公开(公告)号：EP2327057A4

公开(公告)日：2017-11-22

申请号：EP09816484

申请日：2009-09-18

Applicant: MIMOS BERHAD

Inventor： LIM MEI KUAN ,  LIANG KIM MENG ,  MAUL TOMAS HENRIQUE ,  LAI WENG KIN

IPC: G06K9/00 ,  G08B13/196

CPC classification number: G06K9/00348 ,  G06K9/00771 ,  G08B13/19615

Abstract: With the growing market for video surveillance in security area, there is a need for an automated system which provides a way to track and detect human intention based on a particular human motion. The present invention relates to a system and a method for identifying human behavioral intention based on effective motion analysis wherein, the system obtains a sequence of raw images taken from live scene and processes the raw images in an activity analysis component. The activity analysis component is further provided with an activity enrollment component and activity detection component.

公开(公告)号：MY159285A

公开(公告)日：2016-12-30

申请号：MYPI2010005660

申请日：2010-11-29

Applicant: MIMOS BERHAD

Inventor： LIM MEI KUAN ,  LIANG KIM MENG ,  LAI WENG KIN ,  ZULAIKHA KADIM ,  NORSHUHADA SAMUDIN ,  MALEEHA KIRAN ,  AHMED A BAHAA

IPC: G06T7/20 ,  G08B13/194 ,  H04N7/18

Abstract: THE PRESENT INVENTION RELATES TO A SYSTEM AND METHOD OF SURVEILLANCE TO DETECT LOITERING EVENT, MORE PARTICULARLY TO A SYSTEM AND METHOD TO DETECT LOITERING EVENTS DURING OCCLUSION, NON-OCCLUSION OR BOTH IN A REGION, WHEREIN THE SYSTEM COMPRISES A SUBTRACTING MEANS (100), A TRACKING MEANS (101), A TIMER MEANS (102), A STORAGE MEANS (103), AND A PROCESSOR (104) ELECTRICALLY COUPLED TO THE STORAGE MEANS (105) FOR PROCESSING THE METHODS OF DETERMINING A LOITERING EVENT.SINCE THE SYSTEM IS ABLE TO DETECT LOITERING EVENTS DURING OCCLUSION AND NON OCCLUSION, A METHOD OF IMPLEMENTING MULTI-TIMER APPROACH IS ADAPTED INTO THE SYSTEM; ADDITIONALLY SAID ADAPTED METHOD IS CAPABLE OF DETECTING OF RE-APPEARING SUBJECTS.

公开(公告)号：MY178647A

公开(公告)日：2020-10-19

申请号：MYPI20093242

申请日：2009-08-05

Applicant: MIMOS BERHAD

Inventor： LIM MEI KUAN ,  LIANG KIM MENG ,  ZULAIKHA KADIM ,  TANG SZE LING

Abstract: A method of producing signals to estimate dimension of an object from a sequence of image is described. It is difficult to determine a real dimension of an object in a two dimensional image. A scale factor map is constructed by using grid and reference object with known dimension to assist in estimating dimension of an object. First, the position of the moving reference object with known dimension in a grid is determined. Then, the scale factor of each position traveled by the reference object in the grid is determined by comparing the real dimension of reference object with projected dimension of reference object. Next, the scale factor of other position in the grid is calculated to construct a scale factor map by interpolation. The compiled scale factor of every position in a grid provides a scale factor map that relatively indicates a scale to be used for a position in the grid to estimate a dimension. The real dimension of a target can be obtained by using the projected dimension of the object and a scale factor at a particular position. Fig. 1

公开(公告)号：MY173744A

公开(公告)日：2020-02-18

申请号：MYPI20092455

申请日：2009-06-15

Applicant: MIMOS BERHAD

Inventor： LIANG KIM MENG ,  ZULAIKHA KADIM ,  AHMED BAHAA AL-DEEN ,  LIM MEI KUAN ,  TANG SZE LING

Abstract: A method to determine point-of-sight from a sequence of image is described with the following steps. First, visual fixation of human is determined from a sequence of image (20). Then, gaze intersection of visual fixation is detected (40). Multiscale weight is then computed (61) which assign weightage to each pixel which reflect the significance of a particular point, assuming that a point nearer to the detected intersection has a higher possibility of being point-of-sight. Every weightage map is next superimposed and new weightage point for every coordinate is accumulated (62). Later, the master point-of-sight map is updated (63) and harmonized (64). A high value of weightage indicates high probability of point-of-sight. Finally, the weightage of each pixel in the master point-of-sight map is analyzed and compared against predefined rules to indicate the level of suspiciousness in the scene and actuate alert accordingly 80.

