Search

This paper proposes a new morphology-based approach for the interslice interpolation of current transformer (CT) and MRI datasets composed of parallel slices. Our approach is object based and accepts as input data binary slices belonging to the same anatomical structure. Such slices may contain one or more regions, since topological changes between two adjacent slices may occur. Our approach handles explicitly interslice topology changes by decomposing a many-to-many correspondence into three fundamental cases: one-to-one, one-to-many, and zero-to-one correspondences. The proposed interpolation process is iterative. One iteration of this process computes a transition sequence between a pair of corresponding input slices, and selects the element located at equal distance from the input slices. This algorithmic design yields a gradual, smooth change of shape between the input slices. Therefore, the main contribution of our approach is its ability to interpolate between two anatomic shapes by creating a smooth, gradual change of shape, and without generating over-smoothed interpolated shapes. [ABSTRACT FROM PUBLISHER]

The accuracy of 3D reconstruction for metrology applications using active stereo pairs depends on the quality of the calibration of the system. Active stereo pairs are generally composed of cameras mounted on tilt/pan mechanisms separated by a constant or variable baseline. This paper presents a calibration approach based on speckle metrology that allows the separation of translation and rotation in the estimation of extrinsic parameters. To achieve speckle-based calibration, a device called an Almost Punctual Speckle Source (APSS) is introduced. Using the APSS, a thorough method for the calibration of extrinsic parameters of stereo pairs is described. Experimental results obtained with a stereo system called the Agile Stereo Pair (ASP) demonstrate that speckle-based calibration achieves better reconstruction performance than methods using standard calibration procedures. Although the experiments were performed with a specific stereo pair, such as the ASP, which is described in the paper, the speckle-based calibration approach using the APSS can be transposed to other stereo setups.

Most man-made objects are composed of a few basic geometric primitives (GPs) such as spheres, cylinders, planes, ellipsoids, or cones. Thus, the object recognition problem can be considered as one of geometric primitives extraction. Among the different geometric primitives, cylinders are the most frequently used GPs in real-world scenes. Therefore, cylinder detection and extraction are of great importance in 3D computer vision. Despite the rapid progress of cylinder detection algorithms, there are still two open problems in this area. First, a robust strategy is needed for the initial sample selection component of the cylinder extraction module. Second, detecting multiple cylinders simultaneously has not yet been investigated in depth. In this paper, a robust solution is provided to address these problems. The proposed solution is divided into three sub-modules. The first sub-module is a fast and accurate normal vector estimation algorithm from raw depth images. With the estimation method, a closed-form solution is provided for computing the normal vector at each point. The second sub-module benefits from the maximally stable extremal regions (MSER) feature detector to simultaneously detect cylinders present in the scene. Finally, the detected cylinders are extracted using the proposed cylinder extraction algorithm. Quantitative and qualitative results show that the proposed algorithm outperforms the baseline algorithms in each of the following areas: normal estimation, cylinder detection, and cylinder extraction.

Physical interactions within virtual environments are often limited to visual information within a restricted workspace. A new system exploiting a cable-driven parallel robot to combine visual and haptic information related to environmental physical constraints (e.g. shelving, object weight) was developed. The aim of this study was to evaluate the impact on user movement patterns of adding haptic feedback in a virtual environment with this robot. Twelve healthy participants executed a manual handling task under three conditions: 1) in a virtual environment with haptic feedback; 2) in a virtual environment without haptic feedback; 3) in a real physical environment. Temporal parameters (movement time, peak velocity, movement smoothness, time to maximum flexion, time to peak wrist velocity) and spatial parameters of movement (maximum trunk flexion, range of motion of the trunk, length of the trajectory, index of curvature and maximum clearance from the shelf) were analysed during the reaching, lowering and lifting phases. Our results suggest that adding haptic feedback improves spatial parameters of movement to better respect the environmental constraints. However, the visual information presented in the virtual environment through the head mounted display appears to have an impact on temporal parameters of movement leading to greater movement time. Taken together, our results suggest that a cable-driven robot can be a promising device to provide a more ecological context during complex tasks in virtual reality.

