Abstract: Computer-implemented method for providing training data for a machine learning algorithm for image classifying a pathogen infestation of a plant, comprising the steps: providing image data of a plant or a plant part infested with a pathogen; providing genetic result data of the plant or the plant part to which the image data referred comprising at least information about the type of pathogen; labeling the image data with the genetic result data.

Abstract: Methods and systems are provided for improving speech recognition of multilingual named entities. In some embodiments, a list comprising a plurality of named entities may be accessed by a computing device. A first named entity represented in the native language may be compared with the first named entity represented in the foreign language. One or more words that appear in both the first named entity represented in the native language and the first named entity represented in the foreign language may be identified as one or more foreign words. A grapheme-to-phoneme (G2P) conversion may be applied to the one or more foreign words, wherein graphemes of the one or more foreign words are mapped to phonemes in the native language. The G2P conversion may result in a native pronunciation for each of the one or more foreign words, which are added to a recognition dictionary along with the native pronunciations.

Abstract: Method and apparatus for providing visual feedback on an electronic device in a client/server speech recognition system comprising the electronic device and a network device remotely located from the electronic device. The method comprises processing, by an embedded speech recognizer of the electronic device, at least a portion of input audio comprising speech to produce local recognized speech, sending at least a portion of the input audio to the network device for remote speech recognition, and displaying, on a user interface of the electronic device, visual feedback based on at least a portion of the local recognized speech prior to receiving streaming recognition results from the network device.

Abstract: Methods and systems are provided for improving speech recognition of multilingual named entities. In some embodiments, a list comprising a plurality of named entities may be accessed by a computing device. A first named entity represented in the native language may be compared with the first named entity represented in the foreign language. One or more words that appear in both the first named entity represented in the native language and the first named entity represented in the foreign language may be identified as one or more foreign words. A grapheme-to-phoneme (G2P) conversion may be applied to the one or more foreign words, wherein graphemes of the one or more foreign words are mapped to phonemes in the native language. The G2P conversion may result in a native pronunciation for each of the one or more foreign words, which are added to a recognition dictionary along with the native pronunciations.

Abstract: When maneuvering a vehicle, due to the seated position of the driver, the problem arises that a large portion of the space to the rear of the vehicle to be observed is hidden by the vehicle body itself. Therefore, the vehicle driver is presented with a display of a camera image of the space to the rear of the vehicle with a perspective overlay of the driving path and/or the towing path of the vehicle (1). Said driver support system is configured such that it is also suitable for guiding a vehicle or vehicle combination (1) in which the trailer comprises a plurality of vehicle elements (2, 3) that are bendable relative to one another. In order to detect the steering angle (7) of at least one steerable axis (6) of the vehicle (1), and in order to determine the bending angle (5) between at least two vehicle elements (2, 3) bendable relative to one another, sensors are provided.

Abstract: The invention relates to an anisotropic stray light or sun screen for a camera in a motor vehicle, wherein this sun screen shields the camera lens from stray light coming from the vehicle interior or is reflected by a window of the vehicle. The sun screen is thereby however designed in such a manner that a vehicle occupant can see the surroundings of the vehicle through the shield.

Abstract: The invention relates to a method and a device for assisting a driver when maneuvering a vehicle or vehicle-trailer combination (1) which has vehicle elements (2, 3) which can move with respect to one another. The method provides that the vehicle or vehicle-trailer combination is/are displayed in the straight-ahead position on a display unit (A) using a static display element (4) which corresponds to the straight-ahead position of the vehicle elements (2, 3) and in addition respectively using a dynamic display element (6, 7) which is assigned to the respective vehicle element (2, 3) and is determined as a function of an instantaneous or future position of the vehicle elements (2, 3) which can move with respect to one another. In this context, the dynamic display elements (6, 7) are displayed enhanced multiply and highlighted in terms of color.

Abstract: When maneuvering a vehicle, due to the seated position of the driver, the problem arises that a large portion of the space to the rear of the vehicle to be observed is hidden by the vehicle body itself. Therefore, the vehicle driver is presented with a display of a camera image of the space to the rear of the vehicle with a perspective overlay of the driving path and/or the towing path of the vehicle (1). Said driver support system is configured such that it is also suitable for guiding a vehicle or vehicle combination (1) in which the trailer comprises a plurality of vehicle elements (2, 3) that are bendable relative to one another. In order to detect the steering angle (7) of at least one steerable axis (6) of the vehicle (1), and in order to determine the bending angle (5) between at least two vehicle elements (2, 3) bendable relative to one another, sensors are provided.

Abstract: The invention relates to a method and a device for assisting a driver when maneuvering a vehicle or vehicle-trailer combination (1) which has vehicle elements (2, 3) which can move with respect to one another. The method provides that the vehicle or vehicle-trailer combination is/are displayed in the straight-ahead position on a display unit (A) using a static display element (4) which corresponds to the straight-ahead position of the vehicle elements (2, 3) and in addition respectively using a dynamic display element (6, 7) which is assigned to the respective vehicle element (2, 3) and is determined as a function of an instantaneous or future position of the vehicle elements (2, 3) which can move with respect to one another. In this context, the dynamic display elements (6, 7) are displayed enhanced multiply and highlighted in terms of color.

