Order-independent transparency (OIT) rendering is computationally intensive due to required sorting and sufficient memory to store fragments before sorting. We present Dynamic Fragment Buffer, a revamped two-pass OIT ...
详细信息
Order-independent transparency (OIT) rendering is computationally intensive due to required sorting and sufficient memory to store fragments before sorting. We present Dynamic Fragment Buffer, a revamped two-pass OIT rendering technique, which performs correct blending of a large number of transparent layers at interactive frame rates. Our approach self-adjusts memory allocation to handle a variable number of fragments per pixel without wasting memory. In this paper we perform a detailed analysis of several design decisions which lead to this technique. We present a collection of experiments that illustrate the advantages of our technique with respect to others OIT algorithms in the literature.
This survey provides GLSL information for beginners, by means of a series of commented codes and technical explanations, providing an effective way for learning GLSL, one of the main multi-platform and multi-hardware ...
详细信息
This survey provides GLSL information for beginners, by means of a series of commented codes and technical explanations, providing an effective way for learning GLSL, one of the main multi-platform and multi-hardware shader programming languages available. The examples increase in complexity through the text. They may run in several shader tools, including Shaderlabs, a shader development environment, which was developed aiming at helping those willing to learn and practice GLSL development.
Kinect is a device introduced in November 2010 as an accessory of Xbox 360. The acquired data has different and complementary natures, combining geometry with visual attributes. For this reason, Kinect is a flexible t...
详细信息
Kinect is a device introduced in November 2010 as an accessory of Xbox 360. The acquired data has different and complementary natures, combining geometry with visual attributes. For this reason, Kinect is a flexible tool that can be used in applications from several areas such as: computergraphics, imageprocessing, computer Vision and Human-Machine Interaction. In this way, the Kinect is a widely used device in industry (games, robotics, theater performers, natural interfaces, etc.) and in research. We will initially present some concepts about the device: the architecture and the sensor. We then will discuss about the data acquisition process: capturing, representation and filtering. Capturing process consists of obtaining a colored image (RGB) and performing a depth measurement (D), with structured light technique. This data is represented by a structure called RGBD image. We will also talk about the main tools available for developing applications on various platforms. Furthermore, we will discuss some recent projects based on RGBD images. In particular, those related to Object Recognition, 3D Reconstruction, Augmented Reality, imageprocessing, Robotic, and Interaction. In this survey, we will show some research developed by the academic community and some projects developed for the industry. We intend to show the basic principles to begin developing applications using Kinect, and present some projects developed at the VISGRAF Lab. And finally, we intend to discuss the new possibilities, challenges and trends raised by Kinect.
Recently, Katz et al. have shown how visibility information for a point cloud may be estimated by the so-called HPR operator. In a nutshell, the operator consists of a simple transformation of the cloud followed by a ...
详细信息
Recently, Katz et al. have shown how visibility information for a point cloud may be estimated by the so-called HPR operator. In a nutshell, the operator consists of a simple transformation of the cloud followed by a convex hull computation. Since convex hulls take O(n log n) time to compute in the worst case, this method has been considered impractical for real-time rendering of medium to large point clouds. In this paper, we describe a GPU implementation of an approximate convex-hull algorithm that runs in O(n+k) time, where k is a parameter of the method. Experiments show that the method is suitable for real-time rendering and partial reconstruction of point clouds with millions of points.
This paper presents a novel method for combining the outputs of different gender classification techniques based on facial images. Merging the methods is performed by a committee machine using the Bayesian theorem. We...
详细信息
This paper presents a novel method for combining the outputs of different gender classification techniques based on facial images. Merging the methods is performed by a committee machine using the Bayesian theorem. We implement and compare several well-known individual classifiers on four different datasets, then we experiment the proposed machine, and show that it significantly improves the accuracy of classification compared to individual classifiers. We also include results that address the effect of scale on the performance of classifiers.
An efficient memory bandwidth utilization for GPU accelerators is crucial for memory bound applications. In medical imaging, the performance of many kernels is limited by the available memory bandwidth since only a fe...
详细信息
In this paper we propose a new and efficient texture feature extraction method: the Segmentation-based Fractal Texture Analysis, or SFTA. The extraction algorithm consists in decomposing the input image into a set of ...
详细信息
In this paper we propose a new and efficient texture feature extraction method: the Segmentation-based Fractal Texture Analysis, or SFTA. The extraction algorithm consists in decomposing the input image into a set of binary images from which the fractal dimensions of the resulting regions are computed in order to describe segmented texture patterns. The decomposition of the input image is achieved by the Two-Threshold Binary Decomposition (TTBD) algorithm, which we also propose in this work. We evaluated SFTA for the tasks of content-based image retrieval (CBIR) and image classification, comparing its performance to that of other widely employed feature extraction methods such as Haralick and Gabor filter banks. SFTA achieved higher precision and accuracy for CBIR and image classification. Additionally, SFTA was at least 3.7 times faster than Gabor and 1.6 times faster than Haralick with respect to feature extraction time.
Accuracy in image object detection has been usually achieved at the expense of much computational load. Therefore a trade-off between detection performance and fast execution commonly represents the ultimate goal of a...
详细信息
Accuracy in image object detection has been usually achieved at the expense of much computational load. Therefore a trade-off between detection performance and fast execution commonly represents the ultimate goal of an object detector in real life applications. In this present work, we propose a novel method toward that goal. The proposed method was grounded on a multi-scale spectral residual (MSR) analysis for saliency detection. Compared to a regular sliding window search over the images, in our experiments, MSR was able to reduce by 75% (in average) the number of windows to be evaluated by an object detector. The proposed method was thoroughly evaluated over a subset of Label Me dataset (person images), improving detection performance in most cases.
Recently, investigations on medical imaging have been indicating a strong correlation between cases of cancers and the increasing number of Computed Tomography (CT) exams, mainly due to high radiation doses to which p...
详细信息
Recently, investigations on medical imaging have been indicating a strong correlation between cases of cancers and the increasing number of Computed Tomography (CT) exams, mainly due to high radiation doses to which patients are exposed during the data acquisition process. Thus, there is a need to reduce the radiation doses whereas still keeping satisfactory quality images for diagnosis. In this paper, we propose to filter noise in CT images using contextual versions of Wiener Filter such as Generalized Wiener Filter (GWF) and Non Local Means approach for parameter estimation. Experiments show that the proposed methods are promising, since they provide good results with no significant increase in the computational cost.
Recognizing different kinds of fruits and vegetables is a common task in supermarkets. This task, however, poses several challenges as it requires the identification of different species of a particular produce and al...
详细信息
Recognizing different kinds of fruits and vegetables is a common task in supermarkets. This task, however, poses several challenges as it requires the identification of different species of a particular produce and also its variety. Usually, existing computer-based recognition approaches are not automatic and demand long-term and laborious prior training sessions. This paper presents a novel framework for classifier fusion aiming at supporting the automatic recognition of fruits and vegetables in a supermarket environment. The objective is to provide an effective mechanism for combining low-cost classifiers trained for specific classes of interest. The experiments performed demonstrate that the proposed framework yields better results than several related work found in the literature and represents a step forward automatic produce recognition in cashiers of supermarkets.
暂无评论