Conti Temic Microelectronic Gmbh

Adc Automotive Distance Control Systems Gmbh

Adc Automotive Distance Controls Systems Gmbh

Michael Walter

Wladimir Klein

Matthias Zobel

Thomas Fechner

Dominik Maeder

Johannes Hoer

A method and a device are for identifying objects from camera images, e.g. for vehicle driver assistance systems. The method involves: capturing a series of camera images, determining a plurality of planes in space by associating adjacent corresponding features in at least two consecutive camera images with a given one of the planes, determining a relative translation vector of a plane, and identifying dynamic objects in the camera images based on the relative translation vector of an associated plane.

Detection and validation of objects from sequential images of a camera by using homographies

A method and a device are for detecting and validating objects from camera images, e.g. for driver assistance systems. The method involves: capturing a series of camera images, detecting a potential collision object in at least one image, determining corresponding features in two consecutive images in the image region of the detected potential collision object, associating the corresponding features with a plane, and validating the potential collision object when the associated plane corresponds to a back plane or a side plane.

Detection and validation of objects from sequential images of a camera

A method and a device are for identifying objects from camera images, e.g. for driver assistance systems. The method involves: capturing a series of camera images, determining corresponding features in two consecutive images, associating adjacent ones of the corresponding features with a plane in space to determine a plurality of such planes, and detecting objects while taking the determined planes into account.

A lane detection method wherein a digitized image of a lane is evaluated, including the following steps: detecting edges in the image, determining the angles of the detected edges with respect to a reference edge, removing the edges from the plurality of detected edges, the angle of which lies within a predetermined angle sector, and detecting the lane based on the remaining edges of the plurality of detected edges.

Method and device for lane detection

The invention relates to a method for estimating the roll angle in a travelling vehicle (), comprising the following steps. In step a), a camera () is used to record a sequence of images of the vehicle's surroundings, in particular of the road () ahead. In step b), at least one signature (S-S) on the road surface is extracted from the camera images, i.e. said signature is determined and tracked. The changed position of the at least one signature (S-S) in one or more subsequent camera image(s) is used in step c) to determine in which direction the camera () is turned with regard to the roll angle. The value of the roll angle is estimated in step d). For this purpose, the roll angle is either directly estimated in step d), taking into account the vehicle speed (v) and an imaging model of the camera (), or the roll angle is iteratively increased or decreased by a defined correction angle in step d) until the roll angle sufficiently compensates for the turning of the camera (). On this basis, the estimated roll angle is obtained as an overall correction value.

Method for estimating the roll angle in a travelling vehicle

A method for lane detection, wherein a digitized color image of a roadway is processed using the following steps:

A method and a device for distinguishing between reflectors arranged on the roadside and vehicle lights and for identifying said reflectors and vehicle lights for use in an automatic light control system in a vehicle with a camera sensor oriented towards the surroundings of the vehicle. The method includes recording a sequence of images of the surroundings of the vehicle. Light spots are found and subjected to temporal tracking within the sequence of images. Afterwards, for each light spot, a decision is made whether the light source of the light spot is a vehicle light or a reflector. A statistical map for the entire camera image is determined from the position of the light spots found with the statistical map comprising regions that are predominantly occupied by reflectors and regions that are predominantly occupied by vehicles driving ahead or by oncoming vehicles. All light sources that are found within the regions occupied by reflectors are identified as potential reflectors and all light sources within the regions occupied by vehicle lights are identified as potential vehicle lights.

Method for distinguishing between reflectors arranged on the roadside and vehicle lights in the dark

A method for detecting the course of a traffic lane, including the following steps: measuring structures of the traffic lane; evaluating the homogeneity of the measurements; and determining the course of the traffic lane on the basis of the evaluated homogeneity.

Method and device for detecting the course of a traffic lane

A detector for identifying a road lane boundary using a digitalized optical image of the region in front of the vehicle. The detector includes a correlator configured to select the edges which are to be used for road lane estimation by searching for extreme values of convolution response, and to weight each convolution response by a weighting factor. A histogram analysis unit configured to group the extracted edges into pairs, and to determine a frequency distribution of the distances between two paired edges as a histogram, and to use said frequency distribution to determine the distances between two grouped edges forming a frequency peak or a frequency plateau in the histogram as nominal edge widths. A weighting factor determination unit configured to determine, for an edge, the weighting factor of the convolution response in the correlator in such a manner that the weight determined by the weighting factor for an edge of the paired edges is higher the smaller the deviation of the distance between the grouped edges from the nominal edge width.

Detector and method for identifying a road lane boundary

A camera for identifying soiling on a protective screen, such as a vehicle windscreen, is focused on a scene through the protective screen and can be used to identify soiling and for other applications, e.g. to identify driving lanes and/or objects in the scene. Soiling is identified merely by evaluating successively recorded image frames, and artificial reference frames or reference objects are not required. A prerequisite is that the relative speed vbetween the camera and at least one recorded object in the scene is not equal to zero and its trajectory in the image is predicted. By comparing the relevant image frame sections, possible soiling on subregions of the protective screen is identified.

Method for identifying soiling on a transparent screen

In a method for the calibration of a yaw rate measurement in a motor vehicle, the motor vehicle features at least one device for determining the yaw rate, a camera system which is oriented in the forward direction, and, if applicable, a steering angle sensor or a lateral acceleration sensor. At least one initial calibration is carried out at a standstill and at least one second calibration is carried out when the motor vehicle is moving. The second calibration uses image data of the camera system, which detects the environment in front of the motor vehicle, to predict the course of the roadway lane on which the vehicle is driving, from which the yaw rate is estimated.

Growing community of inventors

Neuravensburg, Germany

Michael Walter