Apparatus for identifying position of own vehicle and method for identifying position of own vehicle

• US 10,480,949 B2
• Filed: 06/01/2017
• Issued: 11/19/2019
• Est. Priority Date: 06/03/2016
• Status: Active Grant

• Current Assignee: DENSO Corporation
• Original Assignee: DENSO Corporation
• Inventors: Tateishi, Kojiro, Suzuki, Shunsuke, Mizuno, Hiroshi, Kawasaki, Naoki, Shikimachi, Takeshi
• Primary Examiner(s): Refai, Ramsey
• Application Number:
  US15/611,571
• Publication Number:
  US 20170350712A1
• Time in Patent Office: 901 Days
• CPC Class Codes: G01C 21/30 Map- or contour-matching
• CPC Class Codes: G01C 21/3602 Input other than that of destination using image analysis, e.g. detection of road signs, lanes, buildings, real preceding vehicles using a camera
• CPC Class Codes: G01S 13/89 for mapping or imaging
• CPC Class Codes: G01S 13/931 of land vehicles
• CPC Class Codes: G01S 17/89 for mapping or imaging
• CPC Class Codes: G01S 17/931 of land vehicles
• CPC Class Codes: G01S 19/485 whereby the further system is an optical system or imaging system
• CPC Class Codes: G01S 5/14 Determining absolute distances from a plurality of spaced points of known location
• CPC Class Codes: G01S 7/4808 Evaluating distance, position or velocity data
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06V 10/761 Proximity, similarity or dissimilarity measures
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
• CPC Class Codes: G06V 20/582 of traffic signs
• CPC Class Codes: G08G 1/00 Traffic control systems for road vehicles arrangement of road signs or traffic signals E01F9/00 ; automatic vehicle control B62D
• CPC Class Codes: G08G 1/09626 where the origin of the information is within the own vehicle, e.g. a local storage device, digital map
• CPC Class Codes: G08G 1/165 for passive traffic, e.g. including static obstacles, trees

Abstract

A position identifying apparatus includes a position detecting unit; an information acquiring unit; a feature extracting unit; an index value calculating unit; a feature selecting unit; a correlating unit; a weight setting unit; and a correcting unit. The position detecting unit performs a map matching to detect a vehicle position on a map. The information acquiring unit acquires road information from the map. The feature extracting unit extracts features of a ground object. The index value calculating unit calculates an index value representing a likelihood of a stationary object. The feature selecting unit selects feature candidates among the features having the index values larger than or equal to a predetermined likelihood of the stationary object. The correlating unit correlates the feature candidates with the road information. The weight setting unit sets weights of the feature candidates. The correcting unit corrects the position of the vehicle using the weights.

Claims

1. A position identifying apparatus comprising:

a position detecting unit that detects a position of an own vehicle on a map by using a map matching process;

an information acquiring unit that acquires, from the map, road information surrounding the own vehicle based on the position of the own vehicle detected by the position detecting unit;

a feature extracting unit that extracts features of ground object existing around the own vehicle, based on an output of a feature detecting unit mounted on the own vehicle;

an index value calculating unit that calculates an index value representing a likelihood of a stationary object for the features extracted by the feature extracting unit;

a feature selecting unit that selects feature candidates from among the features having an index value larger than or equal to a predetermined likelihood of the stationary object;

a correlating unit that correlates the feature candidates with the road information acquired by the information acquiring unit;

a weight setting unit that sets weights for feature candidates correlated with the road information, the weight being used for correcting the position of the own vehicle; and

wherein the index value calculating unit is configured to calculate a positional change of the feature, which changes with time, and configured to set a smaller index value to a feature having a large positional change relative to an index value calculated for a feature having a small positional change.

3. The position identifying apparatus according to claim 1, wherein

the apparatus includes a road sign determination unit that determines whether or not the feature is a road sign on a road surface;

the index value calculating unit is configured to set a larger index value to a feature determined as the road sign on the road surface, wherein the larger index value is larger than an index value for a feature not determined as the road sign.

4. The position identifying apparatus according to claim 1, wherein

the information acquiring unit is configured to acquire a position of the feature on the map as the road information;

and

the weight setting unit is configured to calculate a distance from a position of the feature candidate to the feature on the map, and configured to set a larger weight for a feature having a small distance from a position of the feature candidate to the feature on the map relative to a weight set for a feature having a large distance from a position of the feature candidate to the feature on the map.

5. The position identifying apparatus according to claim 1, wherein

the information acquiring unit is configured to acquire a shape of the feature around the vehicle;

and

the weight setting unit is configured to calculate a similarity between an approximate shape of the feature candidate and a shape of the feature acquired by the information acquiring unit, and configured to set a larger weight for a feature candidate in which the similarity is large relative to a weight set for a feature candidate in which the similarity is small.

6. The position identifying apparatus according to claim 1, wherein

the correcting unit is configured to divide the feature candidates based on distance from the own vehicle, and correct the position of the own vehicle;

the weight setting means is configured to calculate a likelihood representing a degree of certainty of the position of the own vehicle after the correction in each section, and configured to set a smaller weight to a section corresponding to a position of the own vehicle having a high likelihood relative to a weight set to a section corresponding to a position of the own vehicle having a low likelihood.

2. A position identifying apparatus comprising:

a position detecting unit that detects a position of an own vehicle on a map by using a map matching process;

an information acquiring unit that acquires, from the map, road information surrounding the own vehicle based on the position of the own vehicle detected by the position detecting unit;

a feature extracting unit that extracts features of a ground object existing around the own vehicle, based on an output of a feature detecting unit mounted on the own vehicle;

an index value calculating unit that calculates an index value representing a likelihood of a stationary object for the features extracted by the feature extracting unit;

a feature selecting unit that selects feature candidates from among the features having an index value larger than or equal to a predetermined likelihood of the stationary object;

a correlating unit that correlates the feature candidates with the road information acquired by the information acquiring unit;

a weight setting unit that sets weights for feature candidates correlated with the road information, the weight being used for correcting the position of the own vehicle; and

a correcting unit that corrects the position of the own vehicle using the weights;

wherein the apparatus includes a type determination unit that determines the feature extracted by the feature extracting unit; and

wherein the index value calculating unit is configured to set a smaller index value to a feature determined as either a vehicle or a pedestrian, wherein the smaller index value is smaller than an index value for a feature not determined as either a vehicle or a pedestrian.

7. A position identifying method comprising:

detecting a position of an own vehicle on a map by using a map matching process;

acquiring, from the map, a road information surrounding the own vehicle based on the position of the own vehicle detected;

extracting features of a ground object existing around the own vehicle, based on an output of a feature detecting unit mounted on the own vehicle;

calculating an index value representing a likelihood of a stationary object for the features extracted;

calculating a positional change of the feature, which changes with time;

setting a smaller index value to a feature having a large positional change relative to an index value calculated for a feature having a small positional change;

selecting feature candidates from among the features having an index value larger than or equal to a predetermined likelihood of the stationary object,

correlating the feature candidates with the road information acquired by the information acquiring unit;

setting weights for the feature candidates correlated with the road information, the weight being used for correcting the position of the own vehicle; and

correcting the position of the own vehicle using the weights.