Abstract: The present invention describes a road terrain detection system that comprises a method for classifying selected locations in the environment of a vehicle based on sensory input signals such as pixel values of a camera image. The method comprises a high level spatial feature generation for selected locations in the environment called base points. The spatial feature generation of the base points is based on a value-continuous confidence representation that captures visual and physical properties of the environment, generated by so called base classifiers operating on raw sensory data. Consequently, the road terrain detection incorporates both local properties of sensor data and their spatial relationship in a two-step feature extraction process.

Abstract: A method for computationally predicting future movement behaviors of at least one target object can have the steps of producing sensor data by at least one sensor physically sensing the environment of a host vehicle, and computing a plurality of movement behavior alternatives of a target object sensed by the sensor(s). The context based prediction step uses a set of classifiers, each classifier estimating a probability that said sensed target object will execute a movement behavior at a time. The method can also include validating the movement behavior alternatives by a physical prediction comparing measured points with trajectories of situation models and determining at least one trajectory indicating at least one possible behavior of the traffic participant, estimating at least one future position of the traffic participant based on the at least one trajectory, and outputting a signal representing the estimate future position.

Abstract: The invention relates to a vision-based attention system, comprising: at least one vision sensor, at least one image processing module processing an output signal of the vision sensor in order to generate at least one two-dimensional feature map, a dorsal attention subsystem generating a first saliency map on the basis of the at least one feature map, the saliency map indicating a first focus of attention for the driver assistance system, a ventral attention subsystem, independent to the dorsal attention subsystem, for generating a second saliency map on the basis of at least one feature map, which can be the same as the one used for the dorsal attention system or a different one, the second saliency map indicating unexpected visual stimuli.

Abstract: A method for forming an associative computer memory comprises the step of forming an inhibitory memory matrix A?=?(Ap?A). According to the Wilshaw model constructed from a given set of address patterns and content patterns' and random matrix structure.

Abstract: A robotic controller using schemata, the schemata being a set of parameterized sequences of motor commands in order to make a robot to achieve a set goal, the parameters of the sequences being gained from the state variables of the robotic controller, a robotic controller comprising an interface for supplying sensory input to the robotic controller. A schemata state memory (1) structure supplied with either input from a schemata recognition module (4) or input from an inverse model module (2) or combinations of them. An inverse model module (2) for generating motor commands based on state variables and stored schemata, a forward model module (3) for predicting state variables based on state variables and stored schemata, and a schemata recognition module (4) for selecting a schemata based on supplied state variables of the robot controlled by the robotic controller.

Abstract: A robot is provided with a motion control unit that avoids collision between segments of the robot or between segments of the robot and other objects. The motion control unit of the robot comprises a distance computing module, a whole body control module, a collision avoidance module, and a blending control unit. The distance computing module calculates two closest points of different segments of the robot connected to each other via at least one joint or a segment of the robot and another object. The collision avoidance module is provided with the information about the two closest points. The blending control unit combines the weighted output control signals of the whole body control module and the collision avoidance control module. The weight of the whole body control output signal is higher when the risk of collision is lower. The weight of the collision avoidance control output signal is higher when the risk of collision is higher.

Abstract: The present invention relates to a technique for detecting dynamic (i.e., moving) objects using sensor signals with 3D information and can be deployed e.g. in driver assistance systems.

Abstract: One embodiment of the present invention provides a post-processing method of a modulation envelope resulting from an interference of two harmonics in a filter band. According to one embodiment, the method comprising filtering the modulation envelope with a band-pass filter bank, wherein a combination of demodulation and application of the band-pass filter on the modulation envelope enables use of identical techniques for resolved and unresolved harmonics. One embodiment of the present invention provides a method of determining whether a frequency band of an input signal includes unresolved harmonics. According to a further embodiment, in response to a determination that the frequency band includes unresolved harmonics, the method comprises obtaining a modulation envelope of the frequency band by demodulating the frequency band, obtaining one or more frequency bands from the modulation envelope, and determining an evidence value that one of the frequency bands originates from one of fundamental frequencies.

Abstract: A computer-implemented system and method for estimating properties of objects represented in digital images, comprising the steps of (a) encoding input data from a sensor in a neural map comprising neurons having numerical activation values, wherein the activation values in the neural maps have continuous time dynamics defined by an update scheme; (b) creating, adapting and deleting weights of the neural map in unsupervised, incremental manner; (c) transmitting data from an input map to an output map, based on the values of the weights; wherein each weight between the input map (IM) and a neural output map (OM) has a unique source and destination neuron; and wherein data transmission is directed; and (d) detecting correlations between the input map (IM).

Abstract: A method for controlling a robot having at least one visual sensor. A target for a motion of the robot is defined. A motion control signal adapted for the robot reaching the target is calculated. A collision avoidance control signal based on the closest points of segments of the robot and a virtual object between the visual sensing means and the target is calculated. The motion control signal and the collision avoidance control signal are weighted and combined. The weight of the motion control signal is higher when a calculated collision risk is lower. The motion of the robot is controlled according to the combined signal so that no segment of the robot enters the space defined by the virtual object.

