公开(公告)号：US11429664B1

公开(公告)日：2022-08-30

申请号：US17700396

申请日：2022-03-21

Applicant: Verkada Inc.

Inventor： Yi Xu ,  Mayank Gupta ,  Xia Yang ,  Yuanyuan Chen ,  Zixiao (Shawn) Wang ,  Qiang (Kevin) Fu ,  Yunchao Gong ,  Naresh Nagabushan

IPC: G06K9/00 ,  G06F16/583 ,  G06V10/56 ,  G06F16/532 ,  G06V10/26 ,  G06F16/538 ,  G06V10/82

Abstract: A computer vision processor of a camera extracts attributes of persons or vehicles from hyperzooms generated from image frames. The hyperzooms represent traffic patterns. The extracting is performed using a feature extractor of an on-camera convolutional neural network (CNN) including an inverted residual structure. The attributes include at least colors of clothing of the persons or colors of the vehicles. Mobile semantic segmentation models of the CNN are generated using the hyperzooms and the attributes. Attribute analytics are generated by executing the mobile semantic segmentation models while obviating network usage by the camera. The attribute analytics are stored in a key-value database located on a memory card of the camera. A query is received from the server instance specifying one or more of the attributes. The attribute analytics are filtered using the one or more of the attributes to obtain a portion of the traffic patterns.

公开(公告)号：US11734343B1

公开(公告)日：2023-08-22

申请号：US18155687

申请日：2023-01-17

Applicant: Verkada Inc.

Inventor： Yi Xu ,  Mayank Gupta ,  Xia Yang ,  Yuanyuan Chen ,  Zixiao (Shawn) Wang ,  Qiang (Kevin) Fu ,  Yunchao Gong ,  Naresh Nagabushan

IPC: G06K9/00 ,  G06F16/583 ,  G06F16/538 ,  G06V10/82 ,  G06V10/26 ,  G06F16/532 ,  G06V10/56

CPC classification number: G06F16/5838 ,  G06F16/532 ,  G06F16/538 ,  G06V10/26 ,  G06V10/56 ,  G06V10/82

Abstract: A computer vision processor of a camera extracts attributes of persons or vehicles from hyperzooms generated from image frames. The hyperzooms represent traffic patterns. The extracting is performed using a feature extractor of an on-camera convolutional neural network (CNN) including an inverted residual structure. The attributes include at least colors of clothing of the persons or colors of the vehicles. Mobile semantic segmentation models of the CNN are generated using the hyperzooms and the attributes. Attribute analytics are generated by executing the mobile semantic segmentation models while obviating network usage by the camera. The attribute analytics are stored in a key-value database located on a memory card of the camera. A query is received from the server instance specifying one or more of the attributes. The attribute analytics are filtered using the one or more of the attributes to obtain a portion of the traffic patterns.

公开(公告)号：US11586667B1

公开(公告)日：2023-02-21

申请号：US17869164

申请日：2022-07-20

Applicant: Verkada Inc.

Inventor： Yi Xu ,  Mayank Gupta ,  Xia Yang ,  Yuanyuan Chen ,  Zixiao (Shawn) Wang ,  Qiang (Kevin) Fu ,  Yunchao Gong ,  Naresh Nagabushan

IPC: G06K9/00 ,  G06F16/583 ,  G06V10/56 ,  G06V10/82 ,  G06F16/532 ,  G06F16/538 ,  G06V10/26

Abstract: A computer vision processor of a camera extracts attributes of persons or vehicles from hyperzooms generated from image frames. The hyperzooms represent traffic patterns. The extracting is performed using a feature extractor of an on-camera convolutional neural network (CNN) including an inverted residual structure. The attributes include at least colors of clothing of the persons or colors of the vehicles. Mobile semantic segmentation models of the CNN are generated using the hyperzooms and the attributes. Attribute analytics are generated by executing the mobile semantic segmentation models while obviating network usage by the camera. The attribute analytics are stored in a key-value database located on a memory card of the camera. A query is received from the server instance specifying one or more of the attributes. The attribute analytics are filtered using the one or more of the attributes to obtain a portion of the traffic patterns.

公开(公告)号：US12205380B2

公开(公告)日：2025-01-21

申请号：US18402956

申请日：2024-01-03

Applicant: Verkada Inc.

