Patents by Inventor Sammy Chan
Sammy Chan has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11093754Abstract: A system and method of selecting a frame capturing a short duration action from a video. The method including receiving a sequence of frames of the video; and determining a reference frame in the sequence of frames by detecting a predetermined action captured in one of a first plurality of frames from the sequence of video frames, the first plurality of frames being sampled from the sequence of frames at a first sampling rate lower than that of the sequence of frames. The method further comprises selecting a second plurality of frames from the sequence of frames, the second plurality of frames having a location associated with the reference frame in the sequence and being selected at a second sampling rate, the second sampling rate being higher than the first sampling rate; and selecting the frame capturing the short duration action from the second plurality of frames.Type: GrantFiled: May 8, 2019Date of Patent: August 17, 2021Assignee: Canon Kabushiki KaishaInventors: David Ian Johnston, Mark Ronald Tainsh, Sammy Chan
-
Patent number: 10885346Abstract: A method of selecting frames of a video sequence. Image data for a plurality of consecutive frames of the video sequence is captured using a camera. Frames from the plurality of consecutive frames where the camera is moving are identified using the captured image data, wherein each of the identified frames comprises a subject. A size of the subject captured in each of the identified frames is determined. The identified frames are selected by detecting that the camera is moving towards and with the subject based on the size of the subject within each of a plurality of the identified frames.Type: GrantFiled: October 5, 2018Date of Patent: January 5, 2021Assignee: Canon Kabushiki KaishaInventors: Mark Ronald Tainsh, Rajanish Calisa, Sammy Chan
-
Patent number: 10650242Abstract: An information processing apparatus includes at least one processor causing the information processing apparatus to act as a first obtainment unit configured to execute processing for obtaining a first feature amount for each of a plurality of frames, a specification unit configured to specify a priority order of frames for obtaining a second feature amount different from the first feature amount based on the first feature amount obtained by the first obtainment unit, a second obtainment unit configured to execute processing for obtaining the second feature amount from a frame in accordance with the priority order, and a selection unit configured to select, based on the second feature amount obtained by the second obtainment unit, an image processing target frame. The number of frames from which the second feature amount is obtained is fewer than the number of the plurality of frames from which the first feature amount is obtained.Type: GrantFiled: November 22, 2017Date of Patent: May 12, 2020Assignee: Canon Kabushiki KaishaInventors: Tatsuya Yamamoto, Sammy Chan
-
Patent number: 10546208Abstract: A method of selecting at least one video frame of a video sequence comprising a plurality of video frames. The method determines a time for analysis based on length of the video sequence and processing capability of a running device. A first sampling pattern is based on the determined time for analysis. A first set of frames in the video sequence is sampled using a first sampling pattern. The first set is sampled infrequently throughout the video sequence in accordance with the first sampling pattern. A candidate frame is determined from the sampled frames based on image quality. A second set of the frames comprising one or more of the frames in a narrow range of the video sequence near the determined candidate frame, is determined in accordance with a second sampling pattern. At least one of the video frames is selected from the sampled frames based on image quality.Type: GrantFiled: September 25, 2017Date of Patent: January 28, 2020Assignee: Canon Kabushiki KaishaInventors: Sammy Chan, Ian Robert Boreham, Ka Ming Leung, Mark Ronald Tainsh
-
Patent number: 10536625Abstract: When a first frame included in a moving image satisfies a predetermined condition about a predetermined feature quantity, a second frame is analyzed and a candidate frame is selected from the first frame and the second frame as a candidate of an output target based on a result of analysis of the first frame and a result of analysis of the second frame.Type: GrantFiled: December 5, 2017Date of Patent: January 14, 2020Assignee: Canon Kabushiki KaishaInventors: Shigeki Hirooka, Satoru Mamiya, Sammy Chan
-
Publication number: 20190377957Abstract: A system and method of selecting a frame capturing a short duration action from a video. The method including receiving a sequence of frames of the video; and determining a reference frame in the sequence of frames by detecting a predetermined action captured in one of a first plurality of frames from the sequence of video frames, the first plurality of frames being sampled from the sequence of frames at a first sampling rate lower than that of the sequence of frames. The method further comprises selecting a second plurality of frames from the sequence of frames, the second plurality of frames having a location associated with the reference frame in the sequence and being selected at a second sampling rate, the second sampling rate being higher than the first sampling rate; and selecting the frame capturing the short duration action from the second plurality of frames.Type: ApplicationFiled: May 8, 2019Publication date: December 12, 2019Inventors: DAVID IAN JOHNSTON, MARK RONALD TAINSH, SAMMY CHAN
-
Patent number: 10372994Abstract: A method of selecting at least one video frame of a video sequence. A plurality of faces is detected in at least one video frame of the video sequence. An orientation of the detected faces is tracked over a series of subsequent video frames to determine whether a first detected face is turning towards a second detected face. The method then determines, using the tracked orientation of the detected faces, a portion of the video sequence in which the first and second detected faces are oriented towards each other for at least a predetermined number of frames defining a gaze fixation of the detected faces. At least one video frame is selected from the determined portion of the video sequence, the selected video frame capturing the gaze fixation of the detected faces.Type: GrantFiled: May 2, 2017Date of Patent: August 6, 2019Assignee: Canon Kabushiki KaishaInventors: Sammy Chan, Ka Ming Leung, Mark Ronald Tainsh
