Patents by Inventor Christy Fernandez CULL
Christy Fernandez CULL 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: 20250100568Abstract: Embodiments provide a hardware-based mechanism to continuously calibrate a set of sensors on a vehicle while the vehicle is in motion or in use. Specifically, each sensor is mounted on a respective rigid mounting device placed on the vehicle. A secondary sensing device for calibration is also rigidly mounted on the mounting device such that the relative position between the secondary device and the camera sensor can remain unchanged. The secondary sensing devices can then be used to detect a relative distance and/or position of the same calibration target. The sensed data is then used to determine, via stereo triangulation, the relative positions of the two secondary sensing devices, which in turn indicates the relative positions of the sensors.Type: ApplicationFiled: October 10, 2024Publication date: March 27, 2025Inventors: David Tse-Zhou Lu, Christy Fernandez Cull, Luca Del Pero, Jonathan Mazur Dyer, Charles J. Richey
-
Publication number: 20240359703Abstract: In one embodiment, a method includes a computing system obtaining, via one or more sensors of a personal mobile vehicle (PMV), a reflection signal indicating a characteristic of a road surface of an environment external to the PMV. The computing system may determine one or more characteristic factors of the road surface of the environment external to the PMV based on the reflection signal. The computing system may generate a vulnerable road user (VRU) classification probability distribution by using a machine learning classifier. The VRU classification probability distribution indicates whether a combination of the one or more characteristic factors is associated with the VRU. The computing system may determine, based on the VRU classification probability distribution, that the road surface is associated with the VRU. The computing system may present an alert message to a display associated with the PMV.Type: ApplicationFiled: July 11, 2024Publication date: October 31, 2024Inventors: Ashley John Cooper, Alison Marie Thurber, Eahab Nagi El Naga, Christy Fernandez Cull, Abdullah Ahsan Zaidi
-
Patent number: 12128913Abstract: Embodiments provide a hardware-based mechanism to continuously calibrate a set of sensors on a vehicle while the vehicle is in motion or in use. Specifically, each sensor is mounted on a respective rigid mounting device placed on the vehicle. A secondary sensing device for calibration is also rigidly mounted on the mounting device such that the relative position between the secondary device and the camera sensor can remain unchanged. The secondary sensing devices can then be used to detect a relative distance and/or position of the same calibration target. The sensed data is then used to determine, via stereo triangulation, the relative positions of the two secondary sensing devices, which in turn indicates the relative positions of the sensors.Type: GrantFiled: October 20, 2020Date of Patent: October 29, 2024Assignee: Lyft, Inc.Inventors: David Tse-Zhou Lu, Christy Fernandez Cull, Luca Del Pero, Jonathan Mazur Dyer, Charles J Richey
-
Patent number: 12065158Abstract: Commercial personal mobile vehicles (PMVs) managed by a fleet management system are sometimes equipped with a radar sensor to detect objects in an environment external to the PMVs. Specifically, the PMV may be equipped with a variety of sensors, such as a radar, a sonar sensor, a (optional) camera, an inertia measurement unit (IMU), and/or the like. The combination of a radar reflection signal and a sonar signal may provide measurements of characteristics such as a Doppler velocity and height information of a nearby object, which may be input to a machine learning classifier to determine the probability that the nearby object is a VRU. For another example, the reflection pattern from radar and ultrasonic may be used to input to a machine learning classifier to determine a type of the road surface, e.g., an asphalt road surface, a concrete sidewalk surface, a wet-grass lawn surface, and/or the like.Type: GrantFiled: July 7, 2022Date of Patent: August 20, 2024Assignee: Lyft, Inc.Inventors: Ashley John Cooper, Alison Marie Thurber, Eahab Nagi El Naga, Christy Fernandez Cull, Abdullah Ahsan Zaidi
-
