公开(公告)号：MY172143A

公开(公告)日：2019-11-14

申请号：MYPI2012005406

申请日：2012-12-13

Applicant: MIMOS BERHAD

Inventor： ZULAIKHA BINTI KADIM ,  HON HOCK WOON ,  NORSHUHADA BINTI SAMUDIN

Abstract: The present invention provides a method for processing videos captured through a stereo camera, the videos having a plurality of frames, each frames includes at least a left and a right images. The method includes acquiring videos captured by the pair of stereo cameras (101) and acceleration information of the stereo camera (101) detected through the accelerometer (102); extracting feature points in the right and left images of a current frame; matching the feature points between the right and left images, wherein disparity value of each feature point is computed; clustering the feature points on a current frame into one or more clouds based on their appearance and distance; determining a correspondence between the clouds of the current frame and previous frame; classifying the clouds through estimating statistical disparity distribution of each cloud to identify if the respective clouds are new clouds, existing clouds or unknown clouds; and merging the clouds that are determined to be a same object based on the tracking information and changes of disparity of the clouds over time. A system carrying out the above method is also provided herein.

公开(公告)号：MY159124A

公开(公告)日：2016-12-15

申请号：MYPI2012005241

申请日：2012-12-04

Applicant: MIMOS BERHAD

Inventor： ZULAIKHA BINTI KADIM ,  LIANG KIM MENG ,  NORSHUHADA BINTI SAMUDIN

IPC: G06T7/20 ,  G06T7/00

Abstract: A METHOD (200) FOR EXTRACTING FOREGROUND OBJECTS OF A CURRENTLY OBSERVED IMAGE IS PROVIDED HEREWITH. THE METHOD COMPRISES SEGMENTING (202) BACKGROUND OBJECTS OF A PREVIOUSLY OBSERVED IMAGE INTO REGIONS OF HOMOGENEOUS BRIGHTNESS AND SETTING INITIAL THRESHOLD VALUES FOR EACH SEGMENTED REGIONS TO INITIALIZE A BACKGROUND IMAGE INFORMATION THAT INCLUDES BACKGROUND IMAGE AND INITIAL THRESHOLD VALUES OF THE CURRENTLY OBSERVED IMAGE, SUBTRACTING (401) THE CURRENTLY OBSERVED IMAGE FROM THE BACKGROUND IMAGE INFORMATION AND THRESHOLDING (402) THE IMAGE DIFFERENCE USING THE INITIAL THRESHOLD VALUES TO EXTRACT FOREGROUND OF THE CURRENTLY OBSERVED IMAGE, AND COMPARING (405A) THE FOREGROUND OF THE CURRENTLY OBSERVED IMAGE AGAINST FOREGROUND OF THE PREVIOUSLY OBSERVED IMAGE TO UPDATE THE INITIAL THRESHOLD VALUES OF THE BACKGROUND IMAGE INFORMATION. (FIG.1)

公开(公告)号：WO2014038924A3

公开(公告)日：2014-03-13

申请号：PCT/MY2013/000154

申请日：2013-09-05

Applicant: MIMOS Berhad

Inventor： ZULAIKHA BINTI KADIM ,  NORSHUHADA BINTI SAMUDIN ,  DR. HON HOCK WOON

IPC: G06T7/20

Abstract: The present invention relates to a novel method for producing a background model based on the images acquired from a non-static camera. Rule-based statistical multiple image analytical method to process multiple non-overlapping background region of a scene using predetermined threshold values to identify the preferred intensity variance for modeling the background pixel. One of the advantages of the a method for modeling dynamic scene using region-based adaptive statistical learning to model dynamic background within one camera view and scene-based modeling to model multiple non-overlapping regions of the background image scene is that it provides an accurate background representation as compared to background modeling using pixel-wise scalar value. Another advantage of the method for the present invention is that a less computational cost is used as compared to background modeling using pixel-wise statistical or kernel density. Furthermore, the method for the present invention has higher sensitive foreground detection as compared to privacy mask concept (masking out dynamic region from being modeled.

