Czech Technical University in Prague

Toyota Jidosha Kabushiki Kaisha

Toyota Motor Europe Nv/sa

Ceske Vysoke Uceni Technicke V Praze

Jiri Matas

Katsuhiro Sakai

Gabriel Othmezouri

Ichiro Sakata

Jan Sochman

Stepán Obdrzálek

Nikolay Chumerin

Stepan Obdrzalek

Ondrej Chum

Michal Neoral

Lukas Neumann

Michal Busta

Methods and systems for egomotion estimation (e.g. of a vehicle) from visual inputs of a stereo pair of video cameras are described. 3D egomotion estimation is a six degrees of freedom problem in general. In embodiments of the present invention, this is simplified to four dimensions and further decomposed to two two-dimensional sub-solutions. The decomposition allows use of a voting strategy that identifies the most probable solution. An input is a set of image correspondences between two temporally consecutive stereo pairs, i.e. feature points do not need to be tracked over time. The experiments show that even if a trajectory is put together as a simple concatenation of frame-to-frame increments, the results are reliable and precise.

Voting strategy for visual ego-motion from stereo

An image search method that is robust and fast (with computational complexity of logarithmic order relative to the number of models). The image search includes extracting a plurality of regions from one or more model images and normalizing the regions as standard regions; setting a specific region in each normalized standard region and classifying the plurality of standard regions under two or more subsets on the basis of a feature of the specific region; iteratively performing an operation of setting another specific region at a location different from that of the aforementioned specific region in each standard region classified in each subset and classifying the plurality of standard regions under still more subsets on the basis of a feature of the other specific region; and outputting the locations of the specific regions in the standard regions in the respective classifications and the features of the specific regions in the classifications.

Image search method and device

An image search method that is robust and fast (with computational complexity of logarithmic order relative to the number of models). The image search method including: extracting a plurality of specific regions possessing such a property that a shape can be normalized regardless of an affine transformation thereof, as affine-invariant regions from one or more learning images; calculating, with respect to a reference affine-invariant region, other neighboring affine-invariant regions as a set; deforming the neighboring affine-invariant regions by a transformation to normalize the shape of the reference affine-invariant region; and outputting the deformed shapes of the neighboring affine-invariant regions, together with combination of the reference affine-invariant region and the neighboring affine-invariant regions.

Image search method and device using affine-invariant regions

Growing community of inventors

Roztoky u Prahy, Czechia

Jiri Matas