Katholieke Universiteit Leuven

Toyota Motor Europe

Toyota Jidosha Kabushiki Kaisha

Katholieke Universiteit Leuven, Ku Leuven R&d

Marc Proesmans

Luc Van Gool

Hiroaki Shimizu

Davy Neven

Kazuki Tamura

Frank Verbiest

Bert De Brabandere

Gabriel Othmezouri

Wim Abbeloos

Stamatios Georgoulis

Wouter Van Gansbeke

Jonas Heylen

Bruno Dawagne

Bert Debrabandere

Simon Vandenhende

A system for producing a virtual image view for a vehicle is provided. The system includes one or more image capture means configured to capture image data in proximity to the vehicle, the image data being defined at least in part by first viewpoint parameters, and to provide an identifier identifying the respective one or more image capture means, storage means configured to store a plurality of virtualization records containing conversion information related to a virtualized viewpoint and a plurality of image capture means, and processing means. The processing means are configured to receive the captured image data, convert the first viewpoint parameters of the captured image data into virtual viewpoint parameters based on the conversion information associated with a virtualization record stored by the storage means, to result in the virtual image view, wherein the virtualization record is identified at least based on the identifier, and execute at least one driver assistance and/or automated driving function based on the virtual image view.

Systems and method for image normalization

A system for generating a mask for object instances in an image is provided. The system includes a first module comprising a trained neural network and configured to input the image to the neural network, wherein the neural network is configured to generate: pixel offset vectors for the pixels of the object instance configured to point towards a unique center of an object instance, the pixel offset vectors thereby forming a cluster with a cluster distribution, and for each object instance an estimate of said cluster distribution defining a margin for determining which pixels belong to the object instance. A method for training a neural network map to be used for generating a mask for object instances in an image is also provided.

System and method for generating a mask for object instances in an image

A computer-implemented method for training a classifier (Φη), including: training a pretext model (ΦΘ) to learn a pretext task, so as to minimize a distance between an output of a source sample via the pretext model (ΦΘ) and an output of a corresponding transformed sample via the pretext model (ΦΘ), the transformed sample being a sample obtained by applying a transformation (T) to the source sample; S) determining a neighborhood (NXi) of samples (Xi) of a dataset (SD) in the embedding space; S) training the classifier (Φη) to predict respective estimated probabilities Φηj(Xi), j=1 . . . C, for a sample (Xi) to belong to respective clusters (Cj), by using a second training criterion which tends to: maximize a likelihood for a sample and its neighbors (Xj) of its neighborhood (Nxi) to belong to the same cluster; and force the samples to be distributed over several clusters.

Computer-implemented training method, classification method and system and computer-readable recording medium

A system and a method for processing a plurality of images, each image of the plurality of images being acquired by a respective image acquisition module of a vehicle and each image acquisition module being oriented outwardly with respect to the vehicle, the method comprising:

Method and system for processing a plurality of images so as to detect lanes on a road

A system and a method for processing an image so as to perform instance segmentation. The system/method includes: a—inputting (S) the image (IMG) to a first neural network configured to output an affinity graph (AF), and b—inputting (S), to a second neural network, the affinity graph and a predefined seed-map (SM), so as to determine whether other pixels belong to a same instance, and set at a first value the value of the other pixels determined as belonging to the same instance.

Method and system for processing an image and performing instance segmentation using affinity graphs

Growing community of inventors

Leuven, Belgium

Marc Proesmans