Publication number: 20240099656Abstract: An apparatus, and method, for a garment embedded secretion analysis. The system includes a liner that includes at least a sensor from a plurality of sensors. The system also includes a computing device embedded in the liner and communicatively connected to the at least a sensor, where the computing device includes a detection module configured to extract at least a biological sample from the user, authenticate the user as a function of the biological sample and a biological data of the user, detect a condition datum as a function of the biological sample and biological data of the user and determine an event datum as a function of the condition datum. Computing device also includes a safety module configured to receive the event datum and generate an alert datum as a function of the event datum.Type: ApplicationFiled: November 7, 2023Publication date: March 28, 2024Applicant: Davinci Wearables, LLCInventors: Christy Fernandez Cull, Maria Galou Laymeyer, Manisha Mohan
-
Publication number: 20230410629Abstract: An apparatus, and method, for a garment embedded secretion analysis. The system includes a liner that includes at least a sensor from a plurality of sensors. The system also includes a computing device embedded in the liner and communicatively connected to the at least a sensor, where the computing device includes a detection module configured to extract at least a biological sample from the user, authenticate the user as a function of the biological sample and a biological data of the user, detect a condition datum as a function of the biological sample and biological data of the user and determine an event datum as a function of the condition datum. Computing device also includes a safety module configured to receive the event datum and generate an alert datum as a function of the event datum.Type: ApplicationFiled: November 30, 2022Publication date: December 21, 2023Applicant: Davinci Wearables, LLCInventors: Christy Fernandez Cull, Maria Galou Laymeyer, Manisha Mohan
-
Patent number: 11830340Abstract: An apparatus, and method, for a garment embedded secretion analysis. The system includes a liner that includes at least a sensor from a plurality of sensors. The system also includes a computing device embedded in the liner and communicatively connected to the at least a sensor, where the computing device includes a detection module configured to extract at least a biological sample from the user, authenticate the user as a function of the biological sample and a biological data of the user, detect a condition datum as a function of the biological sample and biological data of the user and determine an event datum as a function of the condition datum. Computing device also includes a safety module configured to receive the event datum and generate an alert datum as a function of the event datum.Type: GrantFiled: November 30, 2022Date of Patent: November 28, 2023Assignee: Davinci Wearables, LLCInventors: Christy Fernandez Cull, Maria Galou Laymeyer, Manisha Mohan
-
Publication number: 20230092933Abstract: Commercial personal mobile vehicles (PMVs) managed by a fleet management system are sometimes equipped with a radar sensor to detect objects in an environment external to the PMVs. Specifically, the PMV may be equipped with a variety of sensors, such as a radar, a sonar sensor, a (optional) camera, an inertia measurement unit (IMU), and/or the like. The combination of a radar reflection signal and a sonar signal may provide measurements of characteristics such as a Doppler velocity and height information of a nearby object, which may be input to a machine learning classifier to determine the probability that the nearby object is a VRU. For another example, the reflection pattern from radar and ultrasonic may be used to input to a machine learning classifier to determine a type of the road surface, e.g., an asphalt road surface, a concrete sidewalk surface, a wet-grass lawn surface, and/or the like.Type: ApplicationFiled: July 7, 2022Publication date: March 23, 2023Inventors: Ashley John Cooper, Alison Marie Thurber, Eahab Nagi El Naga, Christy Fernandez Cull, Abdullah Ahsan Zaidi
-
Publication number: 20220118994Abstract: Embodiments provide a hardware-based mechanism to continuously calibrate a set of sensors on a vehicle while the vehicle is in motion or in use. Specifically, each sensor is mounted on a respective rigid mounting device placed on the vehicle. A secondary sensing device for calibration is also rigidly mounted on the mounting device such that the relative position between the secondary device and the camera sensor can remain unchanged. The secondary sensing devices can then be used to detect a relative distance and/or position of the same calibration target. The sensed data is then used to determine, via stereo triangulation, the relative positions of the two secondary sensing devices, which in turn indicates the relative positions of the sensors.Type: ApplicationFiled: October 20, 2020Publication date: April 21, 2022Inventors: David Tse-Zhou Lu, Christy Fernandez Cull, Luca Del Pero, Jonathan Mazur Dyer, Charles J Richey
