The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.
The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.
Patent No.:
Date of Patent:
Oct. 15, 2013
Filed:
Apr. 02, 2009
Claudius Schnorr, Mannheim, DE;
Peter Krzystek, Munich, DE;
Josef Reitberger, Rinchnach, DE;
Volkan Oniz, Birkenhordt, DE;
Claudius Schnorr, Mannheim, DE;
Peter Krzystek, Munich, DE;
Josef Reitberger, Rinchnach, DE;
Volkan Oniz, Birkenhordt, DE;
Hochschule Munchen, , DE;
Abstract
The invention relates to a method for computer-aided segmentation of an environment into individual objects, in particular of a wood into individual trees, in which signals (SIG_R) backscattered by the objects are recorded by measurement technology, wherein the backscattered signals (SIG_R) result from the irradiation of the environment to be segmented with electromagnetic radiation. Furthermore, in the method according to the invention, spatial co-ordinates (x, y, z) of points which cause the backscattering and represent the object parts (X, X, . . . , X) are determined from the backscattered signals (SIG_R), and a feature vector (f) is assigned to each of the points (P; P, P), which feature vector comprises at least the spatial co-ordinates (x, y, z) of the point in question (P; P, P). Then a distance measure (d) is determined for each of the feature vectors (f), which represents a similarity between the feature vectors (f) of two points (P; P, P). Finally the feature vectors (f) assigned to the points (P; P, P) are allocated to disjoint segments (A, B) in such a manner that a cost function (E) which takes into account the distance measures (d) of all the feature vectors (f) to each other is minimized, as a result of which the segmentation of the environment into individual objects is provided.