Object position estimation device, object position estimation method and program

摘要

In a technology of acquiring an object position by a visual cone intersection method, an object position estimation device which reduces estimation of incorrect position due to ghost image objects is provided, wherein an object candidate acquisition means estimates an object position by a visual cone intersection method and acquires a candidate object, an object candidate information storage means which stores information on overlap among the candidate objects for the visual cone of the object which is acquired based on the captured image, a degree of co-movement acquisition means acquires an index as a degree of co-movement which is calculated based on number of visual cones including other candidate objects which co-move with a movement of the candidate object and indicates interrelation among candidate objects for candidate objects, and a candidate object determination means identifies said candidate object as either an object or a non-object by a posteriori probability based on the acquired index and outputs position of said candidate object which is determined as an object.

主权项

1. An object position estimation device, comprising:
an object candidate acquisition unit which estimates object positions by a visual cone intersection method and acquires candidate objects; an object candidate information storage unit which stores information on overlap among said candidate objects for a visual cone of objects which is acquired based on a captured image; a degree of co-movement acquisition unit which—acquires a degree of co-movement of said candidate objects which is calculated based on a number of visual cones including other candidate objects which co-move with the movement of said candidate objects, or a degree of confidence acquisition unit which acquires a degree of confidence of said candidate objects which is calculated based on the number of visual cones which an overlap condition determining means determined that there is an overlap of said candidate objects with other candidate objects; and a candidate object determination unit which identifies said candidate objects as either objects or non-objects by a posteriori probability which is calculated based on acquired said degree of co-movement or said degree of confidence and outputs position of said candidate objects which is determined as objects.