In the device according to the present invention, it is possible readily to distinguish between a road of travel and an obstacle in an image, simply using a distance image, even in cases where such a distinction is difficult to make, for instance, when a moving body is inclined during travel or the road forms a slope. Three-dimensional co-ordinate position data in a three-dimensional co-ordinate system is calculated for each pixel of the distance image, on the basis of two-dimensional co-ordinate position data for each pixel in the distance image and distance data from a reference position for each of the pixels, in such a manner that a three-dimensional distribution of pixels corresponding to a plane and an object to be detected is generated. Therefore, the object to be detected corresponding to groups of pixels having a prescribed height or more with respect to this plane can be distinguished readily from groups of pixels corresponding to the plane, on the basis of this three-dimensional distribution of pixels.
The image processing device includes: a distance image capture device which captures a distance image based upon three dimensional coordinate values obtained, by measuring the distances to various points upon body surfaces in the forward visual field of a distance sensor, for those points upon those body surfaces; a straight line extraction device which obtains three dimensional coordinate values of two points from a viewpoint picture element in the distance image and a picture element which is separated by a predetermined distance from that viewpoint picture element, and which extracts a plurality of straight lines in a horizontal plane using two dimensional coordinate values by ignoring the vertical component among these three dimensional coordinate values; and a plane detection device which obtains points on the body surfaces which lie upon various straight lines which have been extracted by the straight line extraction device, and detects points which lie upon the same straight line as being upon the same vertical plane.
An object recognition system having at least two image sensors and a controller that is adapted for measuring the distance from the system to a physical object with respect to respective windows of a n image captured by the sensors. The controller is further programmed to form clusters by uniting adjacent windows that have similar measure distances. The controller is programmed to judge whether each of the clusters is valid or invalid based on the attributes of the cluster and to recognize an object based on the clusters judged to be valid.
In an information extraction apparatus of the present invention, a distance image input section inputs a distance image including a plurality of objects to be respectively recognized. An area division section divides the distance image into a plurality of areas according to position information of a plurality of blocks to respectively execute an active event. An image processing section recognizes the plurality of objects in the areas corresponding to the blocks actually executed the active event, and supplies the recognition result to a system of the active event.
Provided is a technology for helping safe driving and realizing automatic driving of vehicles, or for counting the number of passing vehicles on the road or monitoring those passing vehicles for their driving. Using a plurality of cameras mounted in a vehicle or provided above a road, even if the relationship between the road plane and the respective cameras constantly changes in relative position or posture due to camera vibration or a change in road tilt, any obstacles located on the road such as other vehicles ahead, parked vehicles, and pedestrians on the road are detected without confusing those with textures including white lines, road signs, paint, road stains, and shadows of roadside objects, all of which do not disturb vehicle driving. An obstacle detection device 10 is structured by an image input section 11 for receiving images from a plurality of image pick-up devices 101, a correspondence detection section 12 for finding a plurality of pairs of corresponding points from the received right and left images, the slope degree calculation section 13 for calculating a slope degree of a plane including the corresponding points, and a result determination section 14 for determining as there being an obstacle when the calculated slope degree is larger than a predetermined value.
Provided is a technology for helping safe driving and realizing automatic driving of vehicles, or for counting the number of passing vehicles on the road or monitoring those passing vehicles for their driving. Using a plurality of cameras mounted in a vehicle or provided above a road, even if the relationship between the road plane and the respective cameras constantly changes in relative position or posture due to camera vibration or a change in road tilt, any obstacles located on the road such as other vehicles ahead, parked vehicles, and pedestrians on the road are detected without confusing those with textures including white lines, road signs, paint, road stains, and shadows of roadside objects, all of which do not disturb vehicle driving. An obstacle detection device 10 is structured by an image input section 11 for receiving images from a plurality of image pick-up devices 101, a correspondence detection section 12 for finding a plurality of pairs of corresponding points from the received right and left images, the slope degree calculation section 13 for calculating a slope degree of a plane including the corresponding points, and a result determination section 14 for determining as there being an obstacle when the calculated slope degree is larger than a predetermined value.