Abstract: The invention relates to a system for automatically monitoring a motor vehicle, especially for automatically monitoring a vehicle (E) in a traffic jam. Said system comprises at least one sensor (2) for monitoring the space in front of the vehicle (E), and an electronic regulating device for regulating travel, braking and steering. According to the invention, said sensor is designed in such a way that it detects the movement of a vehicle (A) changing lanes in front of vehicle (E). The control of the vehicle is returned to the driver, or the driver is requested to regain control of the vehicle, when motor vehicle (E) shows a desire to follow the lane change of vehicle (A), and when it is determined, by means of the signals of the lateral sensor (8, 10), that during the monitoring, vehicle (E) is not at a sufficiently safe distance from a vehicle (B) detected by the lateral sensor. One such system for automatically monitoring a motor vehicle thus increases road safety in a simple manner.

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 method for characterizing a pattern present as stored information, includes the steps of generating a characterizing proposal for the pattern using a server computer system, presenting the pattern and the characterizing proposal to a client computer using a computer program via the Internet so as to enable a user to perform an evaluation of the characterizing proposal, and receiving an evaluation input from the user at the server computer system. The evaluation input is one of an acceptance input of the characterizing proposal and a rejection input of the characterizing proposal. The rejection input includes an alternative characterizing proposal.

Abstract: Poor visibility at night is a tiring and dangerous situation in traffic, feared by many drivers. As a result of poor visibility, the frequency of accidents at night is significantly higher than during the day with good visibility conditions. Cars are thus prospectively fitted with night vision systems, in order to increase safety in traffic. A night vision system used for this purpose generally comprises an illumination unit for illuminating the environment surrounding the vehicle, an image recording unit for collecting environmental data, and an image processing unit for evaluating the environmental data. So that the operation of the night vision system can be adapted to different situations, it must be designed in a flexible manner. To this end, the individual components of the night vision system must be able to be operated in different combinations. In order to achieve this, the components of the night vision system can be individually controlled by means of at least one control signal.

Abstract: An image processing system for a motor vehicle, includes a camera system, an image processing module having a data interface for receiving image data produced by the camera system, a memory unit for storing an image processing program, an image processor unit for processing the image data, a display unit for displaying the processed image data, and a miniature computer. At least one of the image processor unit and the display unit are disposed in the miniature computer.

Abstract: Driver assist systems for monitoring blind zones are known from the state-of-the-art. The requirements placed upon the reliability of this type of driver assist system is very high, and as a result these systems known from the state-of-the-art frequently trigger false warnings. For this reason, a process for blind zone monitoring in motor vehicles is proposed, wherein information is detected from the vehicle environment in order to recognize other traffic participants. Under the condition of an intent to carry out a lane change and the presence of other traffic participants in the blind zone of the own vehicle, a driver warning is emitted. Before a driving warning can however occur a check is carried out with respect to whether a lane change can even be carried out on the basis of the traffic infrastructure. Driving warnings are suppressed in the case that as a result of the check a lane change is not possible or permissible.

Abstract: In complex vehicle maneuvers it is often difficult for the driver of the motor vehicle to estimate along which tract the vehicle will move and how much free space is necessary in order to avoid collision. A process is provided for monitoring the environment space in the direction of travel of the own vehicle, in which image data of the environment around the vehicle in the direction of travel of the vehicle is recorded using a camera system the three-dimensional free space required for unimpeded travel is calculated in advance in a signal processing unit and the vehicle operator is informed regarding whether or not a sufficient free space is available to him for unimpeded travel.

Abstract: The invention relates to a night vision system for vehicles. According to the invention, the road in front of the vehicle is stereoscopically recorded via two night vision-capable cameras, e.g. infrared or low-light-level cameras that are mounted in the front of the vehicle at a distance from one another. Corresponding stereoscopic image display devices permit the driver to observe the road in front of the vehicle in three-dimensions. Objects located in front of the vehicle can be detected in critical areas by means of additional image evaluating devices and can be differently accentuated or marked in the image representation. The night vision system can be designed to also permit a two-dimensional display of images or data alternatively or in conjunction with 3D representation. In an enhanced embodiment, head movements and/or the line of sight of the driver are/is detected and used for a corresponding tracking of the image display.

Abstract: The invention relates to a method for displaying a perspective image and to a display device for at least one passenger of a motor vehicle. The air of the vehicle is to guarantee by simple means a high road safety that is substantially independent of the knowledge and skills of the driver. To this end, a method for displaying a perspective image (B) with one image element (4A to 4H) for at least one passenger of a motor vehicle is provided, said image (B) representing the view of the passenger. According to the inventive method, the image element (4A to 4H) is changed in at least one size depending on the forward travel way (F), on at least one operational parameter of the motor vehicle and/or on at least one parameter of an object (6) identified in the range of the travel way (F).

Abstract: The invention concerns a system for assisting an operator of a technical appliance, with a image display device (2), of which the image is in the normal field of vision of the operator, for display of operationally relevant information in the form of images or symbols (1). According to the invention, a respective image or symbol is displayed at least once for a brief period of time, of which the duration is below the threshold of conscious recognition and above the threshold of subconscious recognition of the operator.

Abstract: The invention relates to a system for automatically monitoring a motor vehicle, especially for automatically monitoring a vehicle (E) in a traffic jam. Said system comprises at least one sensor (2) for monitoring the space in front of the vehicle (E), and an electronic regulating device for regulating travel, braking and steering. According to the invention, said sensor is designed in such a way that it detects the movement of a vehicle (A) changing lanes in front of vehicle (E). The control of the vehicle is returned to the driver, or the driver is requested to regain control of the vehicle, when motor vehicle (E) shows a desire to follow the lane change of vehicle (A), and when it is determined, by means of the signals of the lateral sensor (8, 10), that during the monitoring, vehicle (E) is not at a sufficiently safe distance from a vehicle (B) detected by the lateral sensor. One such system for automatically monitoring a motor vehicle thus increases road safety in a simple manner.