中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

28 records (took 0.017 seconds)

    IMAGING SYSTEM WITH OBJECT RECOGNITION FEEDBACK
    21.
    发明申请
    IMAGING SYSTEM WITH OBJECT RECOGNITION FEEDBACK 有权

    公开(公告)号：US20250056111A1

    公开(公告)日：2025-02-13

    申请号：US18366446

    申请日：2023-08-07

    Applicant: MOTOROLA SOLUTIONS, INC.

    Inventor： William Fincannon ,  Joseph Rafferty ,  Pietro Russo ,  Peter L. Venetianer

    IPC: H04N23/61 ,  G06V20/62 ,  G06V30/10

    Abstract: Examples provide an imaging system including an image sensor; and an electronic processor in communication with the image sensor. The electronic processor is configured to determine a set of imaging parameters, and, for each iteration included in an iteration set, update the set of imaging parameters by: receiving an image captured by the image sensor using the set of imaging parameters, performing object recognition on the image to detect an object of interest, determining an object recognition confidence score, determining a set of external factors based on the image and/or information from a second sensor, linking the set of imaging parameters and the set of external factors to the object recognition confidence score, and training a predictive model for updating the set of imaging parameters using the object recognition confidence score, the set of imaging parameters, and the set of external factors.

    Indicating that captured data is associated with an uncompleted task of an incident
    22.
    发明授权
    Indicating that captured data is associated with an uncompleted task of an incident 有权

    公开(公告)号：US12154336B2

    公开(公告)日：2024-11-26

    申请号：US17806683

    申请日：2022-06-13

    Applicant: MOTOROLA SOLUTIONS, INC.

    Inventor： Francesca Schuler ,  Trent J. Miller ,  Pietro Russo ,  Steven D. Tine

    IPC: G06V20/40 ,  G08B13/196

    Abstract: One example device includes an electronic processor configured identify, based on an incident type and a role of an object associated with a public safety incident, an uncompleted task that is to be performed by a public safety officer and that is associated with the object associated with the public safety incident. The electronic processor may be configured to identify first data included in a captured data file associated with the public safety incident that was generated at least partially by monitoring the object. The electronic processor may be configured to determine a time period within the captured data file during which the first data is identified to be present, and display an indication of the uncompleted task and at least one of the time period within the captured data file, the first data, and a user-selectable link to allow a user to consume the first data.

    Device and method for assigning video analytics tasks to computing devices
    25.
    发明授权
    Device and method for assigning video analytics tasks to computing devices 有权

    公开(公告)号：US11503101B1

    公开(公告)日：2022-11-15

    申请号：US17644512

    申请日：2021-12-15

    Applicant: MOTOROLA SOLUTIONS, INC.

    Inventor： Pietro Russo ,  Howard Hoffman ,  Sven Rebien ,  Bert Van Der Zaag

    IPC: G06F13/00 ,  H04L65/80 ,  H04N7/18

    Abstract: A process of assigning video analytics tasks to computing devices. In operation, an electronic computing device obtains predicted scene data associated with a scene corresponding to which video data is to be captured at a particular time period using a video camera. The electronic computing device then estimates, based on the predicted scene data, an edge computing cost to be incurred to complete execution of a video analytics task at one or more edge computing devices and a cloud computing cost to be incurred to complete execution of the same video analytics task at one or more cloud computing devices. If the edge computing cost is lower than the cloud computing cost, then the electronic computing device assigns the video analytics task to the edge computing devices. Otherwise, then the electronic computing device assigns the video analytics task to the cloud computing devices.

    Autonomous self-learning artificial intelligence intent system for access control
    27.
    发明授权
    Autonomous self-learning artificial intelligence intent system for access control 有权

    公开(公告)号：US11157734B1

    公开(公告)日：2021-10-26

    申请号：US17108852

    申请日：2020-12-01

    Applicant: MOTOROLA SOLUTIONS, INC.

    Inventor： Aleksey Lipchin ,  Kaveh Malakuti ,  Pietro Russo ,  Ron Wilson

    IPC: G06K9/00 ,  G07C9/26 ,  G07C9/00 ,  G07C9/37

    Abstract: One embodiment provides an access control system including access control sensors to detect actions performed in a vicinity of an access point, a verification sensor to verify access of the access point, and an electronic processor communicatively coupled to the access control sensors and the verification sensor. The electronic processor is configured to in response to an access intent model satisfying an accuracy condition, deploy the access intent model for the access point and receive a dataset indicating an action performed in the vicinity of the access point. The electronic processor is also configured to predict an access intent to access the access point by applying the access intent model to the dataset and enable access through the access point. The electronic processor is further configured to receive verification data indicating whether the access point is accessed, and automatically assign a label to the dataset based on the verification data.

Patent Agency Ranking