Patents by Inventor Rebecca L. Gerlach
Rebecca L. Gerlach 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: 20220261567Abstract: In some arrangements, product packaging is digitally watermarked over most of its extent to facilitate high-throughput item identification at retail checkouts. Imagery captured by conventional or plenoptic cameras can be processed (e.g., by GPUs) to derive several different perspective-transformed views—further minimizing the need to manually reposition items for identification. Crinkles and other deformations in product packaging can be optically sensed, allowing such surfaces to be virtually flattened to aid identification. Piles of items can be 3D-modelled and virtually segmented into geometric primitives to aid identification, and to discover locations of obscured items. Other data (e.g., including data from sensors in aisles, shelves and carts, and gaze tracking for clues about visual saliency) can be used in assessing identification hypotheses about an item. Logos may be identified and used—or ignored—in product identification. A great variety of other features and arrangements are also detailed.Type: ApplicationFiled: March 11, 2022Publication date: August 18, 2022Inventors: Tony F. Rodriguez, Bruce L. Davis, Geoffrey B. Rhoads, John D. Lord, Alastair M. Reed, Eric D. Evans, Rebecca L. Gerlach, Yang Bai, John F. Stach, Tomas Filler, Marc G. Footen, Sean Calhoon, William Y. Conwell, Brian T. MacIntosh
-
Patent number: 11288472Abstract: In one aspect, a retail store has multiple sensors, including item sensors in a shopping cart for gathering data from a shopper-selected first item. At least certain of the sensor data is provided to a classifier, which was previously-trained (using data including optical data from known items) to identify possible item matches corresponding to data sensed from the first item. An item identification hypothesis that the shopper-selected first item has a particular identity is evaluated based on (a) information from the classifier, and (b) store layout data indicating items associated with a store location visited by the cart or shopper. The item identification hypothesis has a confidence score. If the score meets a criterion, an item of the hypothesized identity is added to a shopping tally. A great number of other features and arrangements are also detailed.Type: GrantFiled: January 6, 2021Date of Patent: March 29, 2022Assignee: Digimarc CorporationInventors: Tony F. Rodriguez, Bruce L. Davis, Geoffrey B. Rhoads, Alastair M. Reed, Eric D. Evans, Rebecca L. Gerlach, John F. Stach, Marc G. Footen
-
Patent number: 11281876Abstract: In one aspect, a retail store includes a multitude of cameras, including a plurality of 3D cameras, and a plurality of other cameras. Certain of the cameras provide imagery from which a shopper's track through the store is monitored, and certain of the cameras are positioned to detect removal of items from store shelves. The store also includes a computer system that provides a database of information about store layout, indicating stock locations of different items. The computer system receives imagery from the cameras (or information derived from such imagery) and uses this data, together with information from the database and information derived from other sensors in the store, to produce a probabilistic tally of items selected by a store shopper. This tally includes an item bearing a barcode, but is produced without reading the barcode. Each item on the tally is associated with a confidence score that meets a computer system-determined threshold.Type: GrantFiled: January 15, 2021Date of Patent: March 22, 2022Assignee: Digimarc CorporationInventors: Tony F. Rodriguez, Bruce L. Davis, Geoffrey B. Rhoads, Eric D. Evans, Rebecca L. Gerlach, John F. Stach, Tomas Filler
-
Publication number: 20210192162Abstract: In some arrangements, product packaging is digitally watermarked over most of its extent to facilitate high-throughput item identification at retail checkouts. Imagery captured by conventional or plenoptic cameras can be processed (e.g., by GPUs) to derive several different perspective-transformed views—further minimizing the need to manually reposition items for identification. Crinkles and other deformations in product packaging can be optically sensed, allowing such surfaces to be virtually flattened to aid identification. Piles of items can be 3D-modelled and virtually segmented into geometric primitives to aid identification, and to discover locations of obscured items. Other data (e.g., including data from sensors in aisles, shelves and carts, and gaze tracking for clues about visual saliency) can be used in assessing identification hypotheses about an item. Logos may be identified and used—or ignored—in product identification. A great variety of other features and arrangements are also detailed.Type: ApplicationFiled: January 6, 2021Publication date: June 24, 2021Inventors: Tony F. Rodriguez, Bruce L. Davis, Geoffrey B. Rhoads, John D. Lord, Alastair M. Reed, Eric D. Evans, Rebecca L. Gerlach, Yang Bai, John F. Stach, Tomas Filler, Marc G. Footen, Sean Calhoon, William Y. Conwell, Brian T. MacIntosh