公开(公告)号：WO2014092549A3

公开(公告)日：2014-09-12

申请号：PCT/MY2013000256

申请日：2013-12-12

Applicant: MIMOS BERHAD

Inventor： ZULAIKHA BINTI KADIM ,  HON HOCK WOON ,  NORSHUHADA BINTI SAMUDIN

IPC: G06T7/00 ,  G06T7/20

CPC classification number: G06T7/285 ,  G06T7/174 ,  G06T7/194 ,  G06T7/215 ,  G06T7/246 ,  G06T7/254 ,  G06T7/73 ,  G06T2207/10021 ,  G06T2207/20221 ,  G06T2207/30232 ,  G06T2207/30244

Abstract: The present invention provides a system and method for processing sequence of image frames captured through an imaging device, the imaging device includes an accelerometer. The system and method comprise an adaptive temporal background subtraction unit and a dynamic foreground object estimation unit for evaluating whether each pixel is either a moving object pixel or a non-moving object pixel based on the classification of the pixels between the first motion map and the second motion map generated thereon.

Abstract translation: 本发明提供了用于处理通过成像装置捕获的图像帧序列的系统和方法，该成像装置包括加速度计。 该系统和方法包括自适应时间背景减除单元和动态前景目标估计单元，用于基于第一运动映射和第一运动映射之间的像素的分类来评估每个像素是移动目标像素还是非移动目标像素 在其上产生第二运动图。

公开(公告)号：WO2014092552A3

公开(公告)日：2014-09-12

申请号：PCT/MY2013000266

申请日：2013-12-13

Applicant: MIMOS BERHAD

Inventor： ZULAIKHA BINTI KADIM ,  HON HOCK WOON ,  NORSHUHADA BINTI SAMUDIN

IPC: G06T7/20

CPC classification number: G06T7/292 ,  G06T7/194 ,  G06T7/215 ,  G06T7/246 ,  G06T7/285 ,  G06T2207/10021 ,  G06T2207/30232

Abstract: The present invention provides a method for processing videos captured through a stereo camera, the videos having a plurality of frames, each frames includes at least a left and a right images. The method includes acquiring videos captured by the pair of stereo cameras (101) and acceleration information of the stereo camera (101) detected through the accelerometer (102); extracting feature points in the right and left images of a current frame; matching the feature points between the right and left images, wherein disparity value of each feature point is computed; clustering the feature points on a current frame into one or more clouds based on their appearance and distance; determining a correspondence between the clouds of the current frame and previous frame; classifying the clouds through estimating statistical disparity distribution of each cloud to identify if the respective clouds are new clouds, existing clouds or unknown clouds; and merging the clouds that are determined to be a same object based on the tracking information and changes of disparity of the clouds over time. A system carrying out the above method is also provided herein.

Abstract translation: 本发明提供了一种用于处理通过立体相机拍摄的视频的方法，所述视频具有多个帧，每个帧至少包括左图像和右图像。 该方法包括获取通过加速度计（102）检测到的一对立体摄像机（101）和立体摄像机（101）的加速度信息拍摄的视频; 提取当前帧的右图像和左图像中的特征点; 匹配右图像和左图像之间的特征点，其中计算每个特征点的视差值; 基于它们的外观和距离将当前帧上的特征点聚类成一个或多个云; 确定当前帧的云与先前帧之间的对应关系; 通过估计每个云的统计差异分布来分类云，以确定相应的云是新云，现有云或未知云; 并且根据跟踪信息和随时间推移的云的差异的变化来合并被确定为相同对象的云。 本文还提供了执行上述方法的系统。

公开(公告)号：WO2014092549A2

公开(公告)日：2014-06-19

申请号：PCT/MY2013000256

申请日：2013-12-12

Applicant: MIMOS BERHAD

Inventor： ZULAIKHA BINTI KADIM ,  HON HOCK WOON ,  NORSHUHADA BINTI SAMUDIN

IPC: G06T7/20

CPC classification number: G06T7/285 ,  G06T7/174 ,  G06T7/194 ,  G06T7/215 ,  G06T7/246 ,  G06T7/254 ,  G06T7/73 ,  G06T2207/10021 ,  G06T2207/20221 ,  G06T2207/30232 ,  G06T2207/30244

Abstract: The present invention provides a system and method for processing sequence of image frames captured through an imaging device, the imaging device includes an accelerometer. The system and method comprise an adaptive temporal background subtraction unit and a dynamic foreground object estimation unit for evaluating whether each pixel is either a moving object pixel or a non-moving object pixel based on the classification of the pixels between the first motion map and the second motion map generated thereon.