-
Patent number: 10318816Abstract: Generating a plurality of event clusters by segmenting an image set. Each event cluster includes at least one image from the image set. The image set, having time metadata corresponding to each image in the set, is accessed. A time interval between each pair of neighboring images in the image set is determined. The neighboring images in each of the pairs are adjacent in a time ordered sequence. The time interval for each of the pairs is determined from time metadata associated with each image in the pair. An adjustment value is determined for one or more of the determined time intervals based on at least one of predetermined time of day information and calendar information. The images in the image set are segmented to generate the plurality of event clusters. Segmentation boundaries for each event cluster are determined using at least the determined adjustment value.Type: GrantFiled: June 23, 2016Date of Patent: June 11, 2019Assignee: Canon Kabushiki KaishaInventors: Mark Ronald Tainsh, Alex Penev, Sammy Chan
-
Patent number: 10275652Abstract: In an information processing method, the importance degree of each person who appears in a first image group and the importance degree of each person who appears in a second image group, containing the first image group, are determined, and, when selecting the image of the output target from the first image group, in a case in which the importance degree of a candidate image of the output target included in the first image group, which is determined from the appearance count in the first image group, exceeds a first threshold, and, in a case in which the importance degree of the candidate image of the output target, which is determined from the appearance count in the second image group, exceeds a second threshold, the candidate image is selected as the output target.Type: GrantFiled: July 26, 2016Date of Patent: April 30, 2019Assignee: Canon Kabushiki KaishaInventors: Tatsuya Yamamoto, Fumitaka Goto, Hiroyasu Kunieda, Sammy Chan
-
Publication number: 20190108402Abstract: A method of selecting frames of a video sequence. Image data for a plurality of consecutive frames of the video sequence is captured using a camera. Frames from the plurality of consecutive frames where the camera is moving are identified using the captured image data, wherein each of the identified frames comprises a subject. A size of the subject captured in each of the identified frames is determined. The identified frames are selected by detecting that the camera is moving towards and with the subject based on the size of the subject within each of a plurality of the identified frames.Type: ApplicationFiled: October 5, 2018Publication date: April 11, 2019Inventors: MARK RONALD TAINSH, RAJANISH CALISA, SAMMY CHAN
-
Publication number: 20180167552Abstract: When a first frame included in a moving image satisfies a predetermined condition about a predetermined feature quantity, a second frame is analyzed and a candidate frame is selected from the first frame and the second frame as a candidate of an output target based on a result of analysis of the first frame and a result of analysis of the second frame.Type: ApplicationFiled: December 5, 2017Publication date: June 14, 2018Inventors: Shigeki Hirooka, Satoru Mamiya, Sammy Chan
-
Publication number: 20180165521Abstract: Processing for obtaining a first feature amount for each of a plurality of frames is executed, and target frames for obtaining a second feature amount for which an obtainment time with respect to one frame is longer than for the first feature amount are specified on the basis of the obtained first feature amount. Processing for obtaining the second feature amount from the specified frames is executed, and image processing target frames are selected on the basis of the obtained second feature amount.Type: ApplicationFiled: November 22, 2017Publication date: June 14, 2018Inventors: Tatsuya Yamamoto, Sammy Chan
-
Patent number: 9990666Abstract: A method of delivering a recommendation is disclosed. A preference rating is received for each of a plurality of electronic devices based on a task to be recommended, each of the preference ratings defining a preference to perform the recommended task on a corresponding one of the electronic devices. A timeliness profile associated with the recommendation is received. The timeliness profile defines relevance of delivering the recommendation over a period of time. One of the electronic devices on which to deliver the recommendation at a particular point in time is selected based on a function of the preference rating of the selected electronic device and the timeliness profile associated with the recommendation at that point in time.Type: GrantFiled: September 10, 2013Date of Patent: June 5, 2018Assignee: CANON KABUSHIKI KAISHAInventors: IJ Eric Wang, Sammy Chan, Mark Ronald Tainsh, Nicholas Grant Fulton
-
Publication number: 20180089528Abstract: A method of selecting at least one video frame of a video sequence comprising a plurality of video frames. The method determines a time for analysis based on length of the video sequence and processing capability of a running device. A first sampling pattern is based on the determined time for analysis. A first set of frames in the video sequence is sampled using a first sampling pattern. The first set is sampled infrequently throughout the video sequence in accordance with the first sampling pattern. A candidate frame is determined from the sampled frames based on image quality. A second set of the frames comprising one or more of the frames in a narrow range of the video sequence near the determined candidate frame, is determined in accordance with a second sampling pattern. At least one of the video frames is selected from the sampled frames based on image quality.Type: ApplicationFiled: September 25, 2017Publication date: March 29, 2018Inventors: SAMMY CHAN, IAN ROBERT BOREHAM, KA MING LEUNG, MARK RONALD TAINSH
