Object detecting method and object detecting device

• US 10,269,127 B2
• Filed: 07/27/2015
• Issued: 04/23/2019
• Est. Priority Date: 07/27/2015
• Status: Active Grant

• Current Assignee: Nissan Motor Co., Ltd.
• Original Assignee: Nissan Motor Co., Ltd.
• Inventors: Fang, Fang, Ueda, Hirotoshi, Nanri, Takuya
• Primary Examiner(s): Sherali, Ishrat I
• Application Number:
  US15/747,272
• Publication Number:
  US 20180350083A1
• Time in Patent Office: 1,366 Days
• Field of Search: 382103, 382104, 382106
• CPC Class Codes: G01S 17/66 Tracking systems using electromagnetic waves other than radio waves
• CPC Class Codes: G01S 17/86 Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
• CPC Class Codes: G01S 17/931 of land vehicles
• CPC Class Codes: G01S 7/4808 Evaluating distance, position or velocity data
• CPC Class Codes: G06F 18/254 of classification results, e.g. of results related to same input data
• CPC Class Codes: G06T 7/292 Multi-camera tracking
• CPC Class Codes: G06T 7/74 involving reference images or patches
• 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

Abstract

Multiple objects detected by multiple sensors are subjected to a determination as to whether or not the objects are identical to each other. If there is an object in the multiple objects, of which object position becomes undetectable after the point when the multiple objects detected by the multiple sensors are determined to be the identical object, a determination is made as to whether or not the continuously detected object is an object identical to the object in a previous processing based on a predicted range calculated from a previously detected object position of the object becoming undetectable, and on a range of presence estimated from an object position of the continuously detected object.

Claims

1. An object detecting method for avoiding objects in a moving vehicle, comprising:

detecting a position of one or more objects using a plurality of sensors mounted on a moving vehicle, each sensor having a detecting region configured to detect a position of one or more moving objects in the detecting region, the detecting region of one sensor overlapping with detecting regions of other sensors;

when the plurality of sensors each detect an object, determining with a controller that the object detected by each of the plurality of sensors is the same object when a range surrounding the position of the object detected by one sensor overlaps a range surrounding the position of the object detected by the other sensors;

determining if the object was identified in a previous detection iteration by obtaining detection results of the previous detection iteration and calculating a predicted range of a subsequent detection iteration based on the position of the object;

when, in a current iteration, the object previously detected by a second sensor of the plurality of sensors becomes undetectable and a first sensor of the plurality of sensors detects an object in the current iteration, determining that the object detected by the first sensor is an object identical to the object detected in the previous detection iteration when a predicted range in the current iteration calculated from the previously detected position by the second sensor overlaps a range estimated from an object position in the current iteration of the object detected by the first sensor.

2. The object detecting method according to claim 1, wherein the controller is further configured to expand the predicted range based on a deviation between object positions of the plurality of objects obtained when the plurality of objects detected by the plurality of sensors are determined to be the same object.

3. The object detecting method according to claim 1, wherein the controller is further configured to:

set an identical identifier to the objects determined to be the same and set identifiers different from each other to objects determined to be not identical, and

when the objects, which are detected by the plurality of sensors, are not identical for a predetermined number of iterations or more starting from an iteration when the objects are determined to be the same, set an identifier to the object determined to be not identical.

4. The object detecting method according to claim 1, wherein the controller is further configured to calculate the predicted range based on a relative velocity at a time of the previous detection iteration of the object which position becomes undetectable in a subsequent iteration.

5. An object detecting device comprising:

a plurality of sensors mounted on a moving body, each sensor having a detecting region configured to detect a position of one or more moving objects in the detecting region, the detecting region of one sensor overlapping with detecting regions of other sensors; and

a controller configured to;

when the plurality of sensors each detect an object, determine that the object is the same object detected by each of the plurality of sensors when a range surrounding the position of the object detected by one sensor overlaps a range surrounding the position of the object detected by the other sensors;

determine if the object was identified in a previous detection iteration by obtaining detection results of the previous detection iteration and calculating a predicted range of a subsequent detection iteration based on the position of the object;

when, in a current iteration, the object previously detected by a second sensor of the plurality of sensors becomes undetectable and a first sensor of the plurality of sensors detects an object in the current iteration, determine that the object detected by the first sensor is an object identical to the object detected in the previous detection iteration when a predicted range in the current iteration calculated from the previously detected position by the second sensor overlaps a range estimated from an object position in the current iteration of the object detected by the first sensor.