Abstract translation: 本发明提供了一种用于处理通过成像装置捕获的图像帧的序列的系统和方法，该成像装置包括加速度计。 该系统和方法包括自适应时间背景减法单元和动态前景对象估计单元，用于基于第一运动图和第一运动图像之间的像素的分类来评估每个像素是运动物体像素还是非移动物体像素 在其上生成的第二运动图。

公开(公告)号：WO2014042514A3

公开(公告)日：2014-05-08

申请号：PCT/MY2013000159

申请日：2013-09-06

Applicant: MIMOS BERHAD

Inventor： ZULAIKHA BINTI KADIM ,  NORSHUHADA BINTI SAMUDIN ,  HON HOCK WOON ,  YUEN SHANG LI ,  LIANG KIM MENG

IPC: G06K9/00 ,  G08B13/196

CPC classification number: G06K9/00771 ,  G08B13/19604 ,  G08B29/046

Abstract: The present invention relates to a surveillance system having a method for tampering detection and correction. The surveillance system is able to detect tampering of the camera view and thereon, adjust its video analytics configuration parameters to perform video analytics even though the orientation of the camera (10) has been changed as long as a partial of the ROI is within the tampered camera view. The surveillance system comprises of at least one camera (10), a video acquisition module (20), a storage device (30), an image processing module (40), a display module (50) and a post detection module (60).

Abstract translation: 本发明涉及一种具有用于篡改检测和校正的方法的监视系统。 监视系统能够检测摄像机视图的篡改，并且在摄像机视图之上检测到篡改，调整其视频分析配置参数以执行视频分析，即使摄像机（10）的方向已经改变，只要ROI的一部分在篡改之内 相机视图。 该监控系统包括至少一个摄像头（10），视频采集模块（20），存储设备（30），图像处理模块（40），显示模块（50）和后检测模块（60） 。

公开(公告)号：WO2014038924A2

公开(公告)日：2014-03-13

申请号：PCT/MY2013000154

申请日：2013-09-05

Applicant: MIMOS BERHAD

Inventor： ZULAIKHA BINTI KADIM ,  NORSHUHADA BINTI SAMUDIN ,  DR HON HOCK WOON

CPC classification number: G06T7/277 ,  G06T2207/20081 ,  G06T2207/30232

Abstract: The present invention relates to a novel method for producing a background model based on the images acquired from a non-static camera. Rule-based statistical multiple image analytical method to process multiple non-overlapping background region of a scene using predetermined threshold values to identify the preferred intensity variance for modeling the background pixel. One of the advantages of the a method for modeling dynamic scene using region-based adaptive statistical learning to model dynamic background within one camera view and scene-based modeling to model multiple non-overlapping regions of the background image scene is that it provides an accurate background representation as compared to background modeling using pixel-wise scalar value. Another advantage of the method for the present invention is that a less computational cost is used as compared to background modeling using pixel-wise statistical or kernel density. Furthermore, the method for the present invention has higher sensitive foreground detection as compared to privacy mask concept (masking out dynamic region from being modeled.

Abstract translation: 本发明涉及一种基于从非静态摄像机获得的图像来制作背景模型的新颖方法。 基于规则的统计多图像分析方法，使用预定阈值来处理场景的多个非重叠背景区域，以识别用于建模背景像素的优选强度方差。 使用基于区域的自适应统计学习建模动态场景的一种方法的一个优点是在一个摄像机视图和基于场景的建模中对动态背景进行建模，以模拟背景图像场景的多个非重叠区域，其提供了准确的 与使用像素级标量值的背景建模相比，背景表示。 本发明的方法的另一个优点是与使用像素统计或核密度的背景建模相比，使用较少的计算成本。 此外，与隐私掩码概念相比，本发明的方法具有更高的灵敏度前景检测（掩蔽动态区域被建模。