Abstract: The invention relates to a method for multi-sensorial object detection, wherein sensor information is evaluated together from several different sensor signal flows having different sensor signal properties. For said evaluation, the at least two sensor signal flows are not adapted to each other and/or projected onto each other, but object hypotheses are generated in each of the at least two sensor signal flows and characteristics for at least one classifier are generated based of said object hypotheses. Said object hypotheses are subsequently evaluated by means of a classifier and are associated with one or more categories. At least two categories are identified and the object is associated with one of the two categories.

Abstract: Assistance systems are increasingly being used to assist vehicle drivers when driving their vehicles. To this end, a camera is used to record image data from the area surrounding a vehicle, and at least some of the image data (1) are shown on a display following object identification and image processing. After the image data have been recorded by the camera, they are processed using object identification in order to identify objects (2, 3) in the recorded image data. At least some of the objects (2, 3) which have been identified in this manner are highlighted when showing the image data (1) on the display. In this case, the identified objects (2, 3) are highlighted in such a manner that the image data (1) to be shown are divided into two types of regions. In this case, the first type of region comprises the objects (2, 3) which have been identified and are to be highlighted and a surrounding region (2a, 3a) which respectively directly adjoins the latter in a corresponding manner.

Abstract: A novel method and a suitable device for the cylinder-specific determination of spark failures on a reciprocating engine through a classifying unit based on measurement data that contain information about the number of crankshaft revolutions. For this process, the measurement data are subjected to a pre-processing procedure in the classifying unit and classified through a classification process, wherein within the framework of the pre-processing procedure the data are subjected to a principal axis transformation (HAT). Due to the utilization of this resource-saving method for detecting spark failures on reciprocating engines in accordance with the invention, the processing requirements for once cycle are less than 5 Kflops, despite a measurement vector v length of 240. Due to the fact that the invented device requires only a single measurement data recorder, e.g.

Abstract: A novel method and a suitable device for the cylinder-specific determination of spark failures on a reciprocating engine through a classifying unit based on measurement data that contain information about the number of crankshaft revolutions. For this process, the measurement data are subjected to a pre-processing procedure in the classifying unit and classified through a classification process, wherein within the framework of the pre-processing procedure the data are subjected to a principal axis transformation (HAT). Due to the utilization of this resource-saving method for detecting spark failures on reciprocating engines in accordance with the invention, the processing requirements for once cycle are less than 5 Kflops, despite a measurement vector v length of 240. Due to the fact that the invented device requires only a single measurement data recorder, e.g.