-
21.发明公开公开(公告)号：US20240119702A1
公开(公告)日：2024-04-11
申请号：US17961230
申请日：2022-10-06
Applicant: Insight Direct USA, Inc.
Inventor： Amol Ajgaonkar
IPC: G06V10/764 , G06N5/04 , G06N20/00
CPC classification number: G06V10/764 , G06N5/04 , G06N20/00
Abstract: A method of obtaining images and data to train an AI model for product detection includes generating, with an image collection system at a first product source, a first annotation package including one or more images of and data about a first product. The first product is placed in a first enclosure located at the first product source. A process for obtaining the one or more images of the first product is initiated in the first enclosure. The one or more images of the first product is obtained with one or more cameras positioned in the first enclosure. The one or more images of the first product is provided to an edge compute device. Data about the first product is input, using an input device, into the edge compute device. An annotation package for the first product is created that includes the one or more images and the data.
-
公开(公告)号：US20240103822A1
公开(公告)日：2024-03-28
申请号：US17953842
申请日：2022-09-27
Applicant: Insight Direct USA, Inc.
Inventor： Amol Ajgaonkar
IPC: G06F8/61 , H04L41/0695
CPC classification number: G06F8/61 , H04L41/0695
Abstract: Apparatus and associated methods relate to automating building of a software solution that is cooperatively performed. A broadcasting computing entity selects a functional operation from a set of one or more functional operations associated with the software solution and then broadcasts a request to perform the functional operation selected. Each of a plurality of listening computing entities connected to the network receives the request to perform the functional operation and determines capability of performing the functional operation. A capable one of the plurality of listening computing entities that determines itself capable of performing the functional operation transmits a response to the request received indicating capability of performing the functional operation and performs the functional operation, thereby generating the output of the functional operation, which is transmitted to the broadcasting computing entity. The broadcasting computing entity then performs an action using the output of the functional operation received.
-
公开(公告)号：US20240103819A1
公开(公告)日：2024-03-28
申请号：US17953850
申请日：2022-09-27
Applicant: Insight Direct USA, Inc.
Inventor： Amol Ajgaonkar
IPC: G06F8/41
CPC classification number: G06F8/41
Abstract: A build of a software solution that is cooperatively performed is automated. A broadcasting computing entity selects a selected set of functional operations from one or more sets of functional operations associated with the software solution and then broadcasts a request to perform each of the functional operations in the selected set. Each of a plurality of listening computing entities connected to the network receives the request and determines capability of performing each of the functional operations in the selected set. After determining itself capable, a capable one of the plurality of listening computing entities transmits a response to the request indicating such capability, and then performs each of the functional operations in the selected set, thereby generating and transmitting to the broadcasting computing entity the output of the selected set of functional operations. The broadcasting computing entity then performs an action using the output of the functional operation received.
-
公开(公告)号：US20240040108A1
公开(公告)日：2024-02-01
申请号：US18221561
申请日：2023-07-13
Applicant: Insight Direct USA, Inc.
Inventor： Amol Ajgaonkar
IPC: H04N17/00 , G11B27/031
CPC classification number: H04N17/00 , G11B27/031
Abstract: A method of improving a main output of a main processing application processing first video data includes analyzing incoming video data via a first processing pipeline and analyzing incoming video data via a second processing pipeline. The second processing pipeline includes identifying, by a parameter optimization module, first test preprocessing parameters; preprocessing the incoming video data according to the first test preprocessing parameters, wherein the first test preprocessing includes formatting the incoming video data to create first test video data; processing the first test video data by a test processing application to determine a first test output that is indicative of a first test inference dependent upon the first test video data; and comparing the first test output and the main output to a baseline criterion. In response to the first test output satisfying the baseline criterion, the parameter optimization module can alter the first preprocessing parameters to be similar to the first test preprocessing parameters.
-
25.发明公开公开(公告)号：US20240037915A1
公开(公告)日：2024-02-01
申请号：US17873780
申请日：2022-07-26
Applicant: Insight Direct USA, Inc.
