Conti Temic Microelectronic Gmbh

Continental Teves, Ag and Company Ohg

Continental Autonomous Mobility Germany Gmbh

Christie Digital Systems Usa, Inc.

Conti Ternie Microelectronic Gmbh

Christian Scharfenberger

Michelle Karg

Robert Thiel

Ann-Katrin Fattal

Stefan Hegemann

Stefan Lueke

Chen Zhang

Matthew Post

Hicham Sekkati

Olga Prokofyeva

Daniel Westhofen

Heiko Hahn

Jason Deglint

Eric Piegert

The invention relates to correcting input image data, from a plurality of cameras of a vehicle panoramic-view system. includes: capturing input image data by the cameras, which are negatively influenced by rain, incident light and/or dirt, and providing to a trained artificial neural network, converting, by the trained network, the input image data into corrected output image data without negative influence, determining a certainty measure which is dependent on the degree of wetting by water, incident light and/or contamination for an image of the input image data, and characterizing the certainty of the trained network that the image correction of the network is accurate, and outputting, by the trained network, the output image data and the determined certainty measure. The method advantageously allows object recognition when cameras are fogged up and generation of an image data stream for human and computer vision from a network for an optimized correspondence search.

Correction of images from a panoramic-view camera system in the case of rain, incident light and contamination

The present disclosure relates to a machine learning method, to a method and to a device for converting input image data from a plurality of vehicle cameras of a panoramic-view system into optimized or enhanced output image data. The method for converting input image data from a plurality of vehicle cameras of a panoramic-view system into optimized or enhanced output image data includes input image data acquired by the vehicle cameras and having a current brightness or color distribution provided to a trained artificial neural network. the trained artificial neural network is configured to convert the input image data having the current brightness or color distribution into optimized or enhanced output image data having different output brightness or color distribution; and the trained artificial neural network is configured to output the output image data.

Converting input image data from a plurality of vehicle cameras of a surround-view system into optimised output image data

The invention relates to a method for converting a first neural network with a first architecture into a second neural network with a second architecture for use in a vehicle controller in order to obtain the knowledge of the first neural network and transfer same to the second neural network. In a first step of the method, a conversion () of at least one layer of the first neural network into at least one layer of the second neural network is carried out. In a second step, a random initialization () of the at least one converted layer is carried out in the architecture of the second neural network. In a third step, a training process () of the at least one converted layer is carried out in the second neural network. In a fourth step, a fine-tuning process () of the non-converted layer is carried out in the second neural network or in the entire second neural network. The conversion of the first neural network into the second neural network is carried out in multiple cycles or iterations, wherein for each cycle, the conversion (), random initialization (), training (), and simultaneous fine-tuning () steps are carried out.

Knowledge transfer between different deep learning architectures

A method for identifying adversarial attacks on an image based detection system for automated driving includes providing a reference signal and a potentially manipulated signal. The method also includes calculating a plurality of metrics which quantify differences between the signals in different ways. The method further includes creating a multi-dimensional feature space based on the calculated metrics and classifying the type of attack based on the calculated metrics. The class of the adversarial attack may then be output.

Automatic identification and classification of adversarial attacks

The present invention relates to a computer-implemented method and a system for testing the output of a neural network () having a plurality of layers (), which detects or classifies objects. The method comprises the step (S) of reading at least one result from at least one first layer () and the confidence value thereof, which is generated in the first layer () of a neural network (), and the step (S) of checking a plausibility of the result by taking into consideration the confidence value thereof so as to conclude whether the object detection by the neural network () is correct or false. The step (S) of checking comprises comparing the confidence value for the result with a predefined threshold value. In the event that it is concluded in the checking step (S) that the object detection is false, output of the object falsely detected by the neural network is prevented.

Testing a neural network

A device is configured to classify data. Its operation involves providing () data samples including one or more of: image data, radar data, acoustic data, and/or lidar data to a processing unit. The data samples include at least one test sample, including positive samples and negative samples. Each positive sample has been determined to contain data relating to at least one object to be detected including at least one pedestrian, car, vehicle, truck or bicycle. Each negative sample has been determined not to contain data relating to the at least one object to be detected. These determinations regarding the positive samples and the negative samples are provided as input data, validated by a human operator, and/or provided by the device itself through a learning algorithm. A first plurality of groups is generated () by the processing unit implementing an artificial neural network, wherein at least some of the first plurality of groups are assigned a weighting factor. Each group of the first plurality of groups is populated () by the processing unit implementing the artificial neural network with a different at least one of the plurality of negative samples based on a different feature of sample data similarity for each group, which involves processing the negative samples to determine a number of different features of sample data similarity in order to populate different groups with negative samples that share or substantially share that or a similar feature, wherein at least one of the groups of the first plurality of groups contains at least two negative samples. It is determined () by the processing unit implementing the artificial neural network whether the at least one test sample contains data relating to the at least one object based on the plurality of the positive samples and the first plurality of groups. The artificial neural network implements the learning algorithm.

Device for classifying data

A method for identifying objects begins with capturing an image of an external environment of a vehicle using a capturing unit arranged on the vehicle. An object region within the image is located by a region proposal process, and an object within the object region is classified in a classification process. The region proposal process and/or the classification process is/are implemented in a convolutional neural network. External prior information highlighting a possible object region is supplied to the region proposal process.

Method for identifying objects in an image of a camera

A method for the three-dimensional graphic or pictorial reconstruction of a vehicle begins with capturing an image of at least one vehicle with a camera. A first rectangular border of the entire vehicle is captured in the image, to obtain a first rectangle. A second rectangular border of one side of a vehicle is captured in the image, to obtain a second rectangle, and it is determined whether the first and second rectangles are borders which relate to the same vehicle. If so, then it is determined whether a side orientation of the vehicle can be assigned from the two rectangles and, if so, the side orientation is determined. Finally, a three-dimensional reconstruction of the vehicle is performed from the first rectangle, the second rectangle and the side orientation.

Method for three-dimensional graphic reconstruction of a vehicle

A device for object recognition of an input image includes: a patch selector configured to subdivide the input image into a plurality of zones and to define a plurality of patches for the zones; a voting maps generator configured to generate a set of voting maps for each zone and for each patch, and to binarize the generated set of voting maps; a voting maps combinator configured to combine the binarized set of voting maps; and a supposition generator configured to generate and refine a supposition out of or from the combined, binarized set of voting maps.

Device and method for object recognition of an input image for a vehicle

A processing unit with at least one image that relates to a scene external to a vehicle, processes the image to extract low level features. A low level feature is defined such that an object in the scene cannot be characterized on the basis of at least one low level feature in a single image of the at least one scene. The processing unit determines if at least a part of an object is present in a part of the scene, the determination comprises an analysis of the low level features. An output unit outputs information that there is something present in the scene.

Device for enabling a vehicle to automatically resume moving

A system and method for online projector-camera calibration from one or more images is provided. The system comprises: a projector, a camera, and a calibration device configured to: determine a map between pixels of each of a projector image and a camera image in fewer than one hundred percent of pixels of the projector image using feature extraction; determine an initial estimate of a fundamental matrix from the map; determine an initial guess of intrinsic properties of the projector and camera using one or more closed-form solutions; iteratively determine an error-function based on the map using the fundamental matrix while adding constraints on the intrinsic properties using the one or more closed-form solutions, and the initial estimate and guess as initial input; and, when the error-function reaches an acceptance value, determine intrinsic and extrinsic properties of the projector and the camera from current values of iterative estimates.

Growing community of inventors

Lindau, Germany

Christian Scharfenberger