-
公开(公告)号：US20200242355A1
公开(公告)日：2020-07-30
申请号：US16649566
申请日：2017-11-29
Applicant: Intel Corporation
Inventor： Tae-Hoon Kim , Minje Park
Abstract: Methods and apparatus to convert images for computer-vision systems are disclosed. An example computer-vision system includes an image converter (112) to convert a near infrared light first image (202) to form a visible light image (206), and to update a coefficient of the image converter (112) based on a difference (214), an object recognizer (102) to recognize an object (208) in the first visible light image (206), and an object recognition analyzer (210) to determine the difference (214) between the object (208) recognized in the first visible light image (206) and an object (212) associated with the near infrared light image (202).
-
2.发明申请公开(公告)号：US20190188555A1
公开(公告)日：2019-06-20
申请号：US16284186
申请日：2019-02-25
Applicant: Intel Corporation
Inventor： Byungseok Roh , Hyunjoon Lee , Seok-Yong Byun , Minje Park
CPC classification number: G06N3/04 , G06K9/6267 , G06N3/082
Abstract: Systems, apparatuses and methods may provide for technology that generates, by a full inference path of a neural network, a first detection result associated with one or more objects in a first video frame. The technology may also generate, by a partial inference path of the neural network, a second detection result based on the first detection result, wherein the second detection result corresponds to a second video frame that is subsequent to the first video frame.
-
3.发明申请公开(公告)号：US20180165551A1
公开(公告)日：2018-06-14
申请号：US15372953
申请日：2016-12-08
Applicant: Intel Corporation
Inventor： Byungseok Roh , Kye-Hyeon Kim , Sanghoon Hong , Minje Park , Yeongjae Cheon
CPC classification number: G06K9/3233 , G06K9/4628 , G06N3/0454
Abstract: Technologies for multi-scale object detection include a computing device including a multi-layer convolution network and a multi-scale region proposal network (RPN). The multi-layer convolution network generates a convolution map based on an input image. The multi-scale RPN includes multiple RPN layers, each with a different receptive field size. Each RPN layer generates region proposals based on the convolution map. The computing device may include a multi-scale object classifier that includes multiple region of interest (ROI) pooling layers and multiple associated fully connected (FC) layers. Each ROI pooling layer has a different output size, and each FC layer may be trained for an object scale based on the output size of the associated ROI pooling layer. Each ROI pooling layer may generate pooled ROIs based on the region proposals and each FC layer may generate object classification vectors based on the pooled ROIs. Other embodiments are described and claimed.
-
4.发明申请FACILITATING EFFICEINT FREE IN-PLANE ROTATION LANDMARK TRACKING OF IMAGES ON COMPUTING DEVICES 审中-公开在计算机设备上实现图像的免费平面图旋转朗读跟踪公开(公告)号：US20160300099A1
公开(公告)日：2016-10-13
申请号：US14762687
申请日：2014-09-25
Applicant: INTEL CORPORATION
Inventor： SHEN XIAOLU , Yangzhou Du , Minje Park , Yeongjae Cheon , Olivier Duchenne , Tae-Hoon Kim
Abstract: A mechanism is described for facilitating efficient free in-plane rotation landmark tracking of images on computing devices according to one embodiment. A method of embodiments, as described herein, includes detecting a first frame having a first image and a second frame having a second image, where the second image is rotated to a position away from the first image. The method may further include assigning a first parameter line and a second parameter line to the second image based on landmark positions associated with the first and second images, detecting a rotation angle between the first parameter line and the second parameter line, and rotating the second image back and forth within a distance associated with the rotation angle to verify positions of the first and second images.
Abstract translation: 描述了根据一个实施例的用于促进计算设备上的图像的有效的自由面内旋转地标跟踪的机构。 如本文所述的实施例的方法包括检测具有第一图像的第一帧和具有第二图像的第二帧，其中第二图像旋转到远离第一图像的位置。 该方法还可以包括基于与第一和第二图像相关联的界标位置向第二图像分配第一参数线和第二参数线，检测第一参数线和第二参数线之间的旋转角度，以及旋转第二参数线 在与旋转角度相关联的距离内来回显示图像，以验证第一和第二图像的位置。
-
公开(公告)号：US20210056746A1
公开(公告)日：2021-02-25
申请号：US16987707
申请日：2020-08-07
Applicant: Intel Corporation
Inventor： Yikai Fang , Yangzhou Du , Qiang Eric Li , Xiaofeng Tong , Wenlong Li , Minje Park , Myung-Ho Ju , Jihyeon Kate Yi , Tae-Hoon Pete Kim
Abstract: Examples of systems and methods for augmented facial animation are generally described herein. A method for mapping facial expressions to an alternative avatar expression may include capturing a series of images of a face, and detecting a sequence of facial expressions of the face from the series of images. The method may include determining an alternative avatar expression mapped to the sequence of facial expressions, and animating an avatar using the alternative avatar expression.
