-
公开(公告)号:US11954900B2
公开(公告)日:2024-04-09
申请号:US18461746
申请日:2023-09-06
Inventor: Gregory Welch , Gerd Bruder , Ryan Schubert , Austin Erickson
IPC: G06V10/70 , G06T3/4038 , G06T7/73 , G06V10/77 , G06V10/774
CPC classification number: G06V10/774 , G06T3/4038 , G06T7/73 , G06V10/70 , G06V10/77 , G05B2219/2642 , G06T2207/20 , G06T2207/20081
Abstract: The invention pertains to methods for monitoring the operational status of a home automation system through extrinsic visual and audible means. Initial training periods involve capturing image and audio data representative of nominal operation, which is then processed to identify operational indicators. Unsupervised machine learning models are trained with these indicators to construct a model of normalcy and identify expectation violations in the system's operational pattern. After meeting specific stopping criteria, real-time monitoring is initiated. When an expectation violation is detected, contrastive collages or sequences are generated comprising nominal and anomalous data. These are then transmitted to an end user, effectively conveying the context of the detected anomalies. Further features include providing deep links to smartphone applications for home automation configuration and the use of auditory scene analysis techniques. The invention provides a multi-modal approach to home automation monitoring, leveraging machine learning for robust anomaly detection.
-
公开(公告)号:US20220101490A1
公开(公告)日:2022-03-31
申请号:US17330679
申请日:2021-05-26
Inventor: Gerd Bruder , Gregory Welch , Kangsoo Kim , Zubin Choudhary
IPC: G06T3/40 , G06V10/764 , G06T7/194
Abstract: One or more cameras capture objects at a higher resolution than the human eye can perceive. Objects are segmented from the background of the image and scaled to human perceptible size. The scaled-up objects are superimposed over the unscaled background. This is presented to a user via an augmented reality display whereby the process selectively amplifies the size of the objects' spatially registered retinal projection while maintaining a natural (unmodified) view in the remainder of the visual field.
-
公开(公告)号:US11287971B1
公开(公告)日:2022-03-29
申请号:US17387219
申请日:2021-07-28
Inventor: Gregory Welch , Ryan McMahan , Gerd Bruder
IPC: G06F3/0488 , G06F3/0484 , G06F3/01 , G06F3/04883 , G06F3/04842
Abstract: A system for remote tactile telepresence wherein tactile telepresence sessions are time-coded along with audiovisual content wherein playback is heard, seen, and felt. Embodiments associate motion capture with the tactile profile so that remote, haptic recipients may see renderings of objects (e.g., hands) imparting vibrotactile sensations.
-
公开(公告)号:US11106357B1
公开(公告)日:2021-08-31
申请号:US17175949
申请日:2021-02-15
Inventor: Gregory Welch , Ryan McMahan , Gerd Bruder
IPC: G06F3/0488 , G06F3/01 , G06F3/0484
Abstract: A system for remote tactile telepresence wherein an array of predefined touch gestures are abstracted into cataloged values and invoked either by pattern matching, by assigned name or visual indicia. A local and remote cache of the catalog reduces latency even for complicated gestures as only a gesture identifier needs to be transmitted to a haptic output destination. Additional embodiments translate gestures to different haptic device affordances. Tactile telepresence sessions are time-coded along with audiovisual content wherein playback is heard, seen, and felt. Another embodiment associates motion capture associated with the tactile profile so that remote, haptic recipients may see renderings of objects (e.g., hands) imparting vibrotactile sensations.
-
公开(公告)号:US20240069516A1
公开(公告)日:2024-02-29
申请号:US18240731
申请日:2023-08-31
Inventor: Gregory Welch , Gerd Bruder , Ryan Schubert , Austin Erickson
IPC: G05B19/042
CPC classification number: G05B19/0428 , G05B2219/2642
Abstract: The invention pertains to methods for monitoring the operational status of a home automation system through extrinsic visual and audible means. Initial training periods involve capturing image and audio data representative of nominal operation, which is then processed to identify operational indicators. Unsupervised machine learning models are trained with these indicators to construct a model of normalcy and identify expectation violations in the system's operational pattern. After meeting specific stopping criteria, real-time monitoring is initiated. When an expectation violation is detected, contrastive collages or sequences are generated comprising nominal and anomalous data. These are then transmitted to an end user, effectively conveying the context of the detected anomalies. Further features include providing deep links to smartphone applications for home automation configuration and the use of auditory scene analysis techniques. The invention provides a multi-modal approach to home automation monitoring, leveraging machine learning for robust anomaly detection.
