Distance transform

About: Distance transform is a research topic. Over the lifetime, 2886 publications have been published within this topic receiving 59481 citations.

Real-time meshless deformation: Collision Detection and Deformable Objects

Abstract: In this paper, we articulate a meshless computational paradigm for the effective modeling, accurate physical simulation, and real-time animation of point-sampled solid objects. Both the interior and the boundary geometry of our volumetric object representation only consist of points, further extending the powerful and popular method of point-sampled surfaces to the volumetric setting. We build the point-based physical model upon continuum mechanics, which affords to effectively model the dynamic elastic behavior of point-based volumetric objects. When only surface samples are provided, our prototype system first generates both interior volumetric points and a volumetric distance field with octree structure. The physics of these volumetric points in a solid interior are simulated using the Meshless Moving Least Squares (MLS) shape functions. In sharp contrast to the traditional finite element method (FEM), the meshless property of our new technique expedites the accurate representation and precise simulation of the underlying discrete model, without the need of domain meshing. In order to achieve real-time simulations, we utilize the warped modal analysis method that is locally linear in nature but globally warped to account for rotational deformation. The structural simplicity and real-time performance of our meshless simulation framework are ideal for interactive animation and game/movie production. Copyright © 2005 John Wiley & Sons, Ltd.

Human detection device and method and program of the same

Abstract: There is provided a human detection device capable of determining whether a human exists in an infrared image with information only contained in the infrared image at high speed with high accuracy regardless of an ambient environment temperature. The human detection device includes: a boundary information extracting unit which receives infrared image data and detects a boundary of a small image region based on a pixel value of a pixel to specify a boundary pixel; a distance converting unit which calculates a shortest distance between each pixel contained in the small image region and the boundary pixel; a processing unit which extracts a pixel having the shortest distance satisfying a predetermined condition, from the pixels contained in the small image region; and a determining unit which performs pattern matching by comparing image data with a predetermined pattern based on the pixel having the shortest distance to determine whether an object shown in the small image region is a human.

Learning class-to-image distance via large margin and l1-norm regularization

Abstract: Image-to-Class (I2C) distance has demonstrated its effectiveness for object recognition in several single-label datasets. However, for the multi-label problem, where an image may contain several regions belonging to different classes, this distance may not work well since it cannot discriminate local features from different regions in the test image and all local features have to be counted in the I2C distance calculation. In this paper, we propose to use Class-to-Image (C2I) distance and show that this distance performs better than I2C distance for multi-label image classification. However, since the number of local features in a class is huge compared to that in an image, the calculation of C2I distance is much more expensive than I2C distance. Moreover, the label information of training images can be used to help select relevant local features for each class and further improve the recognition performance. Therefore, to make C2I distance faster and perform better, we propose an optimization algorithm using L1-norm regularization and large margin constraint to learn the C2I distance, which will not only reduce the number of local features in the class feature set, but also improve the performance of C2I distance due to the use of label information. Experiments on MSRC, Pascal VOC and MirFlickr datasets show that our method can significantly speed up the C2I distance calculation, while achieves better recognition performance than the original C2I distance and other related methods for multi-labeled datasets.

Distance image generation device, distance image generation method, and program

Abstract: PROBLEM TO BE SOLVED: To provide a distance image generation device, a distance image generation method, and a program capable of generating a distance image, having high reliability by acquiring a high-precision operation result in an operation of a subpixel level, while reducing the total processing time. SOLUTION: The distance image generation device includes an image acquisition means for acquiring first image information and second image information to be a comparison object; a first calculation part 15 for comparing a standard image and a reference image by an SAD calculation method to calculate a parallax value in a pixel level; a second calculation part 16 for comparing the standard image and the reference image by a POC calculation method having higher accuracy than that of the SAD calculation method to calculate the parallax value in the subpixel level; and an object area setting part 14 for setting the object area for performing the calculation by the second calculation part 16, on the basis of the calculation result of the parallax value by the first calculation part 15. COPYRIGHT: (C)2008,JPO&INPIT