Search results for "Computer Vision"
showing 10 items of 2353 documents
An inductive learning perspective on automated generation of feature models from given product specifications
2018
For explicit representation of commonality and variability of a product line, a feature model is mostly used. An open question is how a feature model can be inductively learned in an automated way from a limited number of given product specifications in terms of features.We propose to address this problem through machine learning, more precisely inductive generalization from examples. However, no counter-examples are assumed to exist. Basically, a feature model needs to be complete with respect to all the given example specifications. First results indicate the feasibility of this approach, even for generating hierarchies, but many open challenges remain.
Study of the imaging conditions and processing for the aspect control of specular surfaces
2001
A vision system capable of imaging and detecting defects on reflective nonplanar surfaces in the production line at a high cadence is presented in this paper. Defects are typically dust located under the metallic layer of packaging products used in cosmetic industries. To realize this processing, structured lighting which reveals the defects in the image is proposed. Defects appear clearly in the images like a set of brilliant pixels in dark zones. The signature of the defect is then obtained. The size of this signature does not depend linearly on the size of the defect. It is a function of the observation angle. In order to realize a precise and robust process, the necessity of acquiring s…
Automatic texture mapping on real 3D model
2007
We propose a full automatic technique to project virtual texture on a real textureless 3D object. Our system is composed of cameras and projector and are used to determine the pose of the object in the real world with the projector as reference and then estimate the image seen by the projector if it would be a camera.
Novel view synthesis for projective texture mapping on real 3D objects
2006
Industrial reproduction, as stereography or lithography, have a lack in texture information, as they only deal with 3D reconstruction. In this paper, we provide a new technique to map texture on real 3D objects, by synthesizing a novel view from two camera images to a projector frame, considered as a camera acting in reverse. No prior information on the pose or the shape of the 3D object is necessary, however hard calibration of the complete system is needed.
A Non-linear Diffeomorphic Framework for Prostate Multimodal Registration
2011
International audience; This paper presents a novel method for non-rigid registration of prostate multimodal images based on a nonlinear framework. The parametric estimation of the non-linear diffeomorphism between the 2D fixed and moving images has its basis in solving a set of non-linear equations of thin-plate splines. The regularized bending energy of the thin-plate splines along with the localization error of established correspondences is jointly minimized with the fixed and transformed image difference; where, the transformed image is represented by the set of non-linear equations defined over the moving image. The traditional thin-plate splines with established correspondences may p…
Texture Guided Active Appearance Model Propagation for Prostate Segmentation
2010
Fusion of Magnetic Resonance Imaging (MRI) and Trans Rectal Ultra Sound (TRUS) images during TRUS guided prostate biopsy improves localization of the malignant tissues. Segmented prostate in TRUS and MRI improve registration accuracy and reduce computational cost of the procedure. However, accurate segmentation of the prostate in TRUS images can be a challenging task due to low signal to noise ratio, heterogeneous intensity distribution inside the prostate, and imaging artifacts like speckle noise and shadow. We propose to use texture features from approximation coefficients of Haar wavelet transform for propagation of a shape and appearance based statistical model to segment the prostate i…
EMMA: An Adaptive Display for Virtual Therapy
2007
Environments used up to now for therapeutic applications are invariable ones. Their contents can not be changed neither by the therapist nor by the patient. However, this is a technical issue that can be solved with current technology. In this paper, we describe a virtual environment that has been developed taking into account this factor. The main technical feature of the environment is that its aspect can be modified controlled by the therapist that conducts the clinical sessions depending on the emotions that the patient is feeling at each moment, and depending on the purpose of the clinical session. The environment has been applied for the treatment of post traumatic stress disorder, pa…
Compactifying Torus Fibrations Over Integral Affine Manifolds with Singularities
2021
This is an announcement of the following construction: given an integral affine manifold B with singularities, we build a topological space X which is a torus fibration over B. The main new feature of the fibration X → B is that it has the discriminant in codimension 2.
Markerless 2D kinematic analysis of underwater running : A deep learning approach
2018
Kinematic analysis is often performed with a camera system combined with reflective markers placed over bony landmarks. This method is restrictive (and often expensive), and limits the ability to perform analyses outside of the lab. In the present study, we used a markerless deep learning-based method to perform 2D kinematic analysis of deep water running, a task that poses several challenges to image processing methods. A single GoPro camera recorded sagittal plane lower limb motion. A deep neural network was trained using data from 17 individuals, and then used to predict the locations of markers that approximated joint centres. We found that 300–400 labelled images were sufficient to tra…
ROS/Gazebo-Based Simulation of Quadcopter Aircrafts
2018
The main purpose of this work is to present a tutorial description on how to design and develop an observer, which is capable of estimating the position and the orientation of a drone commanded by a controller, whose shape and structure are unknown. Starting from Newton's and Euler's laws, a mathematical model describing the dynamics of a quadcopter has first been obtained. By linearizing this model it is possible to implement a Luenberger observer and validate it with simulations in a Linux environment, thanks to the use of the Ardupilot controller and the Gazebo simulator. Finally, starting from the results obtained from the simulation, it is possible to evaluate the error made in the est…