-
公开(公告)号:US20230056988A1
公开(公告)日:2023-02-23
申请号:US17891754
申请日:2022-08-19
Inventor: Gregory Welch , Matthew Gottsacker , Nahal Norouzi , Gerd Bruder
IPC: H04N21/262 , H04N21/235
Abstract: The present invention is a system to manage interrupt notifications on an operating system based on the characteristics of content in which an end user is currently immersed or engaged. For example, relatively high bitrate video throughput is indicative of corresponding high information depth and more action occurring in the scene. For periods of high information depth, interrupt notifications are deferred until the information depth falls into a relative trough. Additional embodiments of the invention process scene transitions, technical cues, dialog and lyrics to release queued interrupt notification at optimal times. A vamping process is also provided when interrupt notification are released to keep the end user prescient to the background application in which they were engaged prior to the interrupt notification coming into focus.
-
公开(公告)号:US11550470B2
公开(公告)日:2023-01-10
申请号:US17649229
申请日:2022-01-28
Inventor: Gregory Welch , Ryan McMahan , Gerd Bruder
IPC: G06F3/04883 , G06F3/04842 , G06F3/01
Abstract: A system for translating text streams of alphanumeric characters into preconfigured, haptic output. Text strings are parsed against a grammar index to locate assigned haptic or vibratory output. This may include speech-to-text, chat messaging, or text arrays of any kind. When a match is located, a standardized haptic output pattern is invoked through a haptic device. A device affordance module adapts the haptic output pattern to the capabilities of the target haptic device.
-
公开(公告)号:US11467399B2
公开(公告)日:2022-10-11
申请号:US17324198
申请日:2021-05-19
Inventor: Gregory Welch , Gerd Bruder
Abstract: This invention relates to tracking of hand-held devices and vehicles with respect to each other, in circumstances where there are two or more users or existent objects interacting in the same share space (co-location). It extends conventional global and body-relative approaches to “cooperatively” estimate the relative poses between all useful combinations of user-worn tracked devices such as HMDs and hand-held controllers worn (or held) by multiple users. Additionally, the invention provides for tracking of vehicles such as cars and unmanned aerial vehicles.
-
公开(公告)号:US20200043375A1
公开(公告)日:2020-02-06
申请号:US16538212
申请日:2019-08-12
Inventor: Gregory Welch , Arjun Nagendran , Mary Lou Sole , Laura Gonzalez
Abstract: A patient simulation system for healthcare training is provided. The system includes one or more interchangeable shells comprising a physical anatomical model of at least a portion of a patient's body, the shell adapted to be illuminated from behind to provide one or more dynamic images viewable on the outer surface of the shells; a support system adapted to receive the shells via a mounting system, wherein the system comprises one or more image units adapted to render the one or more dynamic images viewable on the outer surface of the shells; one or more interface devices located about the patient shells to receive input and provide output; and one or more computing units in communication with the image units and interface devices, the computing units adapted to provide an interactive simulation for healthcare training.
-
公开(公告)号:US20250008290A1
公开(公告)日:2025-01-02
申请号:US18756382
申请日:2024-06-27
Inventor: Gregory Welch , Gerd Bruder , Zubin Choudhary
IPC: H04S7/00 , G08G1/0967 , G10K15/02 , H04R5/033
Abstract: The invention provides a system for generating spatially explicit auditory cues for a recipient. It includes a processor to receive real-time location data of multiple physical entities relative to the recipient's spatial position and visual orientation. An audio generation module transforms this data into distinct audio signals using Head-Related Transfer Functions (HRTFs) to simulate perceived direction and distance. The output device, such as a headset or vehicle speakers, presents these audio signals spatially to allow perception of entities' relative locations. The system can adjust volume based on entity distance, integrate Doppler effects to indicate motion, and mute entities outside predefined distance boundaries. It also supports above-ground and ground assets, with altitude information converted to audible cues. The system monitors the recipient's orientation in real-time to adjust the HRTFs accordingly.
-
-
-
-
-
-
-
-
-