OBJECT DETECTION DEVICE AND OBJECT DETECTION METHOD

• US 20130335259A1
• Filed: 03/02/2012
• Published: 12/19/2013
• Est. Priority Date: 03/10/2011
• Status: Active Grant

• Current Assignee: Panasonic Intellectual Property Management Co., Ltd. (Panasonic Holdings Corporation)
• Original Assignee: Panasonic Corporation (Panasonic Holdings Corporation)
• Inventors: Yasugi, Makoto, Nishimura, Hirofumi
• Granted Patent: US 9,041,588 B2
• Time in Patent Office: Days
• US Class Current: 342/52
• CPC Class Codes: G01S 13/04 Systems determining presence of a target based on relative movement of target G01S13/56
• CPC Class Codes: G01S 13/52 Discriminating between fixed and moving objects or between objects moving at different speeds
• CPC Class Codes: G01S 13/56 for presence detection presence detection using near field arrangements G01V3/00, e.g. G01V3/08, G01V3/12; burglar, theft or intruder alarms with electrical actuation G08B13/22 - G08B13/26
• CPC Class Codes: G01S 13/86 Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
• CPC Class Codes: G01S 13/867 Combination of radar systems with cameras
• CPC Class Codes: G01S 7/292 Extracting wanted echo-signals
• CPC Class Codes: G01S 7/295 Means for transforming co-ordinates or for evaluating data, e.g. using computers
• CPC Class Codes: G01S 7/41 using analysis of echo signal for target characterisation; Target signature; Target cross-section
• CPC Class Codes: G01S 7/414 Discriminating targets with respect to background clutter
• CPC Class Codes: G01V 8/10 Detecting, e.g. by using light barriers by reflection from the object G01S17/00
• CPC Class Codes: G06F 18/256 of results relating to different input data, e.g. multimodal recognition
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
• CPC Class Codes: G06V 10/811 the classifiers operating on different input data, e.g. multi-modal recognition
• CPC Class Codes: G06V 20/54 of traffic, e.g. cars on the road, trains or boats
• CPC Class Codes: G06V 20/653 by matching three-dimensional models, e.g. conformal mapping of Riemann surfaces
• CPC Class Codes: G08G 1/04 using optical or ultrasonic detectors
• CPC Class Codes: G08G 1/052 with provision for determining speed or overspeed speed measuring in general G01P

Abstract

Disclosed is an object detection device capable of improving object detection accuracy by preventing erroneous combination detection. In this device, a detection object region correction unit (103) corrects a detection object region set by a detection object region set unit (102) on the basis of moving speed map information associated with a coordinate group in a reference image plane and the detected moving speed on each coordinate, which is detected by a radar. Thus, the detection object region can be amended by the use of the moving speed map information even when the detection object region is obtained as a result of erroneous combination. As a result, the object detection accuracy can be improved.

Claims

1-9. -9. (canceled)

10. An object detection apparatus comprising:

a candidate point extraction section that extracts candidate points from camera distance map information in which coordinates in an image plane are mapped to information regarding object presence obtained based on a stereo image, or from combined map information combining the camera distance map information and radar distance map information in which the coordinates in the image plane are mapped to information regarding object presence obtained based on information detected by a radar, the candidate points being coordinates at which corresponding information regarding object presence is equal to or greater than a predetermined value;

a setting section that arranges the extracted candidate points into groups based on values of the corresponding information regarding object presence, and that sets up, as a first detected object region, a region in the image plane including all candidate points of each group; and

a correction section which;

divides, with respect to travel speed map information in which the coordinates in the image plane are mapped to detected travel speeds detected by the radar, a first corresponding region, which corresponds to the first detected object region, into a plurality of partial regions in the direction of a first coordinate axis of coordinate axes of the image plane;

computes a first correlation value with respect to the detected travel speeds between a representative partial region among the plurality of partial regions and a partial region other than the representative partial region; and

divides the first detected object region into a plurality of second detected object regions based on the first correlation value.

11. The object detection apparatus according to claim 10, further comprising a region length correction section which:

divides each of a plurality of second corresponding regions in the travel speed map information, which correspond to the plurality of second detected object regions, into a plurality of partial regions in the direction of a second coordinate axis of the coordinate axes of the image plane;

computes, with respect to each of the plurality of second corresponding regions, a second correlation value with respect to the detected travel speeds between a representative partial region among the plurality of partial regions and a partial region other than the representative partial region; and

generates a third detected object region by correcting the plurality of second corresponding regions based on the second correlation value.

12. The object detection apparatus according to claim 10, further comprising an erroneous separation correction section which:

takes at least two among the plurality of second detected object regions and the third detected object region to be a set of processing target regions;

computes, with respect to each of the processing target regions, an average value of a given coordinate along one of the coordinate axes of the image plane by averaging a plurality of detected speed values mapped to a plurality of coordinates that share the given coordinate while having differing coordinates along the other coordinate axis;

computes an average speed distribution including average values for all coordinates along the one coordinate axis with respect to each of the processing target regions;

computes a correlation value of average speed distributions between each pair of processing target regions in the set of processing target regions; and

sets up as a fourth detected object region a region including each of the pairs of processing target regions based on the computed correlation values among the average speed distributions.

13. The object detection apparatus according to claim 10, further comprising a smoothing process section that smoothes the travel speed map information used at the correction section using a smoothing filter.

14. The object detection apparatus according to claim 10, wherein a coordinate system defining the image plane comprises a coordinate system defined by parallax and one coordinate axis in an image plane coordinate system wherein a virtual installation position of the object detection apparatus is taken to be on a road surface.

15. The object detection apparatus according to claim 13, wherein the smoothing filter has a property where each coordinate along one of two coordinate axes defining the image plane is shifted by an amount corresponding to the height at which the object detection apparatus is installed.

16. The object detection apparatus according to claim 10, further comprising a speed map information correction section that corrects the travel speed map information based on second camera distance map information in which coordinates in an image plane coordinate system, where a virtual installation position of the object detection apparatus is taken to be on a road surface, is mapped to the information regarding object presence obtained based on the stereo image.

17. An object detection method wherein:

a candidate point extraction section extracts candidate points from camera distance map information in which coordinates in an image plane are mapped to information regarding object presence obtained based on a stereo image, or from combined map information combining the camera distance map information and radar distance map information in which the coordinates in the image plane are mapped to information regarding object presence obtained based on information detected by a radar, the candidate points being coordinates at which corresponding information regarding object presence is equal to or greater than a predetermined value;

a setting section arranges the extracted candidate points into groups based on values of the corresponding information regarding object presence, and sets up, as a first detected object region, a region in the image plane including all candidate points of each group; and

a correction section;

divides, with respect to travel speed map information in which the coordinates in the image plane are mapped to detected travel speeds detected by the radar, a first corresponding region, which corresponds to the first detected object region, into a plurality of partial regions in the direction of a first coordinate axis of coordinate axes of the image plane;

computes a first correlation value with respect to the detected travel speeds between a representative partial region among the plurality of partial regions and a partial region other than the representative partial region; and

divides the first detected object region into a plurality of second detected object regions based on the first correlation value.