公开(公告)号：MY173003A

公开(公告)日：2019-12-18

申请号：MYPI20093678

申请日：2009-09-04

Applicant: MIMOS BERHAD

Inventor： LIANG KIM MENG ,  ZULAIKHA KADIM ,  LIM MEI KUAN ,  TANG SZE LING

IPC: A61B3/113

Abstract: A method of providing a signal to predict trajectory path of an object from a sequence of image is described. The image is analyzed by first collecting common paths (16) of a scene. Then, objects entering the scene are analyzed to determine gaze direction of object (50). Later, a frame-based probability of predicted path based on gaze direction of object in each frame (70) is determined. Next, block-based probability of predicted path based on intervals of a number of frames (74) is determined. The trajectory path can be predicted from highest probability and common path (76).

公开(公告)号：MY167109A

公开(公告)日：2018-08-10

申请号：MYPI20095129

申请日：2009-12-02

Applicant: MIMOS BERHAD

Inventor： LIM MEI KUAN ,  LIANG KIM MENG ,  ZULAIKHA KADIM ,  TANG SZE LING

IPC: G06K9/46 ,  G06T7/40

Abstract: A method of identity recognition via human (subject) lip images is proposed. The method includes registration (140) of templates (135) of the lip images for known subjects for later matching with lip images from subjects for identification, by digitally matching (740) with the registered templates (135). The lip portions are divided in four quadrants (410-440) for feature extraction which permits template matching (740) even when only partial Hp images are available for identification. The method includes classifying (220) the lips into categories, for defined characteristic features to be extracted, where the different categories of lips (310-350) contain different prominent features that are unique for representation. The feature extraction from the quadrants may be done in different orientations (610-640). The acquisition of the lip images (110,710) is by available image sensor technologies such as optical imaging, thermal imaging, ultrasonic imaging, passive capacitance and active capacitance imaging.

公开(公告)号：MY159290A

公开(公告)日：2016-12-30

申请号：MYPI2010005760

申请日：2010-12-02

Applicant: MIMOS BERHAD

Inventor： LIM MEI KUAN ,  LIANG KIM MENG ,  YONG YEN SAN ,  CHAU SHEAU WEI

IPC: G06T7/20 ,  H04N7/18

Abstract: THE PRESENT INVENTION RELATES TO A SYSTEM (100) AND A METHOD FOR DETECTING A LOITERING EVENT.THE SYSTEM (100) COMPRISES A MOTION DETECTOR (10) FOR DELINEATING MOTION PIXELS OR FOREGROUND FROM A BACKGROUND OF AN IMAGE SEQUENCE (50); AN OBJECT DETECTOR (20) FOR DETECTING A NEW OBJECT IN AT LEAST ONE REGION-OF-INTEREST (ROL) (60) FROM THE IMAGE SEQUENCE (50); AND AN EVENT DETECTOR (30) FOR DETECTING THE LOITERING EVENT.IN ANOTHER ASPECT OF THE PRESENT INVENTION, THE METHOD COMPRISES THE STEPS OF DELINEATING MOTION PIXELS OR FOREGROUND FROM A BACKGROUND OF AN IMAGE SEQUENCE BY MEANS OF A MOTION DETECTOR (10), DETECTING A NEW OBJECT IN AT LEAST ONE REGION-OF-INTEREST FROM THE IMAGE SEQUENCE (50) BY MEANS OF A OBJECT DETECTOR (20), AND DETECTING THE LOITERING EVENT BY MEANS OF AN EVENT DETECTOR (30).