-
Publication number: 20210157998Abstract: In some arrangements, product packaging is digitally watermarked over most of its extent to facilitate high-throughput item identification at retail checkouts. Imagery captured by conventional or plenoptic cameras can be processed (e.g., by GPUs) to derive several different perspective-transformed views—further minimizing the need to manually reposition items for identification. Crinkles and other deformations in product packaging can be optically sensed, allowing such surfaces to be virtually flattened to aid identification. Piles of items can be 3D-modelled and virtually segmented into geometric primitives to aid identification, and to discover locations of obscured items. Other data (e.g., including data from sensors in aisles, shelves and carts, and gaze tracking for clues about visual saliency) can be used in assessing identification hypotheses about an item. Logos may be identified and used—or ignored—in product identification. A great variety of other features and arrangements are also detailed.Type: ApplicationFiled: January 15, 2021Publication date: May 27, 2021Inventors: Tony F. Rodriguez, Bruce L. Davis, Geoffrey B. Rhoads, John D. Lord, Alastair M. Reed, Eric D. Evans, Rebecca L. Gerlach, Yang Bai, John F. Stach, Tomas Filler, Marc G. Footen, Sean Calhoon, William Y. Conwell, Brian T. MacIntosh
-
Patent number: 10963657Abstract: In some arrangements, product packaging is digitally watermarked over most of its extent to facilitate high-throughput item identification at retail checkouts. Imagery captured by conventional or plenoptic cameras can be processed (e.g., by GPUs) to derive several different perspective-transformed views—further minimizing the need to manually reposition items for identification. Crinkles and other deformations in product packaging can be optically sensed, allowing such surfaces to be virtually flattened to aid identification. Piles of items can be 3D-modelled and virtually segmented into geometric primitives to aid identification, and to discover locations of obscured items. Other data (e.g., including data from sensors in aisles, shelves and carts, and gaze tracking for clues about visual saliency) can be used in assessing identification hypotheses about an item. Logos may be identified and used—or ignored—in product identification. A great variety of other features and arrangements are also detailed.Type: GrantFiled: June 5, 2020Date of Patent: March 30, 2021Assignee: Digimarc CorporationInventors: Tony F. Rodriguez, Bruce L. Davis, Geoffrey B. Rhoads, Eric D. Evans, Rebecca L. Gerlach, Tomas Filler
-
Publication number: 20210004550Abstract: In some arrangements, product packaging is digitally watermarked over most of its extent to facilitate high-throughput item identification at retail checkouts. Imagery captured by conventional or plenoptic cameras can be processed (e.g., by GPUs) to derive several different perspective-transformed views—further minimizing the need to manually reposition items for identification. Crinkles and other deformations in product packaging can be optically sensed, allowing such surfaces to be virtually flattened to aid identification. Piles of items can be 3D-modelled and virtually segmented into geometric primitives to aid identification, and to discover locations of obscured items. Other data (e.g., including data from sensors in aisles, shelves and carts, and gaze tracking for clues about visual saliency) can be used in assessing identification hypotheses about an item. Logos may be identified and used—or ignored—in product identification. A great variety of other features and arrangements are also detailed.Type: ApplicationFiled: March 17, 2017Publication date: January 7, 2021Inventors: Brian T. MacIntosh, Tony F. Rodriguez, Bruce L. Davis, Geoffrey B. Rhoads, John D. Lord, Alastair M. Reed, Eric D. Evans, Rebecca L. Gerlach, Yang Bai, John F. Stach, Tomas Filler, Marc G. Footen, Sean Calhoon, William Y. Conwell
-
Publication number: 20200380226Abstract: In some arrangements, product packaging is digitally watermarked over most of its extent to facilitate high-throughput item identification at retail checkouts. Imagery captured by conventional or plenoptic cameras can be processed (e.g., by GPUs) to derive several different perspective-transformed views—further minimizing the need to manually reposition items for identification. Crinkles and other deformations in product packaging can be optically sensed, allowing such surfaces to be virtually flattened to aid identification. Piles of items can be 3D-modelled and virtually segmented into geometric primitives to aid identification, and to discover locations of obscured items. Other data (e.g., including data from sensors in aisles, shelves and carts, and gaze tracking for clues about visual saliency) can be used in assessing identification hypotheses about an item. Logos may be identified and used—or ignored—in product identification. A great variety of other features and arrangements are also detailed.Type: ApplicationFiled: June 5, 2020Publication date: December 3, 2020Inventors: Tony F. Rodriguez, Bruce L. Davis, Geoffrey B. Rhoads, John D. Lord, Alastair M. Reed, Eric D. Evans, Rebecca L. Gerlach, Yang Bai, John F. Stach, Tomas Filler, Marc G. Footen, Sean Calhoon, William Y. Conwell, Brian T. MacIntosh
