Object detector

• US 20070165967A1
• Filed: 01/10/2007
• Published: 07/19/2007
• Est. Priority Date: 01/16/2006
• Status: Abandoned Application

• Current Assignee: Omron Corporation
• Original Assignee: Omron Corporation
• Inventors: Ando, Tanichi, Fujioka, Ryoji
• Application Number:
  US11/652,177
• Publication Number:
  US 20070165967A1
• Time in Patent Office: Days
• US Class Current: 382/291
• CPC Class Codes: G01S 17/42 Simultaneous measurement of distance and other co-ordinates indirect measurement G01S17/46
• 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: 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 40/16 Human faces, e.g. facial parts, sketches or expressions
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation

Abstract

An object detector detects an object with a camera and calculates position data showing its direction and distance. A laser radar obtains an front image and recognizes an identified image in the front image. Coordinates of this identified image are calculated and converted to data indicating direction to the object. The identified image is correlated with the object detected by the laser radar and the correlated object is identified as an identified object. Position data of this correlated object are outputted as data on the identified object.

Claims

1. An object detector comprising:

an object sensor for detecting an object in front of an automobile;

position data calculating means for calculating position data that show direction and distance of an object detected by said object sensor;

an image sensor for obtaining a front image in front of said automobile and recognizing an identified image in said front image;

coordinate calculating means for calculating coordinates of said identified image recognized by said image sensor in said front image;

a correspondence processing part that converts the coordinates of said identified image calculated by said coordinate calculating means to thereby obtain data indicating direction to said object and to correlate said identified image with the object detected by said object sensor and identifies said correlated object as an identified object; and

data outputting means for outputting position data of said correlated object as data of the identified object.

2. The object detector of claim 1 wherein said correspondence processing part identifies those of objects detected continuously by said object sensor matching in direction and distance of displacement within a specified time as belonging to a same group and correlates a plurality of objects belonging to a same group as the object correlated to said identified object as a single object to said identified image.

3. The object detector of claim 2 further comprising object sensor control means for reducing the threshold value of said object sensor, when said object sensor has detected an object, to cause said object sensor to scan again a surrounding area of said detected object.

4. The object detector of claim 1 wherein said correspondence processing part judges, if a first object was detected at the time of the previous scan in an area which is the same as or next to the area in which a second object is detected at the time of a current scan, that said first object and said second object are the same object.

5. The object detector of claim 2 wherein said correspondence processing part judges, if a first object was detected at the time of the previous scan in an area which is the same as or next to the area in which a second object is detected at the time of a current scan, that said first object and said second object are the same object.

6. The object detector of claim 3 wherein said correspondence processing part judges, if a first object was detected at the time of the previous scan in an area which is the same as or next to the area in which a second object is detected at the time of a current scan, that said first object and said second object are the same object.

7. The object detector of claim 4 wherein said correspondence processing part continues to judge said second object to be said identified object if said first object was judged to correlate to said identified object and said first object and said second object were judged to be the same object, although said second object may not be correlated to said identified object.

8. The object detector of claim 5 wherein said correspondence processing part continues to judge said second object to be said identified object if said first object was judged to correlate to said identified object and said first object and said second object were judged to be the same object, although said second object may not be correlated to said identified object.

9. The object detector of claim 6 wherein said correspondence processing part continues to judge said second object to be said identified object if said first object was judged to correlate to said identified object and said first object and said second object were judged to be the same object, although said second object may not be correlated to said identified object.

10. The object detector of claim 1 wherein said correspondence processing part judges, if a group of objects which are of a plurality of objects detected by said object sensor and are detected in mutually adjacent areas is correlated to said identified image, that said group of objects correlates to said identified object.

11. The object detector of claim 2 wherein said correspondence processing part judges, if a group of objects which are of a plurality of objects detected by said object sensor and are detected in mutually adjacent areas is correlated to said identified image, that said group of objects correlates to said identified object.

12. The object detector of claim 3 wherein said correspondence processing part judges, if a group of objects which are of a plurality of objects detected by said object sensor and are detected in mutually adjacent areas is correlated to said identified image, that said group of objects correlates to said identified object.

13. The object detector of claim 4 wherein said correspondence processing part judges, if a group of objects which are of a plurality of objects detected by said object sensor and are detected in mutually adjacent areas is correlated to said identified image, that said group of objects correlates to said identified object.

14. The object detector of claim 5 wherein said correspondence processing part judges, if a group of objects which are of a plurality of objects detected by said object sensor and are detected in mutually adjacent areas is correlated to said identified image, that said group of objects correlates to said identified object.

15. The object detector of claim 6 wherein said correspondence processing part judges, if a group of objects which are of a plurality of objects detected by said object sensor and are detected in mutually adjacent areas is correlated to said identified image, that said group of objects correlates to said identified object.

16. The object detector of claim 7 wherein said correspondence processing part judges, if a group of objects which are of a plurality of objects detected by said object sensor and are detected in mutually adjacent areas is correlated to said identified image, that said group of objects correlates to said identified object.

17. The object detector of claim 8 wherein said correspondence processing part judges, if a group of objects which are of a plurality of objects detected by said object sensor and are detected in mutually adjacent areas is correlated to said identified image, that said group of objects correlates to said identified object.

18. The object detector of claim 9 wherein said correspondence processing part judges, if a group of objects which are of a plurality of objects detected by said object sensor and are detected in mutually adjacent areas is correlated to said identified image, that said group of objects correlates to said identified object.