公开(公告)号：MY158147A

公开(公告)日：2016-09-15

申请号：MYPI2010001363

申请日：2010-03-26

Applicant: MIMOS BERHAD

Inventor： LIANG KIM MENG ,  LIM MEI KUAN ,  TANG SZE LING ,  ZULAIKHA KADIM

IPC: G06T7/20 ,  H04N7/18

Abstract: [0045] THE PRESENT INVENTION PROVIDES A METHOD FOR TRACKING AND CHARACTERIZING MOTION BLOBS. THE METHOD COMPRISES EXTRACTING (110) MOTION BLOBS FROM A PREVIOUS FRAME AND A CURRENT FRAME; COMPUTING (120) RELATIONSHIPS BETWEEN MOTION BLOBS OF THE PREVIOUS FRAME AND THE CURRENT FRAME; COMPUTING RELATIONSHIPS BETWEEN EACH MOTION BLOBS OF THE CURRENT FRAME; COMPUTING (130) AN OBJECT BLOB BASED ON THE RELATIONSHIPS BETWEEN THE MOTION BLOBS OF THE PREVIOUS FRAME AND THE CURRENT FRAME; DETERMINING (140) AN OBJECT BASED ON THE OBJECT BLOB; AND CHARACTERIZING (150) THE OBJECT BASED ON THE RELATIONSHIPS BETWEEN THE MOTION BLOBS OF THE CURRENT FRAME. [0046]

公开(公告)号：MY164004A

公开(公告)日：2017-11-15

申请号：MYPI2010001056

申请日：2010-03-11

Applicant: MIMOS BERHAD

Inventor： TANG SZE LING ,  LIANG KIM MENG ,  LIM MEI KUAN

IPC: G06K9/46 ,  G06T7/20

Abstract: THERE IS PROVIDED A METHOD FOR USE IN HUMAN AUTHENTICATION, SAID METHOD COMPRISING THE STEPS OF: PROVIDING CAPTURED IMAGE SEQUENCES; PROVIDING POSTURE GAITS BASED ON SAID IMAGE SEQUENCES; STORING SAID POSTURE GAITS IN A DATABASE; SUBTRACTING THE BACKGROUND FROM FOREGROUND OF EACH IMAGE SEQUENCE; WHEREIN SAID SUBTRACTING COMPRISES OBTAINING THE FOREGROUND SILHOUETTE IN EACH IMAGE SEQUENCE; CONSTRUCTING SKELETONS BASED ON SAID FOREGROUND SILHOUETTE IMAGE SEQUENCE; WHEREIN EACH OF SAID SKELETONS COMPRISES AT LEAST ONE CENTROID AND AT LEAST THREE (3) EXTREMIS; DETERMINING THE VERTICAL DISTANCES BETWEEN SAID THREE (3) EXTREMIS AND CENTROID; DETERMINING THE HORIZONTAL DISTANCES BETWEEN SAID THREE (3) EXTREMIS AND CENTROID; TRACKING AND IDENTIFYING THE HUMAN OF INTEREST BASED ON MATCHING BETWEEN IMAGE OF HUMAN OF INTEREST STORED DATABASE AND CONSTRUCTED SKELETONS. MOST ILLUSTRATIVE FIGURE(S): FIG 1

公开(公告)号：MY161490A

公开(公告)日：2017-04-14

申请号：MYPI2010005703

申请日：2010-12-01

Applicant: MIMOS BERHAD

Inventor： LIM MEI KUAN ,  LAI WENG KIN ,  CHAN CHEE SENG ,  ZULAIKHA KADIM

IPC: G06K9/00 ,  H04N7/18

Abstract: One embodiment of the present invention provides a system (800) for detecting loitering event in region of interest. Another embodiment of the present invention provides a method (900) for detecting loitering event in region of interest. The method comprising steps of determining presence of at least one object in region of interest (902), tagging each object of interest with identity (904), computing total time stamp for each object of interest (906), determining time span of each object of interest based on trajectory information and speed profile (908), detecting loitering event based on combination of plurality of determining features (910) and triggering alert when loitering event is detected (912).Total timestamp for each object of interest is computed by classifying each object as normal or suspicious by applying plurality of loitering thresholds by further establishing first threshold value TS to determine loitering event depending on time span of each object (1202); determining loitering event when total time span for object ti in region of interest is greater than first threshold value Ts (1204); establishing second threshold value TL to determine loitering event depending on time span status of each object (1206); and determining loitering event when a total time span for object ti in region of interest is greater than second threshold value TL and its trajectory status is abnormal (1208).