WIPO logo
Mobile | Deutsch | English | Español | 日本語 | 한국어 | Português | Русский | 中文 | العربية |
PATENTSCOPE

Recherche dans les collections de brevets nationales et internationales
World Intellectual Property Organization
Recherche
 
Options de navigation
 
Traduction
 
Options
 
Quoi de neuf
 
Connexion
 
Aide
 
maximize
Traduction automatique
1. (WO2018050642) UN SYSTÈME ET PROCÉDÉ DE VISION POUR UN VÉHICULE À MOTEUR
Note: Texte fondé sur des processus automatiques de reconnaissance optique de caractères. Seule la version PDF a une valeur juridique

Claims :

1. A vision system for detecting free space in front of a motor vehicle, comprising a mono imaging apparatus (11) adapted to capture images (30) from the surrounding of a motor vehicle,, and an electronic processing device (14) adapted to perform image processing of images (30) captured by said mono imaging apparatus (11) in order to detect objects in the surrounding of a motor vehicle, characterized in that said electronic processing device (14) is adapted to calculate a horizontal component of the optical flow (31) , and to determine transitions (33, 35) between regions of essentially constant horizontal optical flow and regions of essentially non-constant horizontal optical flow.

2. The vision system as claimed in claim 1, characterized in that said electronic processing device (14) is adapted to determine said transitions (33, 35) in a vertical image direction .

3. The vision system as claimed in claim 1 or 2 , characterized in that said electronic processing device (14) is adapted to determine a transition point (33) for each image column.

4. The vision system as claimed in any one of the preceding claims, characterized in that said electronic processing device (14) is adapted to determine one or more border lines (35) fitting to the determined transitions.

5. The vision system as claimed in any one of the preceding claims, characterized in that said electronic processing device (14) is adapted to calculate a discrimination image (32) from a horizontal optical flow image (31), where the value of each pixel of the discrimination image (32) provides a measure on whether the pixel belongs to a re-gion of essentially constant horizontal optical flow or to a region of essentially non-constant horizontal optical flow, and to determine said transitions (33, 35) from said discrimination image (32).

The vision system as claimed in claim 5, wherein said dis crimination image (32) is calculated by, in the horizontal optical flow image (31) , considering a number x of pixels above the pixel under consideration, a number y of pixels below the pixel under consideration, where y can be equal to or different from y, calculating a statistical deviation, like the standard deviation, of the horizontal optical flow values of the group of pixels comprising the x pixels above, the y pixels below and the pixel under consideration, and estimating the pixel under consideration to belong to a region of essential constant horizontal optical flow if the calculated standard deviation is below a pre-determined or calculated threshold.

The vision system as claimed in any one of the preceding claims, characterized in that said electronic processing device (14) is adapted to disregard in said transitions determination a central image region (34, 36).

The vision system as claimed in any one of the preceding claims, characterized in that said electronic processing device (14) is adapted to restrict said transitions determination to a lower image part.

The vision system as claimed in any one of the preceding claims, characterized in that said electronic processing device (14) is adapted to determine the world distance from the vehicle to a structure formed by said transitions (33, 35) .

The vision system as claimed in claim 9, characterized in that a flat road assumption is used in said distance determination .

The vision system as claimed in claim 9 or 10, characterized in that road profile information, for example from a satellite navigation system, is used in said distance determination .

A vision method for detecting free space in front of a mo tor vehicle, comprising capturing images (30) from the surrounding of a motor vehicle using a mono imaging apparatus ( 11 ) , and per orming image processing of captured images (30) in order to detect free space in front of the motor vehicle, characterized by calculating a horizontal component of the optical flow (31), and determining transitions (33, 35) between regions of essentially constant horizontal optical flow and regions of essentially non-constant horizontal opt icai flow.