OBJECT RECOGNITION DEVICE AND OBJECT RECOGNITION METHOD

To classify a plurality of objects existing adjacent to each other with good accuracy.SOLUTION: An object recognition device 10 comprises: a detection point cloud acquisition unit 22 for acquiring a detection point cloud composed of a plurality of detection points KP representing objects Ob1, Ob2, Ob3, Ob4; a contour point cloud acquisition unit 23 for extracting a contour point cloud RP of an object from the detection point cloud and acquiring a contour point cloud; a representative point cloud acquisition unit 24 for acquiring a representative point cloud by extracting a representative point DP from the contour point cloud; an inverse protrusion assessment unit 25 for determining whether or not an inverse protrusion shape ITs is included in the contour point cloud by using an inter-vector angle θ between a first vector V1 and a second vector V2, where three points extracted from the representative point cloud are a first point P1, a second point P2 and a third point P3, the first vector V1 being a vector of the first point and the second point, and the second vector V2 being a vector of the second point and the third point; and an object recognition unit 26 that recognizes that a linear object and an object different from the linear object exist adjacent to each other when it is determined that an inverse protrusion shape is included.SELECTED DRAWING: Figure 2 【課題】互いに近接して存在する複数の物体を精度よく区分する。【解決手段】物体認識装置１０は、物体Ｏｂ１、Ｏｂ２、Ｏｂ３、Ｏｂ４を表す複数の検出点ＫＰにより構成される検出点群を取得する検出点群取得部２２と、検出点群から物体の輪郭点ＲＰを抽出して輪郭点群を取得する輪郭点群取得部２３と、輪郭点群から代表点ＤＰを抽出することにより代表点群を取得する代表点群取得部２４と、代表点群から選択された３点を第１点Ｐ１、第２点Ｐ２および第３点Ｐ３とし、第１点と第２点とのベクトルである第１ベクトルＶ１と、第２点と第３点とのベクトルである第２ベクトルＶ２との間の角度であるベクトル間角度θを用いて、輪郭点群に逆凸形状ＩＴｓが含まれるか否かを判定する逆凸判定部２５と、逆凸形状が含まれると判定された場合に、直線状の物体と、直線状の物体とは異なる物体とが互いに近接して存在していると認識する物体認識部２６と、を備える。【選択図】図２