Patents by Inventor Tom TABAK
Tom TABAK 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: 20250225770Abstract: A method for autonomous enriching reference information, including (a) obtaining a current group of trusted reference images of non-anomalous instances of an item: (b) calculating reference pixel-wise distribution information: (c) obtaining multiple sets of item instance pixels from current acquired images of instances of the item, each set originated from an image of an instance of the item and comprises multiple item instance pixels: (d) determining item features of the item for each set, based on the multiple item pixels of the set and by a non-item specific neural network: (e) determining a pixel score for item pixels of the multiple item pixels: (f) calculating a distance between the pixel score and the reference pixel-wise distribution information; and (g) selecting at least one current acquired image to add to the trusted reference images, based on at least one distance of at least one pixel per current acquired image.Type: ApplicationFiled: April 5, 2023Publication date: July 10, 2025Applicant: AI QUALISENSE 2021 LTDInventors: Tom TABAK, Zvi Lapp
-
Patent number: 12340596Abstract: A method for lane boundary detection, the method may include obtaining an image of an environment of a vehicle, the environment comprises at least one lane boundary portions; wherein the image comprises a first plurality of two dimensional (2D) image segments; converting, by a first machine learning process, each of the 2D segments to a segment vector to provide a first plurality of segment vectors; wherein each segment vector represents a 2D segment; finding an associated cluster for each segment vector to provide a second plurality of associated clusters; searching for at least one LBR cluster of the second plurality of associated clusters; and determining, for each LBR segment vector and by a second machine learning process, a location of a lane boundary portion within a 2D image segment that is represented by the LBR segment vector; wherein a LBR segment vector has an associated cluster that is a LBR cluster.Type: GrantFiled: October 11, 2022Date of Patent: June 24, 2025Assignee: AUTOBRAINS TECHNOLOGIES LTDInventor: Tom Tabak
-
Patent number: 12322110Abstract: A method for neural network based image processing, the method may include obtaining multiple two dimensional (2D) segments of a sensed information unit, each 2D segment has a segment location within the sensed information unit; converting each 2D segments to a segment vector; generating multiple segments intermediate results by repeating, for each segment vector: (a) concatenating the segment vector with associated segment location information to provide a first segment concatenated vector; and (b) multiplying the first segment concatenated vector by a learnable embedding matrix to provide a segment intermediate result; concatenating the multiple segments intermediate results with associated segment identifiers to provide a sensed information unit result; and feeding the sensed information unit result to a second layer of a neural network.Type: GrantFiled: October 11, 2022Date of Patent: June 3, 2025Assignee: AUTOBRAINS TECHNOLOGIES LTDInventor: Tom Tabak
-
Patent number: 12159466Abstract: A method for context based lane prediction, the method may include obtaining sensed information regarding an environment of the vehicle; providing the sensed information to a second trained machine learning process; and locating one or more lane boundaries by the second trained machine learning process. The second trained machine learning process is generated by: performing a self-supervised training process, using a first dataset, of a first machine learning process to provide a first trained machine learning process; wherein the first trained machine learning process comprises a first encoder portion and a first decoder portion; replacing the first decoder portion by a second decoder portion to provide a second machine learning process; and performing an additional training process, using a second dataset that is associated with lane boundary metadata, of the second machine learning process to provide a second trained machine learning process.Type: GrantFiled: June 7, 2022Date of Patent: December 3, 2024Assignee: AUTOBRAINS TECHNOLOGIES LTDInventor: Tom Tabak
-
Publication number: 20240290069Abstract: A method for cluster-based and autonomous finding of reference information, the method may include obtaining a group of untagged images, each untagged image captures an instance of an item; wherein at least some of the untagged images capture different instances of the item; obtaining multiple sets of item pixels from the untagged images of the group, each set originated from an untagged image of the group and comprises multiple item pixels; determining item features of the item for each set, based on the multiple item pixels of the set and; repeating, until reaching an end condition the steps of: (a) selecting some of the sets as centroids; (b) clustering the item features of the some of the sets to provide clusters, wherein the clustering is based, at least in part, on the centroids; and (c) removing members of a cluster that has less members than another cluster; and defining untagged images that are associated with a member of any remaining cluster as reference images or as reference image candidates.Type: ApplicationFiled: February 28, 2023Publication date: August 29, 2024Applicant: LEAN AI TECHNOLOGIES LTD.Inventor: Tom TABAK
