Terrains are challenging geometric objects for real-time rendering and interactive manipulation. State-of-the-art terrain rendering systems use custom, multi-resolution, representations like geometry clipmaps for fast...
详细信息
Terrains are challenging geometric objects for real-time rendering and interactive manipulation. State-of-the-art terrain rendering systems use custom, multi-resolution, representations like geometry clipmaps for fast rendering on the GPU. In this paper, we present a system that exploits the power and flexibility of the modern GPUs to store, render, and manipulate terrains with minimal CPU involvement. The central idea is to use a regular-grid representation and fixed size blocks/tiles that change in resolution. The potentially visible portion of the terrain is cached at the highest necessary resolution and is rendered from the GPU. The CPU sends a light geometry template which is expanded by the Geometry Shader to the triangles, using the heights stored in the GPU Cache. The CPU performs a coarse culling of the tiles with the GPU performing fine culling. The GPU cache is updated continuously as the viewpoint changes. Our system enables the terrain to be modified procedurally or edited interactively on the GPU with no CPU involvement. The terrain can also interact with a large number of external objects in real-time entirely within the GPU. We achieve a consistent rendering rate of 100 frames per second with terrain modification and interactions as well as a triangle rate of upto 350 million per second on an Nvidia 8800 GTX GPU for large terrains, with a CPU load below 10%.
We present a novel dance posture based annotation model by combining features using Multiple Kernel Learning (MKL). We have proposed a novel feature representation which represents the local texture properties of the ...
详细信息
We present a novel dance posture based annotation model by combining features using Multiple Kernel Learning (MKL). We have proposed a novel feature representation which represents the local texture properties of the image. The annotation model is defined in the direct a cyclic graph structure using the binary MKL algorithm. The bag-of-words model is applied for image representation. The experiments have been performed on the image collection belonging to two indian classical dances (Bharatnatyam and Odissi). The annotation model has been tested using SIFT and the proposed feature individually and by optimally combining both the features. The experiments have shown promising results.
image denoising is a fundamental task in computervision and imageprocessing, crucial for improving the visual quality and interpretability of images captured in noisy environments. In this research, we propose a qua...
详细信息
This paper introduces a novel technique of computational art with mandala—an iconic heritage of indian folk art. Its novelty lies in several fundamental steps. The first one is fixing the asymmetries and the imperfec...
详细信息
ISBN:
(纸本)9798400716256
This paper introduces a novel technique of computational art with mandala—an iconic heritage of indian folk art. Its novelty lies in several fundamental steps. The first one is fixing the asymmetries and the imperfections in a hand-drawn piece of art based on the notion of a primitive map. The primitive map is described using a novel concept of geometric salience—a set of well-defined salient points on the frontier polygon of a primitive—characterizing the concavities and convexities present in the primitive. The primitive map is also used for the vectorization of a mandala and its succinct representation as a mandala sector graph (MSG), which eventually results in efficient graph operations on an existing artwork to create a new piece of art. The use of frontier polygons in different steps of the algorithm makes it robust and efficient. Experimental results on various datasets demonstrate the potential and versatility of the proposed technique.
Recovery of true color from underwater images is an ill-posed problem. This is because the wide-band attenuation coefficients for the RGB color channels depend on object range, reflectance, etc. which are difficult to...
详细信息
We describe a novel method for human activity segmentation and interpretation in surveillance applications based on Gabor filter-bank features. A complex human activity is modeled as a sequence of elementary human act...
详细信息
We describe a novel method for human activity segmentation and interpretation in surveillance applications based on Gabor filter-bank features. A complex human activity is modeled as a sequence of elementary human actions like walking, running, jogging, boxing, hand-waving etc. Since human silhouette can be modeled by a set of rectangles, the elementary human actions can be modeled as a sequence of a set of rectangles with different orientations and scales. The activity segmentation is based on Gabor filter-bank features and normalized spectral clustering. The feature trajectories of an action category are learnt from training example videos using dynamic time warping. The combined segmentation and the recognition processes are very efficient as both the algorithms share the same framework and Gabor features computed for the former can be used for the later. We have also proposed a simple shadow detection technique to extract good silhouette which is necessary for good accuracy of an action recognition technique.
In this paper, we present a fast and efficient algorithm for regularization and resampling of triangular meshes generated by 3D reconstruction methods such as stereoscopy, laser scanning etc. We also present a scheme ...
详细信息
In this paper, we present a fast and efficient algorithm for regularization and resampling of triangular meshes generated by 3D reconstruction methods such as stereoscopy, laser scanning etc. We also present a scheme for efficient parallel implementation of the proposed algorithm and the time gain with increasing number of processor cores.
We propose an evolving scheme to detect slow as well as fast moving objects in a video sequence. The proposed scheme employ both spatio-temporal and temporal segmentation to obtain the video object plane and hence det...
详细信息
We propose an evolving scheme to detect slow as well as fast moving objects in a video sequence. The proposed scheme employ both spatio-temporal and temporal segmentation to obtain the video object plane and hence detection. We propose a compound Markov random field model as the a priori image model that takes into account the spatial distribution of the current frame, temporal frames and the edge maps of the temporal frames. The spatio-temporal segmentation is cast as a pixel labeling problem and the labels are the MAP estimates. The MAP estimates of a frame are obtained by a hybrid algorithm. The spatial segmentation of a given frame evolves to generate the spatial segmentation of the subsequent frames. The evolved spatial segmentation together with the temporal segmentation produces the Video Object Plane (VOP) and hence detection. Our scheme does require the computation of spatio-temporal segmentation of the initial frame thus speeding up the whole process. The results of the proposed scheme are compared with JSEG method are found to be better in terms of the misclassification error.
Recently, near-infrared to visible light facial image matching is gaining popularity, especially for low-light and night-time surveillance scenarios. Unlike most of the work in literature, we assume that the near-infr...
详细信息
Entropy of order q (depending on the information contained in a sequence of gray levels of length q) and conditional entropy of an image are defined. Using these definitions, two algorithms are formulated and implemen...
详细信息
Entropy of order q (depending on the information contained in a sequence of gray levels of length q) and conditional entropy of an image are defined. Using these definitions, two algorithms are formulated and implemented with the help of its co-occurrence matrix. Their superiority for image thresholding (object-background classification) is established.< >
暂无评论