Distance transform

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

Optical object recognition system

Abstract: An object recognition system comprises a memory for storing a plurality of distance ranges with different distance labels associated with respective distance ranges. The controller converts measured distance values into distance labels according to distance ranges to which the distance values belong. The controller groups the sections or windows of a captured image based on assigned distance labels. Detection area or viewing area of the sensors is divided into a plurality of distance ranges according to tolerance of the measured distance such that broader distance range is defined as the distance from the system is larger. The controller scans the windows with distance labels using a template that defines a joining relationship for the windows and assigns each window with a cluster label that is a combination of the distance label and a occurrence indicia, which is the same for the windows that satisfy the joining relationship. The controller unites the windows having the same cluster labels into a cluster, generates three dimensional data of each of said clusters and combines the clusters that are positioned close to each other based on the three dimensional data to form a candidate of a physical object. The system includes a memory for storing three dimensional data of one or more physical objects that were recognized in previous recognition cycle. The controller infers a physical object which would be recognized in the current cycle based on the stored data and a speed of the vehicle relative to the physical object. The controller compares the inferred physical object with said candidate of a physical object to recognize a physical object.

Witnessed k-Distance

Abstract: Distance functions to compact sets play a central role in several areas of computational geometry. Methods that rely on them are robust to the perturbations of the data by the Hausdorff noise, but fail in the presence of outliers. The recently introduced distance to a measure offers a solution by extending the distance function framework to reasoning about the geometry of probability measures, while maintaining theoretical guarantees about the quality of the inferred information. A combinatorial explosion hinders working with distance to a measure as an ordinary power distance function. In this paper, we analyze an approximation scheme that keeps the representation linear in the size of the input, while maintaining the guarantees on the inference quality close to those for the exact but costly representation.

Method for estimating volumetric distance maps from 2D depth images

Abstract: A volumetric distance map of an object is generated from one or more depth images of the object. Each depth image is projected onto the object by casting parallel rays to the object. The parallel rays are cast perpendicular to the depth image. Sample points in a projected distance volume represent distances from the distance map to a surface of the object. The magnitude of a local gradient at each sample point of the projected distance volume is determined, and each distance at each sample point is divided by the magnitude of the corresponding local gradient at each sample point to obtain a scalar distance to a closest surface of the object.