-
公开(公告)号：US20180239952A1
公开(公告)日：2018-08-23
申请号：US15899301
申请日：2018-02-19
Applicant: COGISEN S.R.L.
Inventor： Christiaan Erik RIJNDERS
Abstract: A method for content detection to be carried out by an electronic processing unit, based either on images or on a digital video stream of images, the images being defined by a single frame or by sequences of frames of said video stream, with the aim of enhancing and then isolating the frequency domain signals representing a content to be identified, and decreasing or ignoring the frequency domain noise with respect to the content within the images or the video stream, comprising the steps of: obtaining a digital image or a sequence of digital images from either a corresponding single frame or a corresponding sequence of frames of said video stream, all the digital images being defined in a spatial domain; selecting one or more pairs of sparse zones, each covering at least a portion of said single frame or at least two frames of said sequence of frames, each pair of sparse zones generating a feature, each zone being defined by two sequences of spatial data; transforming the selected features into frequency domain data by combining, for each zone, said two sequences of spatial data through a 2D variation of an L-transformation, varying the transfer function, shape and direction of the frequency domain data for each zone, thus generating a normalized complex vector for each of said features; combining all said normalized complex vectors to define a model of the content to be identified, usable as an input for a content classifier. The advantage being that current detection methods are given better input data, faster calculations and especially a much increased ability to generate models which capture temporal data in video streams.
-
公开(公告)号：US10586312B2
公开(公告)日：2020-03-10
申请号：US15899331
申请日：2018-02-19
Applicant: COGISEN S.R.L.
Inventor： Christiaan Erik Rijnders
IPC: H04N7/12 , G06T5/10 , H04N19/149 , G06T5/00 , H04N19/139
Abstract: A method for video compression through image processing and object detection, based on images or a digital video stream of images, to enhance and isolate frequency domain signals representing content to be identified, and decrease or ignore frequency domain noise with respect to the content. A digital image or sequence of digital images defined in a spatial domain are obtained. One or more pairs of sparse zones are selected, each pair generating a selected feature, each zone defined by two sequences of spatial data. The selected features are transformed into frequency domain data. The transfer function, shape and direction of the frequency domain data are varied for each zone, thus generating a normalized complex vector for each feature. The normalized complex vectors are then combined to define a model of the content to be identified.
-
Patent Agency Ranking
公开(公告)号：US10540537B2
公开(公告)日：2020-01-21
申请号：US15899301
申请日：2018-02-19
Applicant: COGISEN S.R.L.
Inventor： Christiaan Erik Rijnders
Abstract: A method for content detection based on images or a digital video stream of images, to enhance and isolate frequency domain signals representing content to be identified, and decrease or ignore frequency domain noise with respect to the content. A digital image or sequence of digital images defined in a spatial domain are obtained. One or more pairs of sparse zones are selected, each pair generating a feature, each zone defined by two sequences of spatial data. The selected features are transformed into frequency domain data. The transfer function, shape and direction of the frequency domain data are varied for each zone, thus generating a normalized complex vector for each feature. The normalized complex vectors are then combined to define a model of the content to be identified.
-
公开(公告)号：US20180240221A1
公开(公告)日：2018-08-23
申请号：US15899331
申请日：2018-02-19
Applicant: COGISEN S.R.L.
Inventor： Christiaan Erik RIJNDERS
IPC: G06T5/10 , H04N19/149 , H04N19/139 , G06T5/00
Abstract: A method for video compression through image processing and object detection, to be carried out by an electronic processing unit, based either on images or on a digital video stream of images, the images being defined by a single frame or by sequences of frames of said video stream, with the aim of enhancing and then isolating the frequency domain signals representing a content to be identified, and decreasing or ignoring the frequency domain noise with respect to the content within the images or the video stream, comprises the steps of: obtaining a digital image or a sequence of digital images from either a corresponding single frame or a corresponding sequence of frames of said video stream, all the digital images being defined in a spatial domain; selecting one or more pairs of sparse zones, each covering at least a portion of said single frame or at least two frames of said sequence of frames, each pair of sparse zones generating a selected feature, each zone being defined by two sequences of spatial data; transforming the selected features into frequency domain data by combining, for each zone, said two sequences of spatial data through a 2D variation of an L-transformation, varying the transfer function, shape and direction of the frequency domain data for each zone, thus generating a normalized complex vector for each of said selected features; combining all said normalized complex vectors to define a model of the content to be identified; and inputting that model from said selected features in a classifier, therefore obtaining the data for object detection or visual saliency to use for video compression.