-
Publication number: 20200372228Abstract: In some arrangements, product packaging is digitally watermarked over most of its extent to facilitate high-throughput item identification at retail checkouts. Imagery captured by conventional or plenoptic cameras can be processed (e.g., by GPUs) to derive several different perspective-transformed views—further minimizing the need to manually reposition items for identification. Crinkles and other deformations in product packaging can be optically sensed, allowing such surfaces to be virtually flattened to aid identification. Piles of items can be 3D-modelled and virtually segmented into geometric primitives to aid identification, and to discover locations of obscured items. Other data (e.g., including data from sensors in aisles, shelves and carts, and gaze tracking for clues about visual saliency) can be used in assessing identification hypotheses about an item. Logos may be identified and used—or ignored—in product identification. A great variety of other features and arrangements are also detailed.Type: ApplicationFiled: June 5, 2020Publication date: November 26, 2020Inventors: Tony F. Rodriguez, Bruce L. Davis, Geoffrey B. Rhoads, John D. Lord, Alastair M. Reed, Eric D. Evans, Rebecca L. Gerlach, Yang Bai, John F. Stach, Tomas Filler, Marc G. Footen, Sean Calhoon, William Y. Conwell, Brian T. MacIntosh
-
Publication number: 20200279084Abstract: In some arrangements, product packaging is digitally watermarked over most of its extent to facilitate high-throughput item identification at retail checkouts. Imagery captured by conventional or plenoptic cameras can be processed (e.g., by GPUs) to derive several different perspective-transformed views—further minimizing the need to manually reposition items for identification. Crinkles and other deformations in product packaging can be optically sensed, allowing such surfaces to be virtually flattened to aid identification. Piles of items can be 3D-modelled and virtually segmented into geometric primitives to aid identification, and to discover locations of obscured items. Other data (e.g., including data from sensors in aisles, shelves and carts, and gaze tracking for clues about visual saliency) can be used in assessing identification hypotheses about an item. A great variety of other features and arrangements are also detailed.Type: ApplicationFiled: March 17, 2020Publication date: September 3, 2020Inventors: Bruce L. Davis, Tony F. Rodriguez, Geoffrey B. Rhoads, John D. Lord, Alastair M. Reed, Eric D. Evans, Rebecca L. Gerlach, Yang Bai, John F. Stach, Tomas Filler, Marc G. Footen, Sean C. Calhoon
-
Patent number: 10474858Abstract: A variety of technologies having practical application in retail stores are detailed. One is an improved method of identifying items selected by customers. This method includes receiving sensor data from plural sensors, including (a) ceiling-mounted cameras that monitor tracks of customers through aisles of the store, and (b) inventory sensors that are positioned to monitor removal of stock from store shelves. This received sensor data is employed in evaluating plural alternate item identification hypotheses. These hypotheses include a first hypothesis that a customer selected an item having a first identity, and a second hypothesis that the customer selected an item having a second identity. A confidence score is associated with each of the first and second item selection hypotheses. These confidence scores are refined as sensor data is received, e.g., increasing a confidence score of one hypothesis, and reducing a confidence score of another.Type: GrantFiled: February 15, 2019Date of Patent: November 12, 2019Assignee: Digimarc CorporationInventors: Bruce L. Davis, Tony F. Rodriguez, Geoffrey B. Rhoads, Eric D. Evans, Rebecca L. Gerlach
-
Publication number: 20190188435Abstract: A variety of technologies having practical application in retail stores are detailed. One is an improved method of identifying items selected by customers. This method includes receiving sensor data from plural sensors, including (a) ceiling-mounted cameras that monitor tracks of customers through aisles of the store, and (b) inventory sensors that are positioned to monitor removal of stock from store shelves. This received sensor data is employed in evaluating plural alternate item identification hypotheses. These hypotheses include a first hypothesis that a customer selected an item having a first identity, and a second hypothesis that the customer selected an item having a second identity. A confidence score is associated with each of the first and second item selection hypotheses. These confidence scores are refined as sensor data is received, e.g., increasing a confidence score of one hypothesis, and reducing a confidence score of another.Type: ApplicationFiled: February 15, 2019Publication date: June 20, 2019Inventors: Bruce L. Davis, Tony F. Rodriguez, Geoffrey B. Rhoads, John D. Lord, Alastair M. Reed, Eric D. Evans, Rebecca L. Gerlach, Yang Bai, John F. Stach, Tomas Filler, Marc G. Footen, Sean Calhoon