-
Patent number: 11050963Abstract: Conventional methods for imaging transient targets are constrained by a trade-off between resolution and frame rate, and transient targets moving faster than the detector frame typically result in image blurring. Imagers using digital-pixel focal plane arrays (“DFPAs”) have on-chip global pixel operation capability for extracting a single transient-feature (i.e., single-frequency discrimination) in a snapshot that depends on the number of counters implemented per pixel. However, these DFPA systems are not capable of multi-target and multi-frequency discrimination. Imagers described herein achieve multi-target transient signature discrimination orders of magnitude faster than the readout frame rate using in-pixel electronic shuttering with a known time-encoded modulation. Three-dimensional (x,y,t) data cube reconstruction is performed using compressive sensing algorithms.Type: GrantFiled: March 12, 2020Date of Patent: June 29, 2021Assignee: Massachusetts Institute of TechnologyInventors: Brian M. Tyrrell, Christy Fernandez Cull, Andrew K. Bolstad
-
Publication number: 20200314377Abstract: Conventional methods for imaging transient targets are constrained by a trade-off between resolution and frame rate, and transient targets moving faster than the detector frame typically result in image blurring. Imagers using digital-pixel focal plane arrays (“DFPAs”) have on-chip global pixel operation capability for extracting a single transient-feature (i.e., single-frequency discrimination) in a snapshot that depends on the number of counters implemented per pixel. However, these DFPA systems are not capable of multi-target and multi-frequency discrimination. Imagers described herein achieve multi-target transient signature discrimination orders of magnitude faster than the readout frame rate using in-pixel electronic shuttering with a known time-encoded modulation. Three-dimensional (x,y,t) data cube reconstruction is performed using compressive sensing algorithms.Type: ApplicationFiled: March 12, 2020Publication date: October 1, 2020Inventors: Brian M. TYRRELL, Christy Fernandez CULL, Andrew K. BOLSTAD
-
Patent number: 10616520Abstract: Conventional methods for imaging transient targets are constrained by a trade-off between resolution and frame rate, and transient targets moving faster than the detector frame typically result in image blurring. Imagers using digital-pixel focal plane arrays (“DFPAs”) have on-chip global pixel operation capability for extracting a single transient-feature (i.e., single-frequency discrimination) in a snapshot that depends on the number of counters implemented per pixel. However, these DFPA systems are not capable of multi-target and multi-frequency discrimination. Imagers described herein achieve multi-target transient signature discrimination orders of magnitude faster than the readout frame rate using in-pixel electronic shuttering with a known time-encoded modulation. Three-dimensional (x,y,t) data cube reconstruction is performed using compressive sensing algorithms.Type: GrantFiled: February 25, 2019Date of Patent: April 7, 2020Assignee: Massachusetts Institute of TechnologyInventors: Brian M. Tyrrell, Christy Fernandez Cull, Andrew K. Bolstad
-
Publication number: 20190335129Abstract: Conventional methods for imaging transient targets are constrained by a trade-off between resolution and frame rate, and transient targets moving faster than the detector frame typically result in image blurring. Imagers using digital-pixel focal plane arrays (“DFPAs”) have on-chip global pixel operation capability for extracting a single transient-feature (i.e., single-frequency discrimination) in a snapshot that depends on the number of counters implemented per pixel. However, these DFPA systems are not capable of multi-target and multi-frequency discrimination. Imagers described herein achieve multi-target transient signature discrimination orders of magnitude faster than the readout frame rate using in-pixel electronic shuttering with a known time-encoded modulation. Three-dimensional (x,y,t) data cube reconstruction is performed using compressive sensing algorithms.Type: ApplicationFiled: February 25, 2019Publication date: October 31, 2019Inventors: Brian M. TYRRELL, Christy Fernandez CULL, Andrew K. BOLSTAD
