Patents by Inventor Szabolcs Fulop
Szabolcs Fulop has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240078820Abstract: A vehicle cabin monitoring system includes a customization profile for storing: annotated images associated with annotation(s) indicating a ground truth for an associated region of an image; and a plurality of core processing parameters for an image processing component of an image processor. The system is: responsive to user interaction with a user interactive control of the vehicle within a field of view of a camera for storing an image acquired by the camera at the time of interaction in the customization profile with an annotation indicating a ground truth for an associated region of the image according to the interaction; and configured to use images from the customization profile for re-training an image processing component of the processor and for storing updated core processing parameters produced by the re-training in the customization profile for use by the re-trained image processing component in processing subsequently acquired images.Type: ApplicationFiled: September 7, 2022Publication date: March 7, 2024Inventors: Georgiana NEGISHI, Szabolcs FULOP, Tudor TOPOLEANU, Paul GEORGE
-
Publication number: 20230107097Abstract: A method for identifying a gesture from one of a plurality of dynamic gestures, each dynamic gesture comprising a distinct movement made by a user over a period of time within a field of view of an image acquisition device comprises iteratively: acquiring a current image from said image acquisition device at a given time; and passing at least a portion of the current image through a bidirectionally recurrent multi-layer classifier. A final layer of the multi-layer classifier comprises an output indicating a probability that a gesture from the plurality of dynamic gestures is being made by a user during the time of acquiring the image.Type: ApplicationFiled: October 6, 2021Publication date: April 6, 2023Applicant: FotoNation LimitedInventors: Tudor TOPOLEANU, Szabolcs FULOP, Petronel BIGIOI, Cian RYAN, Joseph LEMLEY
-
Publication number: 20230004745Abstract: A method for monitoring occupants of a vehicle comprises identifying a respective body region for one or more occupants of the vehicle within an obtained image; identifying within the body regions, skeletal points including points on an arm of a body; identifying one or more hand regions; and determining a hand region to be either a left or a right hand of an occupant in accordance with its spatial relationship with identified skeletal points of the body region of an occupant. The left or right hand region for the occupant are provided to a pair of classifiers to provide an activity classification for the occupant, a first classifier being trained with images of hands of occupants in states where objects involved are not visible and a second classifier being trained with images of occupants in the states where the objects are visible in at least one hand region.Type: ApplicationFiled: June 30, 2021Publication date: January 5, 2023Applicant: FotoNation LimitedInventors: Szabolcs FULOP, Dragos DINU, Radu Ene
-
Patent number: 11532148Abstract: An image processing system comprises a template matching engine (TME). The TME reads an image from the memory; and as each pixel of the image is being read, calculates a respective feature value of a plurality of feature maps as a function of the pixel value. A pre-filter is responsive to a current pixel location comprising a node within a limited detector cascade to be applied to a window within the image to: compare a feature value from a selected one of the plurality of feature maps corresponding to the pixel location to a threshold value; and responsive to pixels for all nodes within a limited detector cascade to be applied to the window having been read, determine a score for the window. A classifier, responsive to the pre-filter indicating that a score for a window is below a window threshold, does not apply a longer detector cascade to the window before indicating that the window does not comprise an object to be detected.Type: GrantFiled: August 17, 2020Date of Patent: December 20, 2022Assignee: FotoNation LimitedInventors: Nicolae Nicoara, Cristina Raceala, Corneliu Zaharia, Szabolcs Fulop, Oana Iovita
-
Patent number: 11106894Abstract: An image processing apparatus comprises a normalisation module operatively connected across a bus to a memory storing an image in which a region of interest (ROI) has been identified within the image. The ROI is bound by a rectangle having a non-orthogonal orientation within the image. In one embodiment, the normalisation module is arranged to divide the ROI into one or more slices, each slice comprising a plurality of adjacent rectangular tiles. For each slice, the apparatus successively reads ROI information for each tile from the memory including: reading a portion of the image extending across at least a width of the slice line-by-line along an extent of a slice. For each tile, the apparatus downsamples the ROI information to a buffer to within a scale SD<2 of a required scale for a normalised version of the ROI.Type: GrantFiled: October 25, 2018Date of Patent: August 31, 2021Assignee: FotoNation LimitedInventors: Vlad Georgescu, Mihai Constantin Munteanu, Petronel Bigioi, Corneliu Zaharia, Szabolcs Fulop, Gyorgy Simon
-
