We present a probabilistic reliable-inference framework to address the issue of rapid-and-reliable detection of human actions. The approach determines the shortest video exposure needed for low-latency recognition by ...
详细信息
We present a novel approach that uses boundary interpolation to correct (1) geometric distortion and (2) shading artifacts present in images of printed materials. Unlike existing approaches, our algorithm can simultan...
详细信息
We present a novel approach that uses boundary interpolation to correct (1) geometric distortion and (2) shading artifacts present in images of printed materials. Unlike existing approaches, our algorithm can simultaneously correct a variety of geometric distortions, including skew, fold distortion, binder curl, and combinations of these. In addition, the same interpolation framework can estimate the intrinsic illumination component of the distorted image to correct shading artifacts.
Tracking of humans in dynamic scenes has been an important topic of research. Most techniques, however, are limited to situations where humans appear isolated and occlusion is small. Typical methods rely on appearance...
详细信息
Tracking of humans in dynamic scenes has been an important topic of research. Most techniques, however, are limited to situations where humans appear isolated and occlusion is small. Typical methods rely on appearance models that must be acquired when the humans enter the scene and are not occluded. We present a method that can track humans in crowded environments, with significant and persistent occlusion by making use of human shape models in addition to camera models, the assumption that humans walk on a plane and acquired appearance models. Experimental results and a quantitative evaluation are included.
This paper describes a framework for calibrating motion sensitive sensors attached to an autonomous vehicle. Based on camera auto-calibration techniques, we derive constraints relating sensor measurements to the relat...
详细信息
In this paper we describe a method for skeletonization of gray-scale images without segmentation. Our method is based on anisotropic vector diffusion. The skeleton strength map, calculated from the diffused vector fie...
详细信息
In this paper we describe a method for skeletonization of gray-scale images without segmentation. Our method is based on anisotropic vector diffusion. The skeleton strength map, calculated from the diffused vector field, provides us a measure of how possible each pixel could be on the skeletons. The final skeletons are traced from the skeleton strength map, which mimics the behavior of edge detection from the edge strength map of the original image. A couple of real or synthesized images will be shown to demonstrate the performance of our algorithm.
This paper presents a novel hierarchical approach to triangular mesh generation from height fields. A wavelet-based multiresolution analysis technique is used to estimate local shape information at different levels of...
详细信息
This paper presents a novel hierarchical approach to triangular mesh generation from height fields. A wavelet-based multiresolution analysis technique is used to estimate local shape information at different levels of resolution. Using predefined templates at the coarsest level, the method constructs an initial triangulation in which underlying object shapes are well preserved. Wavelet detail coefficients directly control the selection of appropriate templates, and are then used for subdividing and refining the initial mesh.
In this paper we present a novel method for threshold selection. The idea is based upon quantifying the stability of the number of regions segmented as the threshold is varied. We capture this idea using a scale-space...
详细信息
Detection of events is an essential task in surveillance applications. This task requires finding a general event representation method and developing efficient recognition algorithms dealing with this representation....
详细信息
We address the problem of computing closed contours delineating the boundaries of objects of interest from image tangent maps. The Bayesian formulation of this problem incorporates the notion of foreground and backgro...
详细信息
In natural scenes, objects and patterns can appear at a wide variety of distances from the viewer. For the same visual pattern viewed at different distances, both the image and our perception of the pattern change ove...
详细信息
暂无评论