Abstract: A method for sound source localization comprises the steps of computing an envelope of a signal; performing a non-linear, onset preserving smoothing of the envelope; and evaluating cues for sound source localization, using the points where the smoothing changes from its rising phase to its falling phase as measurement points.

Abstract: A method for segregating a figure region from a background region in image sequences from dynamic visual scenes, comprising the steps of: (a) acquiring an image; (b) determining local motion estimations and confidences for each position of the image; (c) modifying a level-set function by moving and distorting the level-set function with the local motion estimations and smearing it based on the local motion confidences, to generate a predicted level set function that is geometrically in correspondence with the image and diffused at positions where the confidence of the motion estimation is low; (d) obtaining input features of the image by using a series of cues; (e) calculating a mask segregating the figure region from the background region of the image using the modified level-set function and the obtained input features; (f) extracting the figure region from the image; and repeating steps (a)-(f) until a termination criterion is satisfied.

Abstract: Techniques are provided for determining the time course of the fundamental frequency of harmonic signals, wherein the input signal is split into different frequency channels by band pass filters. Distances between crossings of different orders are determined, and a histogram of all these distance values for each instant in time is calculated. The distance values build a peak at the distance corresponding to the fundamental frequency. An example application of this technique is separation of acoustic sound sources in monaural recordings based on their underlying fundamental frequency. Application of these techniques, however, is not limited to the field of acoustics. These techniques can also be applied to other signals such as those originating from pressure sensors.

Abstract: An improved method for optimizing a design, based on direct manipulations of the object points of a design. In addition, the number and modifications of control points is kept as minimal as possible while the targeted movement of object points is realized and the automatic adaptation and generation of a set of control points for deformations which allows the movement of object points to desired positions. One aspect of the invention is to generate the transformation function f which is optimized to be able to realize desired changes of object parameters by means of control point variations. This optimization can be realized in a way that the mapping between the original coordinate system of the design and the spline coordinate system is not changed, so that no additional “freezing” process (the generation of the mapping between the coordinate systems) is necessary.

Abstract: A method and system for obtaining a pool of speech syllable models. The model pool is generated by first detecting a training segment using unsupervised speech segmentation or speech unit spotting. If the model pool is empty, a first speech syllable model is trained and added to the model pool. If the model pool is not empty, an existing model is determined from the model pool that best matches the training segment. Then the existing module is scored for the training segment. If the score is less than a predefined threshold, a new model for the training segment is created and added to the pool. If the score equals the threshold or is larger than the threshold, the training segment is used to improve or to re-estimate the model.

Abstract: The invention presents a method for comparing the similarity between image patches comprising the steps of receiving form at least two sources at least two image patches, wherein each source supplies an image patch, comparing the received image patches by extracting a number of corresponding subpart pairs from each image patch, calculating a normalized local similarity score between all corresponding subpart pairs, calculating a total matching score by integrating the local similarity scores of all corresponding subpart pairs, and using the total matching score as an indicator for an image patch similarity, determining corresponding similar image patches based on the total matching score.

Abstract: The fundamental frequency of a harmonic signal is estimated by forming a fundamental frequency hypothesis (f0?). A comb filter is provided based on the fundamental frequency hypothesis. The harmonic signal is filtered using the comb filter. The fundamental frequency hypothesis is tested for each tooth in the comb filter. A signal indicating an estimated fundamental frequency of the provided harmonic signal may be outputted based on the testing.

Abstract: A method for estimating the location of a sound source. First, a first microphone and a second microphone are moved relative to the sound source. Then the Intra-aural Time Difference (ITD) between the two microphones is measured. The moving and the measuring are repeated until the Intra-aural Time Difference (ITD) is smaller than a predefined threshold.

Abstract: The invention relates to a method for detecting the proper motion of an real-world object, comprising the steps of acquiring, by an image capturing device (ICD), a first image (I1) of the object at a first point in time (t1) and a second image (I2) at a second point in time (t2); obtaining a third (hypothetical) image (I3), based on an estimated effect of the motion of the image capturing device (ICD) itself (EMF) between the first and the second point in time (t1, t2), wherein the effect of the motion of the image capturing device (ICD) itself is estimated based on the forward kinematics of the image capturing device; determining an optical flow (OF) between the second image (I2) and the third image (I3); and evaluating the optical flow (OF) by incorporating uncertainties of the optical flow (OF) and the ego-motion-flow (EMF) in order to determine the proper motion of the object.

Abstract: A method for modifying an object design using a computer comprises the steps of: selecting a first sub-design of the object design comprising a first free form deformation geometry and a first free deformation control volume that is variable and adaptive; choosing a second sub-design comprising a second free form deformation geometry; and replacing the first geometry with the second geometry.