摘要:
In a target-object distance measuring device and a vehicle on which the device is mounted, a human body detection device is utilized for calculating a distance between an image capturing device and a human body candidate in an actual space based on the size of the human body candidate in the image. The head width is approximately 15-16 cm. A body height in the actual space of the human candidate in the image is estimated based on the ratio between the head-width in the extracted image and at least one size of the human body feature, such as total height, in the extracted human body candidate region, and the distance from the image capturing device to the human body candidate in the actual space is calculated based on the estimated body height in the actual space and the body height of the human body candidate in the image.
摘要:
A vehicle periphery monitoring device includes: a parallax calculating unit which extracts a first image section that contains a target object in real space from a first image imaged by a first imaging unit at a predetermined time and extracts a second image section correlated to the first image section from a second image imaged by a second imaging unit at the predetermined time, and then calculates the parallax between the first image section and the second image section; a parallax gradient calculating unit for calculating a parallax gradient based on a time series calculation of the parallax of the identical target object in real space by the parallax calculating unit; and a first distance calculating unit for calculating the distance from the vehicle to the target object on the basis of the parallax gradient and the velocity of the vehicle.
摘要:
Category determination is performed on an object candidate extracted from a captured image after an exclusion process is performed in advance. In the exclusion process, a distance from a vehicle to the object candidate is calculated based on a size of the object candidate in a current image, a moved distance of the vehicle occurring in a time interval from a time a previous image was captured to a time the current image is captured is calculated, the size of the object candidate in the current image is decreased at a change ratio based on the distance to the object candidate and the moved distance, and a size of the object candidate in the previous image and a size of the object candidate decreased at the change ratio are compared. The object candidate with difference between them being determined to be larger than a predetermined value is removed.
摘要:
Category determination is performed on an object candidate extracted from a captured image after an exclusion process is performed in advance. In the exclusion process, a distance from a vehicle to the object candidate is calculated based on a size of the object candidate in a current image, a moved distance of the vehicle occurring in a time interval from a time a previous image was captured to a time the current image is captured is calculated, the size of the object candidate in the current image is decreased at a change ratio based on the distance to the object candidate and the moved distance, and a size of the object candidate in the previous image and a size of the object candidate decreased at the change ratio are compared. The object candidate with difference between them being determined to be larger than a predetermined value is removed.