This work addresses the problem of automatic head pose estimation and its application in 3D gaze estimation using low quality RGB-D sensors without any subject cooperation or manual intervention. The previous works on 3D head pose estimation using RGB-D sensors require either an offline step for supervised learning or 3D head model construction, which may require manual intervention or subject cooperation for complete head model reconstruction. In this paper, we propose a 3D pose estimator based on low quality depth data, which is not limited by any of the aforementioned steps. Instead, the proposed technique relies on modeling the subject's face in 3D rather than the complete head, which, in turn, relaxes all of the constraints in the previous works. The proposed method is robust, highly accurate and fully automatic. Moreover, it does not need any offline step. Unlike some of the previous works, the method only uses depth data for pose estimation. The experimental results on the Biwi head pose database confirm the efficiency of our algorithm in handling large pose variations and partial occlusion. We also evaluated the performance of our algorithm on IDIAP database for 3D head pose and eye gaze estimation.

The driving performance of individuals with mild cognitive impairment (MCI) is suboptimal when compared to healthy older adults. It is expected that the driving will worsen with the progression of the cognitive decline and thus, whether or not these individuals should continue to drive is a matter of debate. The aim of the study was to provide support to the claim that individuals with MCI can benefit from a training program and improve their overall driving performance in a driving simulator. Fifteen older drivers with MCI participated in five training sessions in a simulator (over a 21-day period) and in a 6-month recall session. During training, they received automated auditory feedback on their performance when an error was noted about various maneuvers known to be suboptimal in MCI individuals (for instance, weaving, omitting to indicate a lane change, to verify a blind spot, or to engage in a visual search before crossing an intersection). The number of errors was compiled for eight different maneuvers for all sessions. For the initial five sessions, a gradual and significant decrease in the number of errors was observed, indicating learning and safer driving. The level of performance, however, was not maintained at the 6-month recall session. Nevertheless, the initial learning observed opens up possibilities to undertake more regular interventions to maintain driving skills and safe driving in MCI individuals.

For stereoscopic systems designed for metrology applications, the accuracy of camera calibration dictates the precision of the 3D reconstruction. In this paper, the impact of various calibration conditions on the reconstruction quality is studied using a virtual camera calibration technique and the design file of a commercially available lens. This technique enables the study of the statistical behavior of the reconstruction task in selected calibration conditions. The data show that the mean reprojection error should not always be used to evaluate the performance of the calibration process and that a low quality of feature detection does not always lead to a high mean reconstruction error.

Camera calibration is a critical step in many vision applications. It is a delicate and complex process that is highly sensitive to environmental conditions. This paper presents a novel virtual calibration technique that can be used to study the impact of various factors on the calibration parameters. To highlight the possibilities of the method, the calibration parameters' behavior has been studied regarding the effects of tolerancing and temperature for a specific lens. This technique could also be used in many other promising areas to make calibration in the laboratory or in the field easier.

Background: Driving retraining classes may offer an opportunity to attenuate some effects of aging that may alter driving skills. Unfortunately, there is evidence that classroom programs (driving refresher courses) do not improve the driving performance of older drivers. The aim of the current study was to evaluate if simulator training sessions with video-based feedback can modify visual search behaviors of older drivers while changing lanes in urban driving., Methods: In order to evaluate the effectiveness of the video-based feedback training, 10 older drivers who received a driving refresher course and feedback about their driving performance were tested with an on-road standardized evaluation before and after participating to a simulator training program (Feedback group). Their results were compared to a Control group (12 older drivers) who received the same refresher course and in-simulator active practice as the Feedback group without receiving driving-specific feedback., Results: After attending the training program, the Control group showed no increase in the frequency of the visual inspection of three regions of interests (rear view and left side mirrors, and blind spot). In contrast, for the Feedback group, combining active training and driving-specific feedbacks increased the frequency of blind spot inspection by 100% (32.3 to 64.9% of verification before changing lanes)., Conclusions: These results suggest that simulator training combined with driving-specific feedbacks helped older drivers to improve their visual inspection strategies, and that in-simulator training transferred positively to on-road driving. In order to be effective, it is claimed that driving programs should include active practice sessions with driving-specific feedbacks. Simulators offer a unique environment for developing such programs adapted to older drivers' needs.