Patents by Inventor Alireza Dehghani
Alireza Dehghani 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: 20240128998Abstract: A system and associated method transfer power between a DC source and a variable load. Two power signals are extracted from the DC source at HF frequency via two self-synchronous radio frequency rectifiers/amplifiers switched by two corresponding HF switching signals having between them either a frequency difference or a phase difference controlled by a duty cycle and overlap controller. The two HF power signals are mixed in a wired, wireless, or bimodal wireless HF power link system to produce a transferred power signal based on the mixing and on manipulating the phase difference when present. A power signal conversion circuit in communication with the HF power link system produces an unfolded output power signal from the transferred power signal. The system and method allow transfer to the load of at least one of an adjustable DC power signal and an AC power signal phase locked to an existing power signal in the load.Type: ApplicationFiled: September 27, 2023Publication date: April 18, 2024Inventors: Soroush Dehghani MOHAMMADABADI, Mohammadjavad SHARIATZADEH, Ehsan Hadizadeh HAFSHEJANI, Ehud DAON, Alireza ASOODEH
-
Publication number: 20230237791Abstract: Disclosed examples include accessing sensor data; recognizing, by executing an instruction with programmable circuitry, a feature in the sensor data based on a convolutional neural network; and transitioning, by executing an instruction with the programmable circuitry, a mobile device between at least two of motion feature detection, audio feature detection, or camera feature detection after the feature is recognized in the sensor data, the mobile device to operate at a different level of power consumption after the transition than before the transition.Type: ApplicationFiled: March 31, 2023Publication date: July 27, 2023Inventors: David Moloney, Alireza Dehghani
-
Patent number: 11625910Abstract: A disclosed example to operate a mobile camera includes recognizing a first feature in first sensor data in response to the first feature being detected in the first sensor data; transitioning the mobile camera from a first feature detection state to a second feature detection state in response to the recognizing of the first feature, the mobile camera to operate using higher power consumption in second feature detection state than in the first feature detection state; recognizing a second feature in second sensor data in the second feature detection state; and sending to an external device at least one of first metadata corresponding to the first feature or second metadata corresponding to the second feature.Type: GrantFiled: December 13, 2021Date of Patent: April 11, 2023Assignee: MOVIDIUS LIMITEDInventors: David Moloney, Alireza Dehghani
-
Patent number: 11600059Abstract: Systems and methods are provided for image classification using histograms of oriented gradients (HoG) in conjunction with a trainer. The efficiency of the process is greatly increased by first establishing a bitmap which identifies a subset of the pixels in the HoG window as including relevant foreground information, and limiting the HoG calculation and comparison process to only the pixels included in the bitmap.Type: GrantFiled: June 8, 2021Date of Patent: March 7, 2023Assignee: Movidius LimitedInventors: David Moloney, Alireza Dehghani
-
Publication number: 20220174215Abstract: A disclosed example to operate a mobile camera includes recognizing a first feature in first sensor data in response to the first feature being detected in the first sensor data; transitioning the mobile camera from a first feature detection state to a second feature detection state in response to the recognizing of the first feature, the mobile camera to operate using higher power consumption in second feature detection state than in the first feature detection state; recognizing a second feature in second sensor data in the second feature detection state; and sending to an external device at least one of first metadata corresponding to the first feature or second metadata corresponding to the second feature.Type: ApplicationFiled: December 13, 2021Publication date: June 2, 2022Inventors: David Moloney, Alireza Dehghani
-
Patent number: 11240430Abstract: A disclosed example to operate a mobile camera includes recognizing a first feature in first sensor data in response to the first feature being detected in the first sensor data; transitioning the mobile camera from a first feature detection state to a second feature detection state in response to the recognizing of the first feature, the mobile camera to operate using higher power consumption in second feature detection state than in the first feature detection state; recognizing a second feature in second sensor data in the second feature detection state; and sending to an external device at least one of first metadata corresponding to the first feature or second metadata corresponding to the second feature.Type: GrantFiled: January 17, 2020Date of Patent: February 1, 2022Assignee: MOVIDIUS LTD.Inventors: David Moloney, Alireza Dehghani
-