-
Patent number: 10250831Abstract: Conventional methods for imaging transient targets are constrained by a trade-off between resolution and frame rate, and transient targets moving faster than the detector frame typically result in image blurring. Imagers using digital-pixel focal plane arrays (“DFPAs”) have on-chip global pixel operation capability for extracting a single transient-feature (i.e., single-frequency discrimination) in a snapshot that depends on the number of counters implemented per pixel. However, these DFPA systems are not capable of multi-target and multi-frequency discrimination. Imagers described herein achieve multi-target transient signature discrimination orders of magnitude faster than the readout frame rate using in-pixel electronic shuttering with a known time-encoded modulation. Three-dimensional (x,y,t) data cube reconstruction is performed using compressive sensing algorithms.Type: GrantFiled: August 16, 2017Date of Patent: April 2, 2019Assignee: MASSACHUSETTS INSTITUTE OF TECHNOLOGYInventors: Brian M. Tyrrell, Christy Fernandez Cull, Andrew K. Bolstad
-
Publication number: 20180035067Abstract: Conventional methods for imaging transient targets are constrained by a trade-off between resolution and frame rate, and transient targets moving faster than the detector frame typically result in image blurring. Imagers using digital-pixel focal plane arrays (“DFPAs”) have on-chip global pixel operation capability for extracting a single transient-feature (i.e., single-frequency discrimination) in a snapshot that depends on the number of counters implemented per pixel. However, these DFPA systems are not capable of multi-target and multi-frequency discrimination. Imagers described herein achieve multi-target transient signature discrimination orders of magnitude faster than the readout frame rate using in-pixel electronic shuttering with a known time-encoded modulation. Three-dimensional (x,y,t) data cube reconstruction is performed using compressive sensing algorithms.Type: ApplicationFiled: August 16, 2017Publication date: February 1, 2018Inventors: Brian M. TYRRELL, Christy Fernandez CULL, Andrew K. BOLSTAD
-
Patent number: 9743024Abstract: Conventional methods for imaging transient targets are constrained by a trade-off between resolution and frame rate, and transient targets moving faster than the detector frame typically result in image blurring. Imagers using digital-pixel focal plane arrays (“DFPAs”) have on-chip global pixel operation capability for extracting a single transient-feature (i.e., single-frequency discrimination) in a snapshot that depends on the number of counters implemented per pixel. However, these DFPA systems are not capable of multi-target and multi-frequency discrimination. Imagers described herein achieve multi-target transient signature discrimination orders of magnitude faster than the readout frame rate using in-pixel electronic shuttering with a known time-encoded modulation. Three-dimensional (x,y,t) data cube reconstruction is performed using compressive sensing algorithms.Type: GrantFiled: July 1, 2015Date of Patent: August 22, 2017Assignee: Massachusetts Institute of TechnologyInventors: Brian M. Tyrrell, Christy Fernandez Cull, Andrew K. Bolstad
-
Publication number: 20170041571Abstract: Conventional methods for imaging transient targets are constrained by a trade-off between resolution and frame rate, and transient targets moving faster than the detector frame typically result in image blurring. Imagers using digital-pixel focal plane arrays (“DFPAs”) have on-chip global pixel operation capability for extracting a single transient-feature (i.e., single-frequency discrimination) in a snapshot that depends on the number of counters implemented per pixel. However, these DFPA systems are not capable of multi-target and multi-frequency discrimination. Imagers described herein achieve multi-target transient signature discrimination orders of magnitude faster than the readout frame rate using in-pixel electronic shuttering with a known time-encoded modulation. Three-dimensional (x,y,t) data cube reconstruction is performed using compressive sensing algorithms.Type: ApplicationFiled: July 1, 2015Publication date: February 9, 2017Inventors: Brian M. TYRRELL, Christy Fernandez CULL, Andrew K. BOLSTAD