Toyota Motor Europe

Toyota Jidosha Kabushiki Kaisha

Katholieke Universiteit Leuven

Katholieke Universiteit Leuven, Ku Leuven R&d

K.u. Leuven Research & Development

Eidgenoessische Technische Hochschule Zurich

Eidgenossische Technische Hochschule Zurich

Environmental Systems Research Institute, Inc.

Swiss Federal Institute of Technology Zurich

Luc Van Gool

Ryuji Funayama

Marc Proesmans

Hiroaki Shimizu

Davy Neven

Hiromichi Yanagihara

Bert De Brabandere

Kazuki Tamura

Frank Verbiest

Tinne Tuytelaars

Herbert Bay

Kenichi Kitahama

Philippe Robert Koninckx

Thomas Koninckx

Wim Abbeloos

Konrad Schindler

Pascal Müller

Gang Zeng

Bastian Leibe

Markus Mathias

Nima Razavi

Radu Timofte

Juergen Gall

Jonas Heylen

Bruno Dawagne

Bert Debrabandere

Rodrigo Benenson

Andreas Ess

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 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

A discriminator generation deviceincludes a feature quantity extraction unitwhich, using at least two pattern groups having patterns of different sizes for a detection object, extracts a feature quantity of patterns configuring each pattern group, and a discriminator generation unitwhich generates a discriminator for detecting a detection object of a size corresponding to each pattern group in an image based on the feature quantity of the patterns of each pattern group.

Discrimination container generation device and pattern detection device

For generating a 3D geometric model () and/or a definition of the 3D geometric model from a single digital image of a building facade (), a facade structure is detected from the digital image by dividing the facade () along horizontal lines into horizontal layers representative of floors (), and by dividing the horizontal layers along vertical lines into tiles (). The tiles () are further subdivided into a hierarchy of rectangular image regions (). 3D architectural objects () corresponding to the image regions () are determined in an architectural element library. The 3D geometric model () or the definition of the 3D geometric model is generated based on the facade structure, the hierarchy and the 3D architectural objects (). The library-based generation of the 3D geometric model makes it possible to enhance simple textured building models constructed from aerial images and/or ground-based photographs.

Computer system and method for generating a 3D geometric model

A learning unit generates a function table indicating the relationship between the class number and position information of an object and the probability of appearance of the object for each small area image pattern of a code book, calculates a sharing matrix indicating the commonality of a feature amount between the classes, makes a tree diagram in which the classes with a similar feature amount are clustered, and calculates the weight of each node in the tree diagram for each small area image pattern. The recognition processing unit compares image data captured by a camera with the code book, selects the closest small area image pattern, extracts the class related to the node with the smallest weight among the nodes with a weight equal to or greater than a threshold value, and votes the position information of the small area image pattern for the class, thereby recognizing the object.

Object recognition device

A multiple viewpoint endoscope system having a multiple viewpoint camera setup and/or an intelligent or cognitive image control system and display device particularly adapted for localizing internal structures within a cavity or an enclosing structure, such as an animal body, for instance the abdomen of an animal or human, or for localizing a real or synthetic image of such internal structures within an overview image or on an overview 3D model.

Endoscopic vision system

A method for operating on images is described for interest point detection and/or description working under different scales and with different rotations, e.g. for scale-invariant and rotation-invariant interest point detection and/or description.

Robust interest point detector and descriptor

A motion estimating device first detects mobile objects Oi and Oi' in continuous image frames T and T&#x2032;, and acquires image areas Ri and Ri&#x2032; corresponding to the mobile objects Oi and Oi&#x2032;. Then, the motion estimating device removes the image areas Ri and Ri&#x2032; corresponding to the mobile objects Oi and Oi&#x2032; in the image frames T and T&#x2032;, extracts corresponding point pairs Pj of feature points between the image frames T and T&#x2032; from the image areas having removed the image areas Ri and Ri&#x2032;, and carries out the motion estimation of the autonomous mobile machine between the image frames T and T&#x2032; on the basis of the positional relationship of the corresponding point pairs Pj of feature points.

Motion estimating device

Methods and apparatus for operating on images are described, in particular methods and apparatus for interest point detection and/or description working under different scales and with different rotations, e.g. for scale-invariant and rotation-invariant interest point detection and/or description. The present invention can provide improved or alternative apparatus and methods for matching interest points either in the same image or in a different image. The present invention can provide alternative or improved software for implementing any of the methods of the invention. The present invention can provide alternative or improved data structures created by multiple filtering operations to generate a plurality of filtered images as well as data structures for storing the filtered images themselves, e.g. as stored in memory or transmitted through a network. The present invention can provide alternative or improved data structures including descriptors of interest points in images, e.g. as stored in memory or transmitted through a network as well as data structures associating such descriptors with an original copy of the image or an image derived therefrom, e.g. a thumbnail image.

Growing community of inventors

Antwerp, Belgium

Luc Van Gool