-
Patent number: 10192087Abstract: In some arrangements, product packaging is digitally watermarked over most of its extent to facilitate high-throughput item identification at retail checkouts. Imagery captured by conventional or plenoptic cameras can be processed (e.g., by GPUs) to derive several different perspective-transformed views—further minimizing the need to manually reposition items for identification. Crinkles and other deformations in product packaging can be optically sensed, allowing such surfaces to be virtually flattened to aid identification. Piles of items can be 3D-modelled and virtually segmented into geometric primitives to aid identification, and to discover locations of obscured items. Other data (e.g., including data from sensors in aisles, shelves and carts, and gaze tracking for clues about visual saliency) can be used in assessing identification hypotheses about an item. A great variety of other features and arrangements are also detailed.Type: GrantFiled: June 7, 2016Date of Patent: January 29, 2019Assignee: Digimarc CorporationInventors: Bruce L. Davis, Tony F. Rodriguez, Geoffrey B. Rhoads, John D. Lord, Eric D. Evans, Rebecca L. Gerlach, Yang Bai, John Stach
-
Publication number: 20170249491Abstract: In some arrangements, product packaging is digitally watermarked over most of its extent to facilitate high-throughput item identification at retail checkouts. Imagery captured by conventional or plenoptic cameras can be processed (e.g., by GPUs) to derive several different perspective-transformed views—further minimizing the need to manually reposition items for identification. Crinkles and other deformations in product packaging can be optically sensed, allowing such surfaces to be virtually flattened to aid identification. Piles of items can be 3D-modelled and virtually segmented into geometric primitives to aid identification, and to discover locations of obscured items. Other data (e.g., including data from sensors in aisles, shelves and carts, and gaze tracking for clues about visual saliency) can be used in assessing identification hypotheses about an item. Logos may be identified and used—or ignored—in product identification. A great variety of other features and arrangements are also detailed.Type: ApplicationFiled: March 17, 2017Publication date: August 31, 2017Inventors: Brian T. MacIntosh, Tony F. Rodriguez, Bruce L. Davis, Geoffrey B. Rhoads, John D. Lord, Alastair M. Reed, Eric D. Evans, Rebecca L. Gerlach, Yang Bai, John F. Stach, Tomas Filler, Marc G. Footen, Sean Calhoon, William Y. Conwell
-
Publication number: 20160364634Abstract: In some arrangements, product packaging is digitally watermarked over most of its extent to facilitate high-throughput item identification at retail checkouts. Imagery captured by conventional or plenoptic cameras can be processed (e.g., by GPUs) to derive several different perspective-transformed views—further minimizing the need to manually reposition items for identification. Crinkles and other deformations in product packaging can be optically sensed, allowing such surfaces to be virtually flattened to aid identification. Piles of items can be 3D-modelled and virtually segmented into geometric primitives to aid identification, and to discover locations of obscured items. Other data (e.g., including data from sensors in aisles, shelves and carts, and gaze tracking for clues about visual saliency) can be used in assessing identification hypotheses about an item. A great variety of other features and arrangements are also detailed.Type: ApplicationFiled: June 7, 2016Publication date: December 15, 2016Inventors: Bruce L. Davis, Tony F. Rodriguez, Geoffrey B. Rhoads, John D. Lord, Alastair M. Reed, Eric D. Evans, Rebecca L. Gerlach, Yang Bai, John Stach, Tomas Filler, Marc G. Footen, Sean Calhoon
-
Publication number: 20140112524Abstract: In some arrangements, product packaging is digitally watermarked over most of its extent to facilitate high-throughput item identification at retail checkouts. Imagery of such packaging is analyzed to detect digital watermarking. One claim recites a method utilized at a retail checkout location comprising: receiving imagery representing a packaged item from a digital camera, the packaged item including digital watermarking hidden on its packaging, the packaged item moving relative to the digital camera; determining a region in the imagery corresponding to at least one relatively faster moving object; arranging watermark detection blocks over the determine region; an detecting the digital watermarking from the watermark detection blocks. Of course other claims and combinations are also provided.Type: ApplicationFiled: March 14, 2013Publication date: April 24, 2014Inventors: Yang Bai, Alastair M. Reed, Eric D. Evans, Rebecca L. Gerlach, Tomas Filler