenic’ individuals some four to six months later. Here we examine whether maternal exposure to other infectious diseases can also predispose the foetus to later schizophrenia.MethodTwo independent sets of dates of birth of first admission schizophrenic patients, born between 1938 and 1965 in England and Wales, were obtained from the Mental Health Enquiry in England and Wales. Data on the number of deaths per month from 16 infectious diseases between 1937 and 1965 in England and Wales were also collected. We used a Poisson regression model to examine the relationship between deaths from infectious diseases and schizophrenic births.ResultsIn the two separate data sets, increased national deaths from bronchopneumonia preceded, by three and five months respectively, increased numbers of schizophrenic births. We did not find any other significant associations between schizophrenic births and any of the other 15 infectious diseases.ConclusionsThe association between deaths from bronchopneumonia and increased schizophrenic births some months later may be a reflection of the fact that bronchopneumonia deaths increase markedly during influenza epidemics.


Sign in / Sign up

Export Citation Format

Share Document