Outside-vehicle monitoring system

• US 7,567,687 B2
• Filed: 02/14/2005
• Issued: 07/28/2009
• Est. Priority Date: 02/17/2004
• Status: Expired due to Fees

• Current Assignee: Subaru Corp.
• Original Assignee: Fuji Heavy Industries Limited (Subaru Corp.)
• Inventors: Kudo, Shinya
• Primary Examiner(s): Johns; Andrew W
• Assistant Examiner(s): Thomas; Mia M
• Application Number:
  US11/058,305
• Publication Number:
  US 20050231339A1
• Time in Patent Office: 1,625 Days
• Field of Search: 340/636.18, 340/435, 382/103, 382/104, 348/148
• US Class Current: 382/103
• CPC Class Codes: B60R 1/00 Optical viewing arrangements; Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles
• CPC Class Codes: B60R 21/0134 responsive to imminent contact with an obstacle , e.g. using radar systems
• CPC Class Codes: B60R 21/34 Protecting non-occupants of a vehicle, e.g. pedestrians B60R19/02 takes precedence
• CPC Class Codes: B60R 2300/106 using night vision cameras
• CPC Class Codes: B60R 2300/107 using stereoscopic cameras
• CPC Class Codes: B60R 2300/804 for lane monitoring
• CPC Class Codes: B60R 2300/8093 for obstacle warning
• CPC Class Codes: G01C 11/06 by comparison of two or more pictures of the same area
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G06T 7/97 Determining parameters from multiple pictures depth or shape recovery from multiple images G06T7/55; stereo camera calibration G06T7/85
• 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 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition
• CPC Class Codes: G08G 1/166 for active traffic, e.g. moving vehicles, pedestrians, bikes

Abstract

The present invention includes a stereo camera for picking up a couple of images of outside a vehicle and a far-infrared sensor for detecting the temperature of an object outside the vehicle at least in a detection field overlapping a view field of the stereo camera in the vehicle-width direction. A stereo-image processing unit recognizes three-dimensional objects based on the couple of images and extracts a prospective pedestrian from the recognized three-dimensional objects. A pedestrian-determination unit determines whether or not the prospective pedestrian is a real pedestrian based on a temperature-detection value detected in the same direction the prospective pedestrian exists, where the temperature-detection value is obtained through the far-infrared sensor.

Claims

1. An outside-vehicle monitoring system comprising:

a three dimensional visual light image-pickup device that generates a signal representative of an image of an object outside a vehicle by using solid state image pickup elements;

a three-dimensional-object recognition processor that recognizes a three-dimensional object outside the vehicle by processing the signal representative of the image generated by the three dimensional visual light image-pick up device and detects a prospective pedestrian by extracting three-dimensional object data from the recognized three-dimensional object and comparing the extracted three-dimensional object data with a predetermined width-range;

a plurality of thermal infrared elements that detect a temperature value of the recognized three dimensional object detected by the three dimensional visual light image-pickup device in a detection field overlapping a field of view of the three dimensional visual light image-pickup device, the plurality thermal infrared elements being arranged in a line along a width-direction of the vehicle; and

a pedestrian-determination processor coupled to said three-dimensional-object recognition processor and said plurality of thermal infrared elements that determines whether the prospective pedestrian is an actual pedestrian according to fluctuations in the value of the detected temperature in a detection-direction at which the prospective pedestrian was detected,

wherein the pedestrian-determination processor determines the prospective pedestrian is the actual pedestrian when the temperature-detection value detected by the plurality of thermal infrared elements in the detection direction is higher than a predetermined amount of the previous temperature-detection value detected by the plurality of thermal infrared elements in the detection-direction.

2. The outside-vehicle monitoring system according to claim 1, wherein the three dimensional visual light image-pickup device includes a pair of cameras for picking up the image of an object outside the vehicle from different points of view and the three-dimensional-object recognition processor three-dimensionally recognizes the three-dimensional object based on a couple of images of the same object picked up by the pair of cameras and extracts the prospective pedestrian.