-
公开(公告)号：US20140300538A1
公开(公告)日：2014-10-09
申请号：US14247589
申请日：2014-04-08
申请人： COGISEN S.R.L.
CPC分类号： G06F3/013 , G06K9/00335 , G06K9/00597 , G06K9/0061
摘要： 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.
摘要翻译： 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。
-
公开(公告)号：US09811157B2
公开(公告)日：2017-11-07
申请号：US14247589
申请日：2014-04-08
申请人： COGISEN S.R.L.
CPC分类号： G06F3/013 , G06K9/00335 , G06K9/00597 , G06K9/0061
摘要： 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：US10586312B2
公开(公告)日：2020-03-10
申请号：US15899331
申请日：2018-02-19
申请人： COGISEN S.R.L.
IPC分类号： H04N7/12 , G06T5/10 , H04N19/149 , G06T5/00 , H04N19/139
摘要： 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.
-
公开(公告)号：US10540537B2
公开(公告)日：2020-01-21
申请号：US15899301
申请日：2018-02-19
申请人： COGISEN S.R.L.
摘要： 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.
-
-
-
搜索结果
4 条记录 (耗时 0.012 秒)
