公开(公告)号：US20230368520A1

公开(公告)日：2023-11-16

申请号：US17663035

申请日：2022-05-12

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Ishay Goldin ,  Netanel Stein ,  Alexandra Dana ,  Alon Intrater ,  David Tsidkiahu ,  Nathan Levy ,  Omer Shabtai ,  Ran Vitek ,  Tal Heller ,  Yaron Ukrainitz ,  Yotam Platner ,  Zuf Pilosof

IPC: G06V10/96 ,  G06T3/40 ,  G06V20/40 ,  G06V10/82 ,  G06V20/70 ,  G06V10/774

CPC classification number: G06V10/96 ,  G06T3/4046 ,  G06V20/49 ,  G06V10/82 ,  G06V20/41 ,  G06V20/70 ,  G06V10/774

Abstract: Techniques and apparatuses enabling high accuracy video object detection using reduced system resource requirements (e.g., reduced computational load, shallower neural network designs, etc.) are described. For example, a search domain of an object detection scheme (e.g., a target object class, a target object size, a target object rotation angle, etc.) may be separated into subdomains (e.g., such as subdomains of object classes, subdomains of object sizes, subdomains object rotation angles, etc.). Specialized, subdomain-level object detection/segmentation tasks may then be separated across sequential video frames. As such, different subdomain-level processing techniques (e.g., via specialized neural networks) may be implemented across different frames of a video sequence. Moreover, redundancy information of consecutive video frames may be leveraged, such that specialized object detection tasks combined with visual object tracking across consecutive frames may enable more efficient (e.g., more accurate, less computationally intensive, etc.) full domain object detection and object segmentation schemes.