公开(公告)号：US12033348B1

公开(公告)日：2024-07-09

申请号：US18450085

申请日：2023-08-15

Applicant: Verkada Inc.

Inventor： Rishabh Goyal ,  Song Cao ,  Yi Xu ,  Bhavna Sud

IPC: G06T7/70 ,  G06T7/00 ,  G06T7/12 ,  G06T7/20 ,  G06T11/00 ,  G06V10/764

CPC classification number: G06T7/70 ,  G06T7/0002 ,  G06T7/12 ,  G06T7/20 ,  G06T11/00 ,  G06V10/764 ,  G06T2207/20132 ,  G06T2207/30201 ,  G06V2201/07

Abstract: A method for generating cropped images depicting objects captured in video data includes receiving, at a processor of a video camera system, a video stream including a series of video frames depicting an object. A classification for the object is generated, and an occurrence of the object being detected is identified in an additional video frame(s) from the series of video frames. A motion associated with the object is calculated based on the classification and the additional video frame(s). At least one image that depicts the object and includes a cropped portion of a video frame from the series of video frames is generated, along with an associated set of at least one quality score, in response to calculating the motion. The method also includes causing transmission of the at least one image to at least one remote compute device based on the set of at least one quality score.

公开(公告)号：US11978267B2

公开(公告)日：2024-05-07

申请号：US18168530

申请日：2023-02-13

Applicant: Verkada Inc.

Inventor： Mayank Gupta ,  Suraj Arun Vathsa ,  Song Cao ,  Yi Xu ,  Yuanyuan Chen ,  Yunchao Gong

IPC: G06V20/62 ,  G06V10/774 ,  G06V20/54 ,  G06V30/148

CPC classification number: G06V20/625 ,  G06V10/774 ,  G06V20/54 ,  G06V30/148

Abstract: A method and related system operations include obtaining a video stream with an image sensor of a camera device, detecting a plurality of target objects by executing a neural network model based on the video stream with a vision processor unit of the camera device. The method also includes generating a plurality of bounding boxes, determining a plurality of character sequences by, for each respective bounding box of the plurality of bounding boxes, performing a set of optical character recognition (OCR) operations to determine a respective character sequence of the plurality of character sequences. The method also includes updating a plurality of tracklets to indicate the plurality of bounding boxes and storing the plurality of tracklets in association with the plurality of character sequences in a memory of the camera device.

公开(公告)号：US12056918B1

公开(公告)日：2024-08-06

申请号：US18477280

申请日：2023-09-28

Applicant: Verkada Inc.

Inventor： Rishabh Goyal ,  Song Cao

IPC: G06V10/94 ,  G06F16/71 ,  G06F16/75 ,  G06V10/82 ,  G06V20/40 ,  G06V20/52 ,  H04N5/262 ,  H04N7/18

CPC classification number: G06V10/945 ,  G06F16/71 ,  G06F16/75 ,  G06V10/82 ,  G06V20/41 ,  G06V20/52 ,  H04N5/2628 ,  H04N7/183

Abstract: A method for generating and selecting images of objects based on video data and text data includes receiving, at a processor of a video camera system, a video stream including a series of video frames depicting at least one object. A set of at least one classification for the object is generated. Additionally, an image that depicts the object and that includes a cropped portion of a video frame from the series of video frames is generated. A set of at least one index key is generated based on the set of at least one classification, and the image is stored based on the set of at least one index key. The processor receives a signal representing a text input from a user, and the processor performs at least one of (1) retrieval of the image or (2) generation of an alert.

公开(公告)号：US11983927B1

公开(公告)日：2024-05-14

申请号：US18182922

申请日：2023-03-13

Applicant: Verkada Inc.

Inventor： John Peruzzi ,  Song Cao ,  Rishabh Goyal ,  Yunchao Gong

IPC: G06V20/40 ,  G06V10/771

CPC classification number: G06V20/47 ,  G06V10/771

Abstract: A method includes receiving, at a processor and from a requestor compute device, a request including a representation of at least one video camera from a set of video cameras. In response to receiving the request, a set of at least one video file is generated by retrieving a set of video clips associated with the at least one video camera and the time range. For each of the at least one video camera, a subset of video clips is selected from the set of video clips for that video camera based on a comparison of anomaly scores for that video camera, and concatenating the subsets of video clips to generate the set of at least one video file. The method also includes sending a signal to cause display of at least one video file from the set of at least one video file via the requestor compute device.

公开(公告)号：US12069363B2

公开(公告)日：2024-08-20

申请号：US18191808

申请日：2023-03-28

Applicant: Verkada Inc.

Inventor： Pushpak Pujari ,  Rishabh Goyal ,  Song Cao ,  Erich J. Kreutzer ,  Alan M. Anderson

IPC: H04N23/611 ,  G06T5/70 ,  G06V10/25 ,  G06V20/52 ,  H04N23/661

CPC classification number: H04N23/611 ,  G06T5/70 ,  G06V10/25 ,  G06V20/52 ,  H04N23/661

Abstract: Introduced here are surveillance systems and associated approaches for obfuscating biometric identifiers generated by, or available to, those surveillance systems for privacy reasons. In the event that a surveillance system generates a biometric identifier (e.g., by imaging a face of a person entering the premises of an organization), caution must be taken to only share the biometric identifier with individuals as necessary for security reasons. The approaches introduced here allow the privacy of persons being surveilled to be protected. Specifically, a computer program may selectively apply blurring as an impermanent mask to obfuscate each face in a digital image. This approach limits “reidentification” of a given person to those scenarios where her identity must be determined.

公开(公告)号：US12039781B2

公开(公告)日：2024-07-16

申请号：US18052461

申请日：2022-11-03

Applicant: Verkada Inc.

Inventor： Rishabh Goyal ,  Song Cao ,  John Peruzzi ,  Yunchao Gong

IPC: G06V20/52 ,  G06V10/25 ,  G06V10/74

CPC classification number: G06V20/52 ,  G06V10/25 ,  G06V10/761

Abstract: A method for monitoring protected regions of a camera view includes receiving, at a processor of a video camera system, a video stream including a series of video frames depicting at least one scene. A background model is identified based on a predefined representation of at least one region of interest associated with the scene. Each of the video frames is compared to the background model, to define an associated binary mask. A persistent change in the at least one region of interest is detected, based on the binary masks, the persistent change having an associated duration that exceeds a predefined threshold. In response to detecting the persistent change, a change notification message including a video file is generated. The method also includes causing display of the change notification message via a user interface and/or causing transmission of the change notification message to a remote compute device.