Image Processing Using Multiple GPUs on Webcam Image Streams

Munoz, Hannah; Dascalu, Sergiu M.; Wu, Rui; Barford, Lee; HarrisJr., Frederick C.

doi:10.1007/978-3-030-14070-0_44

Cited by 1 publication

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[16,17], can be considered to be outstanding articles in the field since in both cases they do processing using the Graphics Processing Unit (GPU) using CUDA-Cores, causing the processing of the images to be significantly accelerated, neither of the two works have a stage that synchronizes the acquired images in a serial way, i.e., the non-parallel acquisition with parallel processing. Munoz et al in [16] do not use any artificial intelligence tool to analyze the captured data, their proposal is limited to measuring the processing speed. In the case of Lee and Yang in [17], SURF key points are used as an artificial intelligence method, making a design without any tool to analyze its results; the authors expose these results in screenshots of their developed system.…”

Section: Introductionmentioning

confidence: 99%

Biomedical Signal Acquisition Using Sensors under the Paradigm of Parallel Computing

Escobar

Matamoros

Tejeida-Padilla

et al. 2020

Sensors

View full text Add to dashboard Cite

There are several pathologies attacking the central nervous system and diverse therapies for each specific disease. These therapies seek as far as possible to minimize or offset the consequences caused by these types of pathologies and disorders in the patient. Therefore, comprehensive neurological care has been performed by neurorehabilitation therapies, to improve the patients’ life quality and facilitating their performance in society. One way to know how the neurorehabilitation therapies contribute to help patients is by measuring changes in their brain activity by means of electroencephalograms (EEG). EEG data-processing applications have been used in neuroscience research to be highly computing- and data-intensive. Our proposal is an integrated system of Electroencephalographic, Electrocardiographic, Bioacoustic, and Digital Image Acquisition Analysis to provide neuroscience experts with tools to estimate the efficiency of a great variety of therapies. The three main axes of this proposal are: parallel or distributed capture, filtering and adaptation of biomedical signals, and synchronization in real epochs of sampling. Thus, the present proposal underlies a general system, whose main objective is to be a wireless benchmark in the field. In this way, this proposal could acquire and give some analysis tools for biomedical signals used for measuring brain interactions when it is stimulated by an external system during therapies, for example. Therefore, this system supports extreme environmental conditions, when necessary, which broadens the spectrum of its applications. In addition, in this proposal sensors could be added or eliminated depending on the needs of the research, generating a wide range of configuration limited by the number of CPU cores, i.e., the more biosensors, the more CPU cores will be required. To validate the proposed integrated system, it is used in a Dolphin-Assisted Therapy in patients with Infantile Cerebral Palsy and Obsessive–Compulsive Disorder, as well as with a neurotypical one. Event synchronization of sample periods helped isolate the same therapy stimulus and allowed it to be analyzed by tools such as the Power Spectrum or the Fractal Geometry.

show abstract