-
Publication number: 20240075925Abstract: A method for steering assistance, the method may include obtaining by vehicle camera, an image of an environment of the vehicle; feeding the image to a machine learning process; outputting, by the machine learning process, road line metadata that comprises a line offset value, a line angle value, a line curvature value and a line curvature rate; and preforming a steering related response to the road line metadata.Type: ApplicationFiled: September 5, 2023Publication date: March 7, 2024Applicant: AUTOBRAINS TECHNOLOGIES LTDInventors: JONATHAN COHEN, Tom TABAK
-
Publication number: 20230274415Abstract: A method for unsupervised learning based anomaly detection of manufactured items, the method may include: obtaining multiple item pixels of an item; determining item features of the item, based on the multiple item pixels and by a non-item specific neural network, the non-item specific neural network is pre-trained to perform feature extraction of objects, at least some of the objects differ from the item; determining, based on the item features, a pixel score for item pixels of the multiple item pixels; for each of the item pixels, calculating a distance between the pixel score and reference pixel-wise distribution information; and for each of the item pixels, determining whether the item pixel is an anomaly pixel based on a comparison between the pixel score and a pixel-wise threshold.Type: ApplicationFiled: February 28, 2023Publication date: August 31, 2023Applicant: LEAN AI TECHNOLOGIES LTD.Inventors: Tom TABAK, Zvi Lapp
-
Publication number: 20230119374Abstract: A method for neural network based image processing, the method may include obtaining multiple two dimensional (2D) segments of a sensed information unit, each 2D segment has a segment location within the sensed information unit; converting each 2D segments to a segment vector; generating multiple segments intermediate results by repeating, for each segment vector: (a) concatenating the segment vector with associated segment location information to provide a first segment concatenated vector; and (b) multiplying the first segment concatenated vector by a learnable embedding matrix to provide a segment intermediate result; concatenating the multiple segments intermediate results with associated segment identifiers to provide a sensed information unit result; and feeding the sensed information unit result to a second layer of a neural network.Type: ApplicationFiled: October 11, 2022Publication date: April 20, 2023Applicant: AUTOBRAINS TECHNOLOGIES LTDInventor: Tom TABAK
-
Publication number: 20230114215Abstract: A method for lane boundary detection, the method may include obtaining an image of an environment of a vehicle, the environment comprises at least one lane boundary portions; wherein the image comprises a first plurality of two dimensional (2D) image segments; converting, by a first machine learning process, each of the 2D segments to a segment vector to provide a first plurality of segment vectors; wherein each segment vector represents a 2D segment; finding an associated cluster for each segment vector to provide a second plurality of associated clusters; searching for at least one LBR cluster of the second plurality of associated clusters; and determining, for each LBR segment vector and by a second machine learning process, a location of a lane boundary portion within a 2D image segment that is represented by the LBR segment vector; wherein a LBR segment vector has an associated cluster that is a LBR cluster.Type: ApplicationFiled: October 11, 2022Publication date: April 13, 2023Applicant: AUTOBRAINS TECHNOLOGIES LTDInventor: Tom TABAK
-
Publication number: 20230045885Abstract: A method for context based lane prediction, the method may include obtaining sensed information regarding an environment of the vehicle; providing the sensed information to a second trained machine learning process; and locating one or more lane boundaries by the second trained machine learning process. The second trained machine learning process is generated by: performing a self-supervised training process, using a first dataset, of a first machine learning process to provide a first trained machine learning process; wherein the first trained machine learning process comprises a first encoder portion and a first decoder portion; replacing the first decoder portion by a second decoder portion to provide a second machine learning process; and performing an additional training process, using a second dataset that is associated with lane boundary metadata, of the second machine learning process to provide a second trained machine learning process.Type: ApplicationFiled: June 7, 2022Publication date: February 16, 2023Applicant: AUTOBRAINS TECHNOLOGIES LTDInventor: Tom TABAK