-
Publication number: 20170330038Abstract: A method of selecting at least one video frame of a video sequence. A plurality of faces is detected in at least one video frame of the video sequence. An orientation of the detected faces is tracked over a series of subsequent video frames to determine whether a first detected face is turning towards a second detected face. The method then determines, using the tracked orientation of the detected faces, a portion of the video sequence in which the first and second detected faces are oriented towards each other for at least a predetermined number of frames defining a gaze fixation of the detected faces. At least one video frame is selected from the determined portion of the video sequence, the selected video frame capturing the gaze fixation of the detected faces.Type: ApplicationFiled: May 2, 2017Publication date: November 16, 2017Inventors: SAMMY CHAN, KA MING LEUNG, MARK RONALD TAINSH
-
Publication number: 20170039427Abstract: In an information processing method, the importance degree of each person who appears in a first image group and the importance degree of each person who appears in a second image group containing the first image group are determined, and when selecting the image of the output target from the first image group, in a case in which the importance degree of a candidate image of the output target included in the first image group, which is determined from the appearance count in the first image group, exceeds a first threshold and in a case in which the importance degree of the candidate image of the output target, which is determined from the appearance count in the second image group, exceeds a second threshold, the candidate image is selected as the output target.Type: ApplicationFiled: July 26, 2016Publication date: February 9, 2017Inventors: Tatsuya Yamamoto, Fumitaka Goto, Hiroyasu Kunieda, Sammy Chan
-
Publication number: 20160379058Abstract: A method of segmenting an image set to generate a plurality of event clusters. Each event cluster includes at least one image from the image set. The image set, having time metadata corresponding to each image in the set, is accessed. A time interval between each pair of neighbouring images in the image set is determined. The neighbouring images in each of the pairs are adjacent in a time ordered sequence. The time interval for each of the pairs is determined from time metadata associated with each image in the pair. An adjustment value is determined for one or more of the determined time intervals based on at least one of predetermined time of day information and calendar information. The images in the image set are segmented to generate the plurality of event clusters. Segmentation boundaries for each event cluster are determined using at least the determined adjustment value.Type: ApplicationFiled: June 23, 2016Publication date: December 29, 2016Inventors: Mark Ronald TAINSH, Alex PENEV, Sammy CHAN
-
Patent number: 8738622Abstract: Methods (105), apparatuses (600), and computer readable storage mediums for processing captured images having geolocations related to the captured images at the time of capture are disclosed. A representative geolocation is associated (110) with each group of images previously captured at the same location. For each representative geolocation, based on at least the timestamp of the images associated with the representative geolocation, the probability is determined (120) that a further image will be captured at or near the representative geolocation. For representative geolocations with a determined probability above a predetermined threshold, the respective representative geolocation is associated (130) with at least one personal place.Type: GrantFiled: December 1, 2010Date of Patent: May 27, 2014Assignee: Canon Kabushiki KaishaInventor: Sammy Chan
-
Publication number: 20140074653Abstract: A method of delivering a recommendation is disclosed. A preference rating is received for each of a plurality of electronic devices based on a task to be recommended, each of the preference ratings defining a preference to perform the recommended task on a corresponding one of the electronic devices. A timeliness profile associated with the recommendation is received. The timeliness profile defines relevance of delivering the recommendation over a period of time. One of the electronic devices on which to deliver the recommendation at a particular point in time is selected based on a function of the preference rating of the selected electronic device and the timeliness profile associated with the recommendation at that point in time.Type: ApplicationFiled: September 10, 2013Publication date: March 13, 2014Applicant: CANON KABUSHIKI KAISHAInventors: lJ Eric WANG, Sammy CHAN, Mark Ronald TAINSH, Nicholas Grant FULTON
-
Patent number: 7983159Abstract: An active queue management (AQM) process for network communications equipment. The AQM process is queue based and involves applying at a queue size threshold congestion notification to communications packets in a queue of a link via packet dropping; and adjusting said queue size threshold on the basis of the congestion level. The AQM process releases more buffer capacity to accommodate more incoming packets by increasing said queue size threshold when congestion increases; and decreases buffer capacity by reducing said queue size threshold when congestion decreases. Network communications equipment includes a switch component for switching communications packets between input ports and output ports, packet queues for at least the output ports, and an active queue manager for applying congestion notification to communications packets in the queues for the output ports via packet dropping.Type: GrantFiled: April 12, 2010Date of Patent: July 19, 2011Assignee: Intellectual Ventures Holding 57 LLCInventors: Jinshen Sun, King-Tim Ko, Guanrong Chen, Sammy Chan, Moshe Zukerman