公开(公告)号：WO2022093004A1

公开(公告)日：2022-05-05

申请号：PCT/MY2020/050197

申请日：2020-12-15

Applicant: MIMOS BERHAD

Inventor： LIANG, Kim Meng ,  HON, Hock Woon ,  A/L RANGGANAZAN, Durai Naidu

IPC: G06T7/262 ,  G06T7/215 ,  G06K9/00

Abstract: The present invention discloses a system for computing motion information from detected moving objects, the system comprising a background model module (9), an object presence module (10), and a descriptor module (11). The system is configured for computing a plurality of background models (103) based on inputs from a plurality of learning rates (101), determining whether a detected moving object is present in a captured image (201) for each learning rate (101), and computing at least one descriptor (300, 400, 500, 600) based on the presence of the detected moving objects in the captured image (201) for each learning rate (101).

公开(公告)号：WO2022005274A1

公开(公告)日：2022-01-06

申请号：PCT/MY2020/050185

申请日：2020-12-01

Applicant: MIMOS BERHAD

Inventor： LIANG, Kim Meng ,  HON, Hock Woon ,  A/L RANGGANAZAN, Durai Naidu

IPC: G06K9/20 ,  G06N3/08 ,  G06T7/194 ,  G06T5/00

Abstract: The present invention discloses a system to detect a moving object in a dynamic environment from a sequence of captured images, comprising a learning rate module (9), an image filtering module (10), an object likelihood level module (11), and an object identification module (12). The system executes the following steps: determining a learning rate seed (301) based on the speed rate (306) of the moving object, applying the determined learning rate seed (301) to a data training module (13) for filtering of background images (403) from captured images, calculating an object likelihood level (505) by computing statistical properties of the filtered images (406), and identifying the moving object based on the object likelihood level (505), wherein the learning rate seed (301) and the object likelihood level (505) are updated based on a processing of one or more new images.