Inventor： Yi Xu ,  Mayank Gupta ,  Xia Yang ,  Yuanyuan Chen ,  Zixiao (Shawn) Wang ,  Qiang (Kevin) Fu ,  Yunchao Gong ,  Naresh Nagabushan

IPC: G06V20/58 ,  B60W40/08 ,  G06F16/28

Abstract: A computer vision processor of a camera generates hyperzooms for persons or vehicles from image frames captured by the camera. The hyperzooms include a first hyperzoom associated with the persons or vehicles. The computer vision processor tracks traffic patterns of the persons or vehicles while obviating network usage by the camera by predicting positions of the persons or vehicles using a Kalman Filter from the first hyperzoom. The persons or vehicles are detected in the second hyperzoom. The positions of the persons or vehicles are updated based on detecting the persons or vehicles in the second hyperzoom. The first hyperzoom is removed from the camera. Tracks of the persons or vehicles are generated based on the updated positions. The second hyperzoom is removed from the camera. Track metadata is generated from the tracks for storing in a key-value database located on a non-transitory computer-readable storage medium of the camera.

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：US12056183B2

公开(公告)日：2024-08-06

申请号：US18347503

申请日：2023-07-05

Applicant: Verkada Inc.

Inventor： Yi Xu ,  Mayank Gupta ,  Xia Yang ,  Yuanyuan Chen ,  Zixiao (Shawn) Wang ,  Qiang (Kevin) Fu ,  Yunchao Gong ,  Naresh Nagabushan

IPC: G06K9/00 ,  G06F16/532 ,  G06F16/538 ,  G06F16/583 ,  G06V10/26 ,  G06V10/56 ,  G06V10/82

CPC classification number: G06F16/5838 ,  G06F16/532 ,  G06F16/538 ,  G06V10/26 ,  G06V10/56 ,  G06V10/82

Abstract: A computer vision processor of a camera extracts attributes of persons or vehicles from hyperzooms generated from image frames. The hyperzooms represent traffic patterns. The extracting is performed using a feature extractor of an on-camera convolutional neural network (CNN) including an inverted residual structure. The attributes include at least colors of clothing of the persons or colors of the vehicles. Mobile semantic segmentation models of the CNN are generated using the hyperzooms and the attributes. Attribute analytics are generated by executing the mobile semantic segmentation models while obviating network usage by the camera. The attribute analytics are stored in a key-value database located on a memory card of the camera. A query is received from the server instance specifying one or more of the attributes. The attribute analytics are filtered using the one or more of the attributes to obtain a portion of the traffic patterns.

公开(公告)号：US11900688B2

公开(公告)日：2024-02-13

申请号：US18155666

申请日：2023-01-17

Applicant: Verkada Inc.

Inventor： Yi Xu ,  Mayank Gupta ,  Xia Yang ,  Yuanyuan Chen ,  Zixiao (Shawn) Wang ,  Qiang (Kevin) Fu ,  Yunchao Gong ,  Naresh Nagabushan

IPC: G06V10/56 ,  G06V20/58 ,  G06F16/583 ,  G06F16/532 ,  G06F16/28 ,  B60W40/08

CPC classification number: G06V20/58 ,  B60W40/08 ,  G06F16/284 ,  G06F16/287 ,  B60W2420/42

Abstract: A computer vision processor of a camera generates hyperzooms for persons or vehicles from image frames captured by the camera. The hyperzooms include a first hyperzoom associated with the persons or vehicles. The computer vision processor tracks traffic patterns of the persons or vehicles while obviating network usage by the camera by predicting positions of the persons or vehicles using a Kalman Filter from the first hyperzoom. The persons or vehicles are detected in the second hyperzoom. The positions of the persons or vehicles are updated based on detecting the persons or vehicles in the second hyperzoom. The first hyperzoom is removed from the camera. Tracks of the persons or vehicles are generated based on the updated positions. The second hyperzoom is removed from the camera. Track metadata is generated from the tracks for storing in a key-value database located on a non-transitory computer-readable storage medium of the camera.

公开(公告)号：US11594043B1

公开(公告)日：2023-02-28

申请号：US17700383

申请日：2022-03-21

Applicant: Verkada Inc.

Inventor： Yi Xu ,  Mayank Gupta ,  Xia Yang ,  Yuanyuan Chen ,  Zixiao (Shawn) Wang ,  Qiang (Kevin) Fu ,  Yunchao Gong ,  Naresh Nagabushan

IPC: G06V10/56 ,  G06F16/583 ,  G06F16/532 ,  G06V20/58 ,  G06F16/28 ,  B60W40/08

Abstract: A computer vision processor of a camera generates hyperzooms for persons or vehicles from image frames captured by the camera. The hyperzooms include a first hyperzoom associated with the persons or vehicles. The computer vision processor tracks traffic patterns of the persons or vehicles while obviating network usage by the camera by predicting positions of the persons or vehicles using a Kalman Filter from the first hyperzoom. The persons or vehicles are detected in the second hyperzoom. The positions of the persons or vehicles are updated based on detecting the persons or vehicles in the second hyperzoom. The first hyperzoom is removed from the camera. Tracks of the persons or vehicles are generated based on the updated positions. The second hyperzoom is removed from the camera. Track metadata is generated from the tracks for storing in a key-value database located on a non-transitory computer-readable storage medium of the camera.