Search results for "artificial intelligence"

Skeletons for parallel image processing: an overview of the SKiPPER project

2002

International audience; This paper is a general overview of the SKIPPER project, run at Blaise Pascal University between 1996 and 2002. The main goal of the SKIPPER project was to demonstrate the appli- cability of skeleton-based parallel programming techniques to the fast prototyping of reactive vision applications. This project has produced several versions of a full-fledged integrated pa- rallel programming environment (PPE). These PPEs have been used to implement realistic vi- sion applications, such as road following or vehicle tracking for assisted driving, on embedded parallel platforms embarked on semi-autonomous vehicles. All versions of SKIPPER share a common front-end and reperto…

Subcutaneous veins detection and backprojection method using Frangi vesselness filter

2015

Blood vessels detection is a common task performed in numerous medical procedures. During regular medical treatments venipuncture procedures are performed for invasive medication and blood sampling. Near infrared imaging technology can be used to visualize the subcutaneous veins in cases of difficult venous access. In this paper the methods for veins centerline detection and back projection is presented. In order to highlight the suitable veins for venipuncture, the centerline of larger veins are detected and back projected to the original image. The method is applied on the near infrared images of subjects selected from four different classes of skin tone. This can be helpful to medical st…

2021

Abstract Reliable patient-specific ventricular repolarization times (RTs) can identify regions of functional block or afterdepolarizations, indicating arrhythmogenic cardiac tissue and the risk of sudden cardiac death. Unipolar electrograms (UEs) record electric potentials, and the Wyatt method has been shown to be accurate for estimating RT from a UE. High-pass filtering is an important step in processing UEs, however, it is known to distort the T-wave phase of the UE, which may compromise the accuracy of the Wyatt method. The aim of this study was to examine the effects of high-pass filtering, and improve RT estimates derived from filtered UEs. We first generated a comprehensive set of UE…

Color superposition: a new modality for contrast echocardiography.

1987

To improve the estimation of endocardial borders in echocardiography, a technique has been developed to combine images from contrasted and noncontrasted echocardiograms of the same heart-phase using a color superposition mode. This method allows both experienced as well as less experienced examiners to define the endocardial borders more reproducibly and objectively. This is achieved by displaying tissue structures as gray level images while the ventricular cavity is marked selectively by the color display of the contrast material zone. Results of volume estimations of the left ventricle by different examiners using several imaging modes including color superposition display are presented.

Saliency Features for 3D CAD-Data in the Context of Sampling-Based Motion Planning

2021

In this paper, we consider disassembly scenarios for real-world 3D CAD-data, where each component is defined by a triangle mesh. For a fast construction of collision-free disassembly paths, common approaches use sampling-based rigid body motion planning which is well studied in the literature. One fact that has so far received little attention is that in industrial disassembly scenarios components are often attached to each other with flexible fastening elements like clips. In the planning process, the fastening elements show the following characteristics: 1) They can cause complex non-linear disassembly paths. 2) They are often deformable. 3) They are usually modeled in a relaxed state and…

Multi-domain Feature of Event-Related Potential Extracted by Nonnegative Tensor Factorization: 5 vs. 14 Electrodes EEG Data

2012

As nonnegative tensor factorization (NTF) is particularly useful for the problem of underdetermined linear transform model, we performed NTF on the EEG data recorded from 14 electrodes to extract the multi-domain feature of N170 which is a visual event-related potential (ERP), as well as 5 typical electrodes in occipital-temporal sites for N170 and in frontal-central sites for vertex positive potential (VPP) which is the counterpart of N170, respectively. We found that the multi-domain feature of N170 from 5 electrodes was very similar to that from 14 electrodes and more discriminative for different groups of participants than that of VPP from 5 electrodes. Hence, we conclude that when the …

Efficient Dense Disparity Map Reconstruction using Sparse Measurements

2018

International audience; In this paper, we propose a new stereo matching algorithm able to reconstruct efficiently a dense disparity maps from few sparse disparity measurements. The algorithm is initialized by sampling the reference image using the Simple Linear Iterative Clustering (SLIC) superpixel method. Then, a sparse disparity map is generated only for the obtained boundary pixels. The reconstruction of the entire disparity map is obtained through the scanline propagation method. Outliers were effectively removed using an adaptive vertical median filter. Experimental results were conducted on the standard and the new Middlebury datasets show that the proposed method produces high-quali…

A Kalman filter single point positioning for maritime applications using a smartphone

2020

Different positioning techniques have been largely adopted for maritime applications that require high accuracy kinematic positioning. The main objective of the paper is the performance assessment of a Single Point Positioning algorithm (SPP), with a Kalman filter (KF) estimator, adapted for maritime applications. The KF has been chosen as estimation technique due to the ability to consider both the state vector dynamic and the measurements. Particularly, in order to compute an accurate vertical component of the position, suitable for maritime applications, the KF settings have been modified by tuning the covariance matrix of the process noise. The algorithm is developed in Matlab environme…

Intra-visual conflict in visually induced motion sickness

2011

Abstract Motion sickness (MS) can be a debilitating side-effect not just of sea travel, but also when immersed in video games or virtual environments (visually induced MS). To explore the impact of visual display parameters on motion sickness, we presented footage taken on an automobile race track to different groups of observers during three experiments. In Experiment 1, one group watched the movie wearing a head-mounted display (HMD) and a second group looked at a large projection screen with unrestricted view. Resolution and visual angle were equated. In contrast to common assumption, the projection screen produced significantly higher motion sickness scores than the HMD. To understand t…

General remarks on the role of the vestibular system in weightlessness

1987

Different methods are described to experimentally achieve weightlessness. Since the function of the otolith system depends on the presence of contact forces opposing gravity, it is disabled in weightlessness and may send misleading positional information to the brain. Without the contributions of the otolith system it is difficult in space to distinguish self-motion from object motion. Furthermore, the disintegration of information from the neck position receptors from those of the otolith system can lead to additional illusory positional sensations. Since the function of the semicircular canal system in previous space flights was found to be essentially undisturbed, the vestibular experime…