-
公开(公告)号：US09811157B2
公开(公告)日：2017-11-07
申请号：US14247589
申请日：2014-04-08
Applicant: COGISEN S.R.L.
Inventor： Christiaan Erik Rijnders
CPC classification number: G06F3/013 , G06K9/00335 , G06K9/00597 , G06K9/0061
Abstract: A method for gaze tracking achieves high performances at the same time requiring both limited processor engagement and reduced power, so as to be particularly but not exclusively fit for mobile uses is described. The method includes the steps of: obtaining a digital video stream of a face through a camera, wherein eyes or pupils are identified in corresponding boxes in the spatial domain, the size thereof being function of the face position and orientation relative to said camera, the content of the boxes being the input for the further calculations; transferring the content of the boxes to the frequency domain; applying to the boxes transferred to the frequency domain one or more sparse zones, covering together a fraction of the boxed area transferred to the frequency domain, and a filtering kernel, at least partially overlapping the sparse zones; performing a multiplication between the frequency data within each sparse zone and the kernel, combining the results in a single value for each sparse zone; and repeating the above steps obtaining for each frame said single value, fluctuation of the single value being representative of gaze direction changes along time.
-
公开(公告)号：US20180032135A1
公开(公告)日：2018-02-01
申请号：US15720355
申请日：2017-09-29
Applicant: COGISEN S.R.L.
Inventor： Christiaan Erik RIJNDERS
CPC classification number: G06F3/013 , G06K9/00335 , G06K9/00597 , G06K9/0061
Abstract: A method for gaze tracking achieves high performances at the same time requiring both limited processor engagement and reduced power, so as to be particularly but not exclusively fit for mobile uses is described. The method includes the steps of: obtaining a digital video stream of a face through a camera, wherein eyes or pupils are identified in corresponding boxes in the spatial domain, the size thereof being function of the face position and orientation relative to said camera, the content of the boxes being the input for the further calculations; transferring the content of the boxes to the frequency domain; applying to the boxes transferred to the frequency domain one or more sparse zones, covering together a fraction of the boxed area transferred to the frequency domain, and a filtering kernel, at least partially overlapping the sparse zones; performing a multiplication between the frequency data within each sparse zone and the kernel, combining the results in a single value for each sparse zone; and repeating the above steps obtaining for each frame said single value, fluctuation of the single value being representative of gaze direction changes along time.
-
公开(公告)号：US20140300538A1
公开(公告)日：2014-10-09
申请号：US14247589
申请日：2014-04-08
Applicant: COGISEN S.R.L.
Inventor： Christiaan Erik RIJNDERS
CPC classification number: G06F3/013 , G06K9/00335 , G06K9/00597 , G06K9/0061
Abstract: A method for gaze tracking achieves high performances at the same time requiring both limited processor engagement and reduced power, so as to be particularly but not exclusively fit for mobile uses is described. The method includes the steps of: obtaining a digital video stream of a face through a camera, wherein eyes or pupils are identified in corresponding boxes in the spatial domain, the size thereof being function of the face position and orientation relative to said camera, the content of the boxes being the input for the further calculations; transferring the content of the boxes to the frequency domain; applying to the boxes transferred to the frequency domain one or more sparse zones, covering together a fraction of the boxed area transferred to the frequency domain, and a filtering kernel, at least partially overlapping the sparse zones; performing a multiplication between the frequency data within each sparse zone and the kernel, combining the results in a single value for each sparse zone; and repeating the above steps obtaining for each frame said single value, fluctuation of the single value being representative of gaze direction changes along time.
Abstract translation: 描述了注视追踪的方法，同时要求有限的处理器接合和降低功率的高性能，因此特别但非完全适用于移动用途。 该方法包括以下步骤：通过相机获得面部的数字视频流，其中在空间域中的相应框中识别眼睛或瞳孔，其尺寸是相对于所述相机的脸部位置和取向的函数， 框的内容是进一步计算的输入; 将盒子的内容传送到频域; 应用于传输到频域的一个或多个稀疏区域的盒子，将传送到频域的盒区域的一部分覆盖在一起，并且至少部分地与稀疏区域重叠的过滤核; 执行每个稀疏区域内的频率数据与内核之间的乘法，将每个稀疏区域的单个值合并结果; 并且重复上述步骤获得每个帧所述单个值，代表注视方向的单个值的波动随时间变化。
-
-
-
-
-
-
Search Results
7
records
(took 0.012 seconds)
