Zaremba
Marek Zaremba, Ottawa CA
Patent application number | Description | Published |
---|---|---|
20120328161 | METHOD AND MULTI-SCALE ATTENTION SYSTEM FOR SPATIOTEMPORAL CHANGE DETERMINATION AND OBJECT DETECTION - A method and multi-scale attention system for the detection of objects and temporal change regions by a spatiotemporal attention operator of an image sequence, which linearly aggregates temporal change filter with spatial saliency filter and includes an extractor of salient maxima, which selects consecutive salient maxima of the spatiotemporal operator to produce the locations of the objects of interest and the centers of temporal change regions. The concept of spatial local scale introduced into the system and method for its determination allows for a scale-adaptive integration of the temporal change with spatial saliency and effective detection of different in size and location objects of interest. Can be used for object and spatiotemporal change detection in monitoring pollution, natural disasters, weather conditions and environmental changes based on satellite remote sensing imagery from various sensors. | 12-27-2012 |
Mark Zaremba, Bedfordshire GB
Patent application number | Description | Published |
---|---|---|
20150225684 | PHOTOBIOREACTOR - A method for non-invasive growth measurement of organisms in an apparatus for growing and harvesting organisms or substances derived from such organisms. The organisms are comprised in an aqueous medium in a vessel, the method comprising the steps of: a) Providing means for measuring the opacity of the aqueous medium in order to estimate a growth rate of the organisms; b) The means for measuring the opacity are arranged in the apparatus such that they are located at predetermined locations relative to the vessel; c) The means for measuring the opacity are calibrated to account for refraction, absorbance and reflection caused by the vessel at the predetermined location. Finally the method also allows for measuring the opacity of the aqueous medium at the predetermined location. | 08-13-2015 |
Wojciech Zaremba, Kluczbork PL
Patent application number | Description | Published |
---|---|---|
20160098632 | TRAINING NEURAL NETWORKS ON PARTITIONED TRAINING DATA - Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network. One of the methods includes obtaining partitioned training data for the neural network, wherein the partitioned training data comprises a plurality of training items each of which is assigned to a respective one of a plurality of partitions, wherein each partition is associated with a respective difficulty level; and training the neural network on each of the partitions in a sequence from a partition associated with an easiest difficulty level to a partition associated with a hardest difficulty level, wherein, for each of the partitions, training the neural network comprises: training the neural network on a sequence of training items that includes training items selected from the training items in the partition interspersed with training items selected from the training items in all of the partitions. | 04-07-2016 |