Publication number: 20200380291Abstract: An image processing system comprises a template matching engine (TME). The TME reads an image from the memory; and as each pixel of the image is being read, calculates a respective feature value of a plurality of feature maps as a function of the pixel value. A pre-filter is responsive to a current pixel location comprising a node within a limited detector cascade to be applied to a window within the image to: compare a feature value from a selected one of the plurality of feature maps corresponding to the pixel location to a threshold value; and responsive to pixels for all nodes within a limited detector cascade to be applied to the window having been read, determine a score for the window. A classifier, responsive to the pre-filter indicating that a score for a window is below a window threshold, does not apply a longer detector cascade to the window before indicating that the window does not comprise an object to be detected.Type: ApplicationFiled: August 17, 2020Publication date: December 3, 2020Applicant: FotoNation LimitedInventors: Nicolae NICOARA, Cristina RACEALA, Corneliu ZAHARIA, Szabolcs FULOP, Oana IOVITA
-
Publication number: 20200184321Abstract: A multi-processor neural network processing apparatus comprises: a plurality of network processing engines, each for processing one or more layers of a neural network according to a network configuration. A memory at least temporarily stores network configuration information, input image information, intermediate image information and output information for the network processing engines. At least one of the network processing engines is configured, when otherwise idle, to identify configuration information and input image information to be processed by another target network processing engine and to use the configuration information and input image information to replicate the processing of the target network processing engine.Type: ApplicationFiled: December 11, 2018Publication date: June 11, 2020Applicant: FotoNation LimitedInventors: Szabolcs FULOP, Corneliu ZAHARIA, Petronel BIGIOI
-
Publication number: 20200050885Abstract: An image processing system comprises a template matching engine (TME). The TME reads an image from the memory; and as each pixel of the image is being read, calculates a respective feature value of a plurality of feature maps as a function of the pixel value. A pre-filter is responsive to a current pixel location comprising a node within a limited detector cascade to be applied to a window within the image to: compare a feature value from a selected one of the plurality of feature maps corresponding to the pixel location to a threshold value; and responsive to pixels for all nodes within a limited detector cascade to be applied to the window having been read, determine a score for the window. A classifier, responsive to the pre-filter indicating that a score for a window is below a window threshold, does not apply a longer detector cascade to the window before indicating that the window does not comprise an object to be detected.Type: ApplicationFiled: October 22, 2019Publication date: February 13, 2020Applicant: FotoNation LimitedInventors: Nicolae NICOARA, Cristina RACEALA, Corneliu ZAHARIA, Szabolcs FULOP, Oana IOVITA
-
Patent number: 10460198Abstract: An image processing system comprises a template matching engine (TME). The TME reads an image from the memory; and as each pixel of the image is being read, calculates a respective feature value of a plurality of feature maps as a function of the pixel value. A pre-filter is responsive to a current pixel location comprising a node within a limited detector cascade to be applied to a window within the image to: compare a feature value from a selected one of the plurality of feature maps corresponding to the pixel location to a threshold value; and responsive to pixels for all nodes within a limited detector cascade to be applied to the window having been read, determine a score for the window. A classifier, responsive to the pre-filter indicating that a score for a window is below a window threshold, does not apply a longer detector cascade to the window before indicating that the window does not comprise an object to be detected.Type: GrantFiled: December 15, 2016Date of Patent: October 29, 2019Assignee: FotoNation LimitedInventors: Nicolae Nicoara, Cristina Raceala, Corneliu Zaharia, Szabolcs Fulop, Oana Iovita
-
Publication number: 20190130164Abstract: An image processing apparatus comprises a normalisation module operatively connected across a bus to a memory storing an image in which a region of interest (ROI) has been identified within the image. The ROI is bound by a rectangle having a non-orthogonal orientation within the image. In one embodiment, the normalisation module is arranged to divide the ROI into one or more slices, each slice comprising a plurality of adjacent rectangular tiles. For each slice, the apparatus successively reads ROI information for each tile from the memory including: reading a portion of the image extending across at least a width of the slice line-by-line along an extent of a slice. For each tile, the apparatus downsamples the ROI information to a buffer to within a scale SD<2 of a required scale for a normalised version of the ROI.Type: ApplicationFiled: October 25, 2018Publication date: May 2, 2019Inventors: Vlad GEORGESCU, Mihai Constantin MUNTEANU, Petronel BIGIOI, Corneliu ZAHARIA, Szabolcs FULOP, Gyorgy SIMON
-