Publication number: 20210374464Abstract: Systems and methods are provided for image classification using histograms of oriented gradients (HoG) in conjunction with a trainer. The efficiency of the process is greatly increased by first establishing a bitmap which identifies a subset of the pixels in the HoG window as including relevant foreground information, and limiting the HoG calculation and comparison process to only the pixels included in the bitmap.Type: ApplicationFiled: June 8, 2021Publication date: December 2, 2021Inventors: David Moloney, Alireza Dehghani
-
Publication number: 20210182595Abstract: Methods, systems, apparatus and articles of manufacture are disclosed herein to improve image classification with boundary-bitmaps. An example disclosed apparatus includes a silhouette engine to identify a foreground silhouette within the image, generate a bounding box based on borders of the foreground silhouette, and generate an encoded silhouette matrix which identifies cells of a foreground and cells of a background, a convolution cell selector to convolve the encoded silhouette matrix to generate a convoluted bitmap matrix, and a filter cell selector to improve image classification efficiency by identifying eligible blocks of the convoluted bitmap matrix by retaining first respective cells of the convoluted bitmap matrix that satisfy a cell retention threshold, and removing second respective cells of the convoluted bitmap matrix that do not satisfy the cell retention threshold.Type: ApplicationFiled: February 24, 2021Publication date: June 17, 2021Inventors: David Moloney, Alireza Dehghani
-
Patent number: 11037020Abstract: Systems and methods are provided for image classification using histograms of oriented gradients (HoG) in conjunction with a trainer. The efficiency of the process is greatly increased by first establishing a bitmap which identifies a subset of the pixels in the HoG window as including relevant foreground information, and limiting the HoG calculation and comparison process to only the pixels included in the bitmap.Type: GrantFiled: February 8, 2019Date of Patent: June 15, 2021Assignee: MOVIDIUS LIMITEDInventors: David Moloney, Alireza Dehghani
-
Patent number: 10936899Abstract: Methods, systems, apparatus and articles of manufacture are disclosed herein to improve image classification with boundary-bitmaps. An example disclosed apparatus includes a silhouette engine to identify a foreground silhouette within the image, generate a bounding box based on borders of the foreground silhouette, and generate an encoded silhouette matrix which identifies cells of a foreground and cells of a background, a convolution cell selector to convolve the encoded silhouette matrix to generate a convoluted bitmap matrix, and a filter cell selector to improve image classification efficiency by identifying eligible blocks of the convoluted bitmap matrix by retaining first respective cells of the convoluted bitmap matrix that satisfy a cell retention threshold, and removing second respective cells of the convoluted bitmap matrix that do not satisfy the cell retention threshold.Type: GrantFiled: June 6, 2017Date of Patent: March 2, 2021Inventors: David Moloney, Alireza Dehghani
-
Publication number: 20200396383Abstract: A disclosed example to operate a mobile camera includes recognizing a first feature in first sensor data in response to the first feature being detected in the first sensor data; transitioning the mobile camera from a first feature detection state to a second feature detection state in response to the recognizing of the first feature, the mobile camera to operate using higher power consumption in second feature detection state than in the first feature detection state; recognizing a second feature in second sensor data in the second feature detection state; and sending to an external device at least one of first metadata corresponding to the first feature or second metadata corresponding to the second feature.Type: ApplicationFiled: January 17, 2020Publication date: December 17, 2020Inventors: David Moloney, Alireza Dehghani
-
Patent number: 10574890Abstract: An example mobile camera includes a first convolutional neural network to recognize a first feature in first sensor data in response to the first feature being detected in the first sensor data; a state transitioner to transition the mobile camera from a first feature detection state to a second feature detection state in response to the first convolutional neural network recognizing the first feature, the mobile camera to operate using higher power consumption in the second feature detection state than in the first feature detection state; a second convolutional neural network to recognize a second feature in second sensor data in the second feature detection state; and a communications interface to send to an external device at least one of first metadata corresponding to the first feature or second metadata corresponding to the second feature.Type: GrantFiled: January 12, 2018Date of Patent: February 25, 2020Assignee: Movidius Ltd.Inventors: David Moloney, Alireza Dehghani
-
