公开(公告)号：MY184711A

公开(公告)日：2021-04-19

申请号：MYPI2013700746

申请日：2013-05-08

Applicant: MIMOS BERHAD ,  MULTIMEDIA UNIV

Inventor： ETTIKAN KANDASAMY A/L KARUPPIAH ,  SHAHIRINA BINTI MOHD TAHIR ,  ONG PENG SHEN ,  CHANG YOONG CHOON ,  OOI CHEE PUN

Abstract: The present invention relates to a system and method for detecting an object. The system and method reduce the amount of computations needed in detecting and tracking the moving object by predicting the motion of the object in the following frames. Thus, the system (1000) is able to focus on computing a portion of the frame where the object has been predicted to be in. The system (1000) comprises of an image acquisition module (1100), a buffering module (1200), a pre-processor (1300), an image sub-segmenting module (1400), an image sub-segment module (1500), a main processor (1600), an object feature extracting module (1700), a predictive module (1800) and an object and priority evaluator (1900). (Figure 1)

公开(公告)号：MY173428A

公开(公告)日：2020-01-23

申请号：MYPI2014002432

申请日：2014-08-20

Applicant: MIMOS BERHAD

Inventor： ETTIKAN KANDASAMY A/L KARUPPIAH ,  SHAHIRINA BINTI MOHD TAHIR ,  ONG PENG SHEN ,  NGO CHUAN HAI ,  LEE CHIN YANG

Abstract: Video Analytics (VA) is a compute intensive and time consuming process. The method and apparatus (100) of the present disclosure addresses this problem by creating a parallel mechanism for data reuse and eliminating resource and compute redundancy for multiple video analytics execution. The method involves identifying common VA modules for execution across VA operations (14, 16), collating outputs of the executed VA modules in a parallel configuration (18, 18.2) and analysing the collated outputs for detecting occurrence of an event associated with pre-defined specifications (20). Fig. 1

公开(公告)号：WO2014182156A1

公开(公告)日：2014-11-13

申请号：PCT/MY2014/000083

申请日：2014-04-28

Applicant: MIMOS BERHAD ,  MULTIMEDIA UNIVERSITY

Inventor： SHAHIRINA BINTI MOHD TAHIR ,  ETTIKAN KANDASAMY A/L KARUPPIAH ,  ONG PENG SHEN ,  CHANG YOONG CHOON ,  OOI CHEE PUN

IPC: G06T7/20

CPC classification number: G06T7/254 ,  G06T2200/28 ,  G06T2207/20021 ,  G06T2207/30232

Abstract: The present invention relates to a system and method for detecting an object. The system and method reduce the amount of computations needed in detecting and tracking the moving object by predicting the motion of the object in the following frames. Thus, the system (1000) is able to focus on computing a portion of the frame where the object has been predicted to be in. The system (1000) comprises of an image acquisition module (1100), a buffering module (1200), a pre-processor (1300), an image sub-segmenting module (1400), an image sub-segment module (1500), a main processor (1600), an object feature extracting module (1700), a predictive module (1800) and an object and priority evaluator (1900).

Abstract translation: 本发明涉及一种用于检测物体的系统和方法。 该系统和方法通过预测下一帧中物体的运动来减少检测和跟踪移动物体所需的计算量。 因此，系统（1000）能够专注于计算已经预测对象的帧的一部分。系统（1000）包括图像获取模块（1100），缓冲模块（1200） 预处理器（1300），图像子分割模块（1400），图像子段模块（1500），主处理器（1600），对象特征提取模块（1700），预测模块（1800） 和对象和优先级评估器（1900）。