-
Patent Agency Ranking
公开(公告)号：US09898849B2
公开(公告)日：2018-02-20
申请号：US14775324
申请日：2014-11-05
Applicant: Intel Corporation
Inventor： Yangzhou Du , Wenlong Li , Qiang Li , Xiaofeng Tong , Tae-Hoon Kim , Minje Park
CPC classification number: G06T13/40 , G06F17/2785 , G06K9/00248 , G06K9/00281 , G06K9/00308 , G06T13/205 , G10L25/48
Abstract: Apparatuses, methods and storage medium associated with creating an avatar video are disclosed herein. In embodiments, the apparatus may one or more facial expression engines, an animation-rendering engine, and a video generator. The one or more facial expression engines may be configured to receive video, voice and/or text inputs, and, in response, generate a plurality of animation messages having facial expression parameters that depict facial expressions for a plurality of avatars based at least in part on the video, voice and/or text inputs received. The animation-rendering engine may be configured to receive the one or more animation messages, and drive a plurality of avatar models, to animate and render the plurality of avatars with the facial expression depicted. The video generator may be configured to capture the animation and rendering of the plurality of avatars, to generate a video. Other embodiments may be described and/or claimed.
-
公开(公告)号：US09684830B2
公开(公告)日：2017-06-20
申请号：US14541631
申请日：2014-11-14
Applicant: Intel Corporation
Inventor： Tae-Hoon Kim , Minje Park
CPC classification number: G06K9/00624 , G06K9/3241 , G06K9/46 , G06K9/6201 , G06K2009/3291 , G06T7/20 , H04N5/232 , H04N7/18
Abstract: Techniques related to automatic target object selection from multiple tracked objects for imaging devices are discussed. Such techniques may include generating one or more object selection metrics such as accumulated distances from frame center, accumulated velocities, and trajectory comparisons of predicted to actual trajectories for tracked objects and selecting the target object based on the object selection metric or metrics.
-
8.发明授权Method, apparatus and computer-readable recording medium for managing images in image database 有权用于管理图像数据库中的图像的方法，装置和计算机可读记录介质公开(公告)号：US09471603B2
公开(公告)日：2016-10-18
申请号：US14129328
申请日：2013-02-15
Applicant: INTEL CORPORATION
Inventor： Tae-Hoon Kim , Minje Park
CPC classification number: G06F17/30277 , G06F17/30247 , G06F17/3028
Abstract: Managing images in an image database is described, comprising: when a query image is input, performing a match to determine whether an image similar to the query image exists within the database by comparing the images stored in the database with the query image; and if the image similar to the query image is a recognized image, providing at least one image in an image group to which the recognized image belongs and information thereon as a result, and if the image similar to the query image is an unrecognized image, providing at least one image in an image group to which the unrecognized image belongs as a result. When at least one image of the image group including the image similar to the query image is a recognized image, information on the corresponding recognized image is assigned to the images in the image group and provided as a result.
Abstract translation: 描述管理图像数据库中的图像，包括：当输入查询图像时，通过将存储在数据库中的图像与查询图像进行比较，执行匹配以确定与查询图像相似的图像是否存在于数据库内; 并且如果与查询图像类似的图像是识别的图像，则在所识别的图像所属的图像组中提供至少一个图像，并且在其上提供关于其的信息，并且如果与查询图像相似的图像是无法识别的图像， 作为结果，在不能识别的图像所属的图像组中提供至少一个图像。 当包括与查询图像相似的图像的图像组的至少一个图像是识别的图像时，关于相应的识别图像的信息被分配给图像组中的图像并作为结果。
-
公开(公告)号：US20160132718A1
公开(公告)日：2016-05-12
申请号：US14535133
申请日：2014-11-06
Applicant: Intel Corporation
Inventor： Minje Park , Hyungsoo Lee , Hongmo Je , Tae-Hoon Kim , Yeongjae Cheon , Taesup Kim
CPC classification number: G06K9/3275 , G06K9/00248
Abstract: Computer-readable storage media, computing devices and methods are discussed herein. In embodiments, a computing device may be configured to perform facial recognition based on gradient based feature extractions of images of faces. In embodiments, the computing device may be configured to determine directional matching patterns of the images from the gradient based feature extraction and may utilize these directional matching patterns in performing a facial recognition analysis of the images of faces. Other embodiments may be described and/or claimed.
Abstract translation: 本文讨论了计算机可读存储介质，计算设备和方法。 在实施例中，计算设备可以被配置为基于面部图像的基于梯度的特征提取来执行面部识别。 在实施例中，计算设备可以被配置为从基于梯度的特征提取来确定图像的方向匹配模式，并且可以在对面部图像执行面部识别分析时利用这些方向匹配模式。 可以描述和/或要求保护其他实施例。
-
公开(公告)号：US11295502B2
公开(公告)日：2022-04-05
申请号：US16987707
申请日：2020-08-07
Applicant: Intel Corporation
Inventor： Yikai Fang , Yangzhou Du , Qiang Eric Li , Xiaofeng Tong , Wenlong Li , Minje Park , Myung-Ho Ju , Jihyeon Kate Yi , Tae-Hoon Pete Kim
Abstract: Examples of systems and methods for augmented facial animation are generally described herein. A method for mapping facial expressions to an alternative avatar expression may include capturing a series of images of a face, and detecting a sequence of facial expressions of the face from the series of images. The method may include determining an alternative avatar expression mapped to the sequence of facial expressions, and animating an avatar using the alternative avatar expression.
-
-
-
-
-
-
-
-
-
Search Results
36
records
(took 0.016 seconds)