Patent number: 10115003Abstract: An image processing apparatus comprises a normalisation module operatively connected across a bus to a memory storing an image in which a region of interest (ROI) has been identified within the image. The ROI is bound by a rectangle having a non-orthogonal orientation within the image. In one embodiment, the normalisation module is arranged to divide the ROI into one or more slices, each slice comprising a plurality of adjacent rectangular tiles. For each slice, the apparatus successively reads ROI information for each tile from the memory including: reading a portion of the image extending across at least a width of the slice line-by-line along an extent of a slice. For each tile, the apparatus downsamples the ROI information to a buffer to within a scale SD<2 of a required scale for a normalised version of the ROI.Type: GrantFiled: August 25, 2016Date of Patent: October 30, 2018Assignee: FotoNation LimitedInventors: Vlad Georgescu, Mihai Constantin Munteanu, Petronel Bigioi, Corneliu Zaharia, Szabolcs Fulop, Gyorgy Simon
-
Publication number: 20170185864Abstract: An image processing system comprises a template matching engine (TME). The TME reads an image from the memory; and as each pixel of the image is being read, calculates a respective feature value of a plurality of feature maps as a function of the pixel value. A pre-filter is responsive to a current pixel location comprising a node within a limited detector cascade to be applied to a window within the image to: compare a feature value from a selected one of the plurality of feature maps corresponding to the pixel location to a threshold value; and responsive to pixels for all nodes within a limited detector cascade to be applied to the window having been read, determine a score for the window. A classifier, responsive to the pre-filter indicating that a score for a window is below a window threshold, does not apply a longer detector cascade to the window before indicating that the window does not comprise an object to be detected.Type: ApplicationFiled: December 15, 2016Publication date: June 29, 2017Inventors: Nicolae NICOARA, Cristina RACEALA, Corneliu ZAHARIA, Szabolcs FULOP, Oana IOVITA
-
Patent number: 9639775Abstract: A template matching module is configured to program a processor to apply multiple differently-tuned object detection classifier sets in parallel to a digital image to determine one or more of an object type, configuration, orientation, pose or illumination condition, and to dynamically switch between object detection templates to match a determined object type, configuration, orientation, pose, blur, exposure and/or directional illumination condition.Type: GrantFiled: March 30, 2015Date of Patent: May 2, 2017Assignee: FotoNation LimitedInventors: Bogdan Sultana, Stefan Petrescu, Radu Nicolau, Vlad Ionut Ursachi, Petronel Bigioi, Corneliu Zaharia, Peter Corcoran, Szabolcs Fulop, Mihnea Gangea
-
Publication number: 20170061639Abstract: An image processing apparatus comprises a normalisation module operatively connected across a bus to a memory storing an image in which a region of interest (ROI) has been identified within the image. The ROI is bound by a rectangle having a non-orthogonal orientation within the image. In one embodiment, the normalisation module is arranged to divide the ROI into one or more slices, each slice comprising a plurality of adjacent rectangular tiles. For each slice, the apparatus successively reads ROI information for each tile from the memory including: reading a portion of the image extending across at least a width of the slice line-by-line along an extent of a slice. For each tile, the apparatus downsamples the ROI information to a buffer to within a scale SD<2 of a required scale for a normalised version of the ROI.Type: ApplicationFiled: August 25, 2016Publication date: March 2, 2017Inventors: Vlad GEORGESCU, Mihai Constantin MUNTEANU, Petronel BIGIOI, Corneliu ZAHARIA, Szabolcs FULOP, Gyorgy SIMON
-
Publication number: 20150206030Abstract: A template matching module is configured to program a processor to apply multiple differently-tuned object detection classifier sets in parallel to a digital image to determine one or more of an object type, configuration, orientation, pose or illumination condition, and to dynamically switch between object detection templates to match a determined object type, configuration, orientation, pose, blur, exposure and/or directional illumination condition.Type: ApplicationFiled: March 30, 2015Publication date: July 23, 2015Inventors: BOGDAN SULTANA, STEFAN PETRESCU, RADU NICOLAU, VLAD IONUT URSACHI, PETRONEL BIGIOI, CORNELIU ZAHARIA, PETER CORCORAN, SZABOLCS FULOP, MIHNEA GANGEA
-
Patent number: 8995715Abstract: A template matching module is configured to program a processor to apply multiple differently-tuned object detection classifier sets in parallel to a digital image to determine one or more of an object type, configuration, orientation, pose or illumination condition, and to dynamically switch between object detection templates to match a determined object type, configuration, orientation, pose, blur, exposure and/or directional illumination condition.Type: GrantFiled: October 26, 2011Date of Patent: March 31, 2015Assignee: FotoNation LimitedInventors: Bogdan Sultana, Stefan Petrescu, Radu Nicolau, Vlad Ionut Ursachi, Petronel Bigioi, Corneliu Zaharia, Peter Corcoran, Szabolcs Fulop, Mihnea Gangea
-
Publication number: 20120106790Abstract: A template matching module is configured to program a processor to apply multiple differently-tuned object detection classifier sets in parallel to a digital image to determine one or more of an object type, configuration, orientation, pose or illumination condition, and to dynamically switch between object detection templates to match a determined object type, configuration, orientation, pose, blur, exposure and/or directional illumination condition.Type: ApplicationFiled: October 26, 2011Publication date: May 3, 2012Applicant: DIGITALOPTICS CORPORATION EUROPE LIMITEDInventors: Bogdan Sultana, Stefan Petrescu, Radu Nicolau, Vlad Ionut Ursachi, Petronel Bigioi, Corneliu Zaharia, Peter Corcoran, Szabolcs Fulop, Mihnea Gangea