Inventor： Amol Ajgaonkar
IPC: G06V10/774 , G06V20/40 , G06T5/00 , G06T5/30 , G06N5/04
CPC classification number: G06V10/774 , G06V20/40 , G06T5/001 , G06T5/009 , G06T5/30 , G06N5/04 , G06T2207/10016
Abstract: A method of improving a main output of a main AI model [language will be added when claims are finalized]
-
Patent Agency Ranking
公开(公告)号：US12260195B2
公开(公告)日：2025-03-25
申请号：US18675387
申请日：2024-05-28
Applicant: Insight Direct USA, Inc.
Inventor： Amol Ajgaonkar
IPC: G06F8/41
Abstract: A build of a software solution that is cooperatively performed is automated. A broadcasting computing entity broadcasts a request to perform each of the functional operations in the selected set. Each of a plurality of listening computing entities connected to the network receives the request and determines capability of performing each of the functional operations in the selected set. After determining itself capable, a capable one of the plurality of listening computing entities transmits a response to the request indicating such capability, and then performs each of the functional operations in the selected set, thereby generating and transmitting to the broadcasting computing entity the output of the selected set of functional operations. The broadcasting computing entity then performs an action using the output of the functional operation received.
-
公开(公告)号：US12254298B2
公开(公告)日：2025-03-18
申请号：US18675416
申请日：2024-05-28
Applicant: Insight Direct USA, Inc.
Inventor： Amol Ajgaonkar
IPC: G06F8/41
Abstract: A build of a software solution that is cooperatively performed is automated. A broadcasting computing entity broadcasts an announcement of the functional operation of which the broadcasting computing entity is capable. Each of a plurality of listening computing entities connected to the network receives the announcement and compares the functional operation with a list of operational needs. After determining itself in need of performance of such a functional operation, a subscribing one of the plurality of listening computing entities transmits a response to the request indicating subscription to the output of the functional operation. The broadcasting computing entity then performs the functional operation, thereby generating and transmitting to the subscribing one of the plurality of listening computing entities the output of the functional operation. The subscribing one of the plurality of listening computing entities then performs an action using the output of the functional operation received.
-
公开(公告)号：US12106536B2
公开(公告)日：2024-10-01
申请号：US18222683
申请日：2023-07-17
Applicant: Insight Direct USA, Inc.
Inventor： Amol Ajgaonkar
Abstract: A method of preprocessing incoming video data of at least one region of interest from a camera collecting video data having a first field of view is disclosed herein that includes receiving the incoming video data from the camera; preprocessing the incoming video data, by a computer processor, according to preprocessing parameters defined within a runtime configuration file, with the preprocessing including formatting the incoming video data to create first video data of a first region of interest with a second field of view that is less than the first field of view; and publishing the first video data of the first region of interest to an endpoint to allow access by a first subscriber.
-
公开(公告)号：US12026486B2
公开(公告)日：2024-07-02
申请号：US17953850
申请日：2022-09-27
Applicant: Insight Direct USA, Inc.
Inventor： Amol Ajgaonkar
IPC: G06F8/41
CPC classification number: G06F8/41
Abstract: A build of a software solution that is cooperatively performed is automated. A broadcasting computing entity selects a selected set of functional operations from one or more sets of functional operations associated with the software solution and then broadcasts a request to perform each of the functional operations in the selected set. Each of a plurality of listening computing entities connected to the network receives the request and determines capability of performing each of the functional operations in the selected set. After determining itself capable, a capable one of the plurality of listening computing entities transmits a response to the request indicating such capability, and then performs each of the functional operations in the selected set, thereby generating and transmitting to the broadcasting computing entity the output of the selected set of functional operations. The broadcasting computing entity then performs an action using the output of the functional operation received.
-
30.发明公开公开(公告)号：US20240177443A1
公开(公告)日：2024-05-30
申请号：US18428084
申请日：2024-01-31
Applicant: Insight Direct USA, Inc.
Inventor： Amol Ajgaonkar
Abstract: A method of preprocessing incoming video data of at least one region of interest from a camera collecting video data is disclosed herein that includes receiving the incoming video data from the camera; preprocessing the incoming video data, by a computer processor, according to preprocessing parameters defined within a runtime configuration file, with the preprocessing including formatting the incoming video data to create first video data of a first region of interest; and publishing the first video data of the first region of interest to an endpoint to allow access by a first subscriber.
-
-
-
-
-
-
-
-
-
Search Results
49
records
(took 0.02 seconds)
