SELF-POSITION ESTIMATION DEVICE, SELF-POSITION ESTIMATION METHOD, AND PROGRAM

• Main Authors: KAJIWARA YASUHIRO, HASHIMOTO YASUKO, TAKAZAWA KAZUHIRO, MATSUSHITA KAZUFUMI, SHIRATAKA YASUKO, SADASUE TAMON, AOKI MASARU
• Format: Patent
• Language: English; Japanese
• Published: 01.09.2016
• Subjects: CALCULATING; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; MEASURING; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS; MEASURING LENGTH, THICKNESS OR SIMILAR LINEARDIMENSIONS; PHYSICS; SIGNALLING; TESTING; TRAFFIC CONTROL SYSTEMS

PROBLEM TO BE SOLVED: To provide a self-position estimation device, a self-position estimation method, and a program capable of accurately estimating a self-position by generating an initial environment map to be used for estimating the self-position.SOLUTION: A self-position estimation device is configured to extract the feature point of an object from a time series image successively input from an image input part (camera) 11, and to track the extracted feature point to calculate a moving vector, and to determine, on the basis of the length and direction of the calculated moving vector at the feature point, whether or not the feature point is a mobile object, and to remove, when determining that the feature point is the mobile object, an object corresponding to the feature point from the time series image, and to generate map information including the coordinates in the world coordinate system of the unremoved object at the feature point, and to estimate a self-position on the basis of the generated map information.SELECTED DRAWING: Figure 2 【課題】自己位置の推定に用いる初期の環境地図を生成して精度良く自己位置を推定することができる自己位置推定装置、自己位置推定方法およびプログラムを提供する。【解決手段】本発明に係る自己位置推定装置は、画像入力部（カメラ）１１から順に入力された時系列画像から物体の特徴点を抽出して、抽出した特徴点を追跡して移動ベクトルを算出する。そして、算出された特徴点の移動ベクトルの長さ及び方向に基づいて、特徴点が移動物体であるか否かを判定し、特徴点が移動物体であると判定した場合、特徴点に対応する物体を時系列画像から除去し、除去されなかった特徴点の物体の世界座標系における座標を含む地図情報を生成し、生成した地図情報に基づいて自己位置を推定する。【選択図】図２