Title:
クラス分け処理結果の評定と時間的安定化のための方法
Document Type and Number:
Japanese Patent JP4284322
Kind Code:
B2
Abstract:
Classification methods are described that proceed in computer-assisted fashion, and in particular a method for evaluation and stabilization over time of classification results is described in which objects to be classified are sensed using sensors over a period of time, and are repeatedly classified with the inclusion of specific quality parameters for each object class. To ensure better classification reliability, the following steps may be carried out: a) increasing the value of the confidence parameter if a subsequent classification confirms the result of a previous classification; b) decreasing the value of the confidence parameter if a subsequent classification does not confirm the result of a previous classification; and c) generating a final classification result including the confidence parameters that have been increased or decreased in value.
Inventors:
Jimon Stefan
Zebastian Lindner
Henning Felts
Zebastian Lindner
Henning Felts
Application Number:
JP2005518315A
Publication Date:
June 24, 2009
Filing Date:
September 03, 2004
Export Citation:
Assignee:
ROBERT BOSCH GMBH
International Classes:
G06T7/00; G08G1/017; G08G1/16
Domestic Patent References:
| JP10011575A | ||||
| JP2001174551A | ||||
| JP64007276A | ||||
| JP11203483A |
Other References:
中川龍童,外2名,固有空間法を用いた未知物体学習可能な物体認識,電子情報通信学会2002年総合大会講演論文集(情報・システム2),日本,社団法人電子情報通信学会,2002年 3月 7日,p.222~222
Attorney, Agent or Firm:
Toshio Yano
Einzel Felix-Reinhard
Reinhard Einsel
Einzel Felix-Reinhard
Reinhard Einsel