Publication number: 20190340464Abstract: Systems and methods are provided for image classification using histograms of oriented gradients (HoG) in conjunction with a trainer. The efficiency of the process is greatly increased by first establishing a bitmap which identifies a subset of the pixels in the HoG window as including relevant foreground information, and limiting the HoG calculation and comparison process to only the pixels included in the bitmap.Type: ApplicationFiled: February 8, 2019Publication date: November 7, 2019Inventors: David MOLONEY, Alireza DEHGHANI
-
Publication number: 20190279082Abstract: An example includes sending first weight values to first client devices; accessing sets of updated weight values provided by the first client devices, the updated weight values generated by the first client devices training respective first convolutional neural networks (CNNs) based on: the first weight values, and sensor data generated at the client devices; testing performance in a second CNN of at least one of: the sets of the updated weight values, or a combination of ones of the updated weight values from the sets of the updated weight values; selecting server-synchronized weight (SSW) values from the at least one of: the sets of the updated weight values, or a combination of ones of the updated weight values from the sets of the updated weight values; and sending the SSW values to at least one of: at least some of the first client devices, or second client devices.Type: ApplicationFiled: March 7, 2018Publication date: September 12, 2019Inventors: David Moloney, Alireza Dehghani, Aubrey Keith Dunne
-
Publication number: 20190222756Abstract: An example mobile camera includes a first convolutional neural network to recognize a first feature in first sensor data in response to the first feature being detected in the first sensor data; a state transitioner to transition the mobile camera from a first feature detection state to a second feature detection state in response to the first convolutional neural network recognizing the first feature, the mobile camera to operate using higher power consumption in the second feature detection state than in the first feature detection state; a second convolutional neural network to recognize a second feature in second sensor data in the second feature detection state; and a communications interface to send to an external device at least one of first metadata corresponding to the first feature or second metadata corresponding to the second feature.Type: ApplicationFiled: January 12, 2018Publication date: July 18, 2019Inventors: David Moloney, Alireza Dehghani
-
Publication number: 20190156141Abstract: Methods, systems, apparatus and articles of manufacture are disclosed herein to improve image classification with boundary-bitmaps. An example disclosed apparatus includes a silhouette engine to identify a foreground silhouette within the image, generate a bounding box based on borders of the foreground silhouette, and generate an encoded silhouette matrix which identifies cells of a foreground and cells of a background, a convolution cell selector to convolve the encoded silhouette matrix to generate a convoluted bitmap matrix, and a filter cell selector to improve image classification efficiency by identifying eligible blocks of the convoluted bitmap matrix by retaining first respective cells of the convoluted bitmap matrix that satisfy a cell retention threshold, and removing second respective cells of the convoluted bitmap matrix that do not satisfy the cell retention threshold.Type: ApplicationFiled: June 6, 2017Publication date: May 23, 2019Applicant: Linear Algebra Technologies LimitedInventors: David Moloney, Alireza Dehghani
-
Patent number: 10248884Abstract: Systems and methods are provided for image classification using histograms of oriented gradients (HoG) in conjunction with a trainer. The efficiency of the process is greatly increased by first establishing a bitmap which identifies a subset of the pixels in the HoG window as including relevant foreground information, and limiting the HoG calculation and comparison process to only the pixels included in the bitmap.Type: GrantFiled: April 10, 2017Date of Patent: April 2, 2019Assignee: Linear Algebra Technologies LimitedInventors: David Moloney, Alireza Dehghani
-
Publication number: 20170277972Abstract: Systems and methods are provided for image classification using histograms of oriented gradients (HoG) in conjunction with a trainer. The efficiency of the process is greatly increased by first establishing a bitmap which identifies a subset of the pixels in the HoG window as including relevant foreground information, and limiting the HoG calculation and comparison process to only the pixels included in the bitmap.Type: ApplicationFiled: April 10, 2017Publication date: September 28, 2017Inventors: David MOLONEY, Alireza DEHGHANI
-
Patent number: 9639777Abstract: Systems and methods are provided for image classification using histograms of oriented gradients (HoG) in conjunction with a trainer. The efficiency of the process is greatly increased by first establishing a bitmap which identifies a subset of the pixels in the HoG window as including relevant foreground information, and limiting the HoG calculation and comparison process to only the pixels included in the bitmap.Type: GrantFiled: December 17, 2015Date of Patent: May 2, 2017Assignee: LINEAR ALGEBRA TECHNOLOGIES LIMITEDInventors: David Moloney, Alireza Dehghani