公开(公告)号：US12165379B2

公开(公告)日：2024-12-10

申请号：US17581423

申请日：2022-01-21

Applicant: Lemon Inc.

Inventor： Linjie Yang ,  Yiming Cui ,  Ding Liu

IPC: G06K9/00 ,  G06T7/70 ,  G06V10/40 ,  G06V10/70 ,  G06V10/764 ,  G06V10/82 ,  G06V10/94

Abstract: Described are examples for detecting objects in an image on a device including setting, based on a condition, a number of sparse proposals to use in performing object detection in the image, performing object detection in the image based on providing the sparse proposals as input to an object detection process to infer object location and classification of one or more objects in the image, and indicating, to an application and based on an output of the object detection process, the object location and classification of the one or more objects.

公开(公告)号：US20240168991A1

公开(公告)日：2024-05-23

申请号：US18057008

申请日：2022-11-18

Applicant: Lemon Inc.

Inventor： Linjie Yang ,  Yiming Cui ,  Haichao Yu

IPC: G06F16/538 ,  G06V10/42 ,  G06V10/77 ,  G06V10/774 ,  G06V10/82 ,  G06V20/70

CPC classification number: G06F16/538 ,  G06V10/42 ,  G06V10/7715 ,  G06V10/774 ,  G06V10/82 ,  G06V20/70

Abstract: Object detection using a transformer-based object detection model includes randomly initializing basic queries for the model, modulating the basic queries based on semantics of input images, and training the model basic on features extracted from input images and the modulated queries.

公开(公告)号：US11625814B2

公开(公告)日：2023-04-11

申请号：US17192549

申请日：2021-03-04

Applicant: Lemon Inc.

Inventor： Linjie Yang ,  Ding Liu ,  Xueyan Zou

IPC: G06K9/00 ,  G06T5/00 ,  G06N3/08 ,  G06T3/00

Abstract: Systems and methods are directed to inpainting video. More specifically, initial video data including a sequence of image frames containing missing or corrupted pixel information may be received. Optical flow displacement values and optical flow validity masks may be generated for neighboring image frames of initial video data. Image features from image feature maps of one or more neighboring image frames may be warp-shifted to image feature maps of a current image frame using the optical flow displacement values and warp-shifted image features from the feature maps of the one or more neighboring image frames may be selected based on one or more of the optical flow validity masks. A sequence of complete image frames may be generated based on the selected warp-shifted image features from the feature maps of the one or more neighboring image frames and image features from the image feature maps of the current image frame.

公开(公告)号：US11501447B2

公开(公告)日：2022-11-15

申请号：US17192599

申请日：2021-03-04

Applicant: Lemon Inc.

Inventor： Linjie Yang ,  Ziyu Jiang ,  Ding Liu ,  Longyin Wen

IPC: G06K9/00 ,  G06T7/174 ,  G06K9/62 ,  G06V20/40 ,  G06T7/194

Abstract: Systems and method directed to performing video object segmentation are provided. In examples, video data representing a sequence of image frames and video data representing an object mask may be received at a video object segmentation server. Image features may be generated based on a first image frame of the sequence of image frames, image features may be generated based on a second image frame of the sequence of image frames; and object features may be generated based on the object mask. A transform matrix may be computed based on the image features of the first image frame and image features of the second image frame; the transform matrix may be applied to the object features resulting in transformed object features. A predicted object mask associated with the second image frame may be obtained by decoding the transformed object features.