-
公开(公告)号：US20190220653A1
公开(公告)日：2019-07-18
申请号：US15869342
申请日：2018-01-12
Applicant: QUALCOMM Incorporated
Inventor： Lei Wang , Ning Bi , Yingyong Qi
Abstract: Methods, systems, and devices for object recognition are described. Generally, the described techniques provide for a compact and efficient convolutional neural network (CNN) model for facial recognition. The proposed techniques relate to a light model with a set of layers of convolution and one fully connected layer for feature representation. A new building block of for each convolution layer is proposed. A maximum feature map (MFM) operation may be employed to reduce channels (e.g., by combining two or more channels via maximum feature selection within the channels). Depth-wise separable convolution may be employed for computation reduction (e.g., reduction of convolution computation). Batch normalization may be applied to normalize the output of the convolution layers and the fully connected layer (e.g., to prevent overfitting). The described techniques provide a compact and efficient CNN model which can be used for efficient and effective face recognition.
-
公开(公告)号：US10325391B2
公开(公告)日：2019-06-18
申请号：US15357486
申请日：2016-11-21
Applicant: QUALCOMM Incorporated
Inventor： Bijan Forutanpour , Phi Hung Le Nguyen , Ning Bi
Abstract: Techniques are described related to generating image content. A graphics processing unit (GPU) is configured to receive a first set of images generated from a first camera device in a first location, the first camera device having a first orientation, render for display the first set of images oriented to an orientation reference, receive a second, different set of images generated from a second, different camera device in a second, different location, the second camera device having a second orientation, the second orientation being different than the first orientation, and render for display the second set of images oriented to the orientation reference.
-
公开(公告)号：US10268895B2
公开(公告)日：2019-04-23
申请号：US15973114
申请日：2018-05-07
Applicant: QUALCOMM Incorporated
Abstract: Techniques and systems are provided for maintaining blob trackers for one or more video frames. For example, a blob tracker is identified for a current video frame. The blob tracker is associated with a blob detected for the current video frame. The blob includes pixels of at least a portion of one or more objects in the current video frame. A current characteristic of pixels in a region of the current video frame associated with the blob tracker is determined. A previous characteristic of pixels in a region of a previous video frame associated with the blob tracker is also determined. A difference is determined between the current characteristic and the previous characteristic, and a status of the blob tracker is determined based on the determined difference. The status of the blob tracker indicating whether to maintain the blob tracker for the one or more video frames.
-
公开(公告)号：US10140718B2
公开(公告)日：2018-11-27
申请号：US15384802
申请日：2016-12-20
Applicant: QUALCOMM Incorporated
Inventor： Ying Chen , Lei Wang , Jinglun Gao , Ning Bi
Abstract: Techniques and systems are provided for processing video data. For example, techniques and systems are provided for maintaining blob trackers for one or more video frames. A blob tracker can be associated with a blob generated for a video frame. The blob includes pixels of at least a portion of one or more foreground objects in the video frame. The blob tracker can be determined to be a first type of tracker or a second type of tracker. A first type of tracker has a first bounding box and a second bounding box with an overlapping ratio greater than an alignment threshold for the first type of tracker. A second type of tracker has an irregular size change or an irregular motion change over a threshold duration. The blob tracker can be removed from the plurality of blob trackers maintained for the one or more video frames when the blob tracker is the first type of tracker or the second type of tracker.
-
公开(公告)号：US10115005B2
公开(公告)日：2018-10-30
申请号：US15384997
申请日：2016-12-20
Applicant: QUALCOMM Incorporated
Inventor： Jinglun Gao , Ying Chen , Lei Wang , Ning Bi
Abstract: Techniques and systems are provided for processing video data. For example, techniques and systems are provided for performing context-aware object or blob tracker updates (e.g., by updating a motion model of a blob tracker). In some cases, to perform a context-aware blob tracker update, a blob tracker is associated with a first blob. The first blob includes pixels of at least a portion of one or more foreground objects in one or more video frames. A split of the first blob and a second blob in a current video frame can be detected, and a motion model of the blob tracker is reset in response to detecting the split of the first blob and the second blob. In some cases, a motion model of a blob tracker associated with a merged blob is updated to include a predicted location of the blob tracker in a next video frame. The motion model can be updated by using a previously predicted location of blob tracker as the predicted location of the blob tracker in the next video frame in response to the blob tracker being associated with the merged blob. The previously predicted location of the blob tracker can be determined using a blob location of a blob from a previous video frame.
-
Patent Agency Ranking
公开(公告)号：US20180295428A1
公开(公告)日：2018-10-11
申请号：US15758881
申请日：2015-09-25
Applicant: QUALCOMM Incorporated
Inventor： Ning Bi , Fan Ling , Jingting Ding , Yu Sun
IPC: H04N21/845 , H04N21/234 , H04N21/2343 , H04N21/81 , H04N21/8549 , G06F17/30
Abstract: A system and method of video processing are disclosed. In a particular implementation, a device includes a processor configured to generate index data for video content. The index data includes a summary frame and metadata. The summary frame is associated with a portion of the video content and illustrates multiple representations of an object included in the portion of the video content. The metadata includes marker data that indicates a playback position of the video content. The playback position is associated with the summary frame. The device also includes a memory configured to store the index data.
-
公开(公告)号：US10043318B2
公开(公告)日：2018-08-07
申请号：US15374165
申请日：2016-12-09
Applicant: QUALCOMM Incorporated
Inventor： Moinul Khan , Nhon Quach , Martin Renschler , Ramesh Chandrasekhar , Assaf Menachem , Ning Bi , Maurice Ribble
Abstract: Certain aspects of the present disclosure provide methods and apparatus for operating a wearable display device. Certain aspects of the present disclosure provide a method for operating a wearable display device. The method includes determining a position of the wearable display device based on a motion sensor. The method includes rendering, by a graphics processing unit, an image based on the determined position. The method includes determining a first updated position of the wearable display device based on the motion sensor. The method includes warping, by a warp engine, a first portion of the rendered image based on the first updated position. The method includes displaying the warped first portion of the rendered image on a display of the wearable display device.
-
公开(公告)号：US20180046858A1
公开(公告)日：2018-02-15
申请号：US15264270
申请日：2016-09-13
Applicant: QUALCOMM Incorporated
Inventor： Ying Chen , Jianfeng Ren , Jian Wei , Ning Bi
CPC classification number: G06K9/00577 , G06K9/00771 , G06K9/342 , G06T5/20 , G06T7/11 , G06T7/194 , G06T2207/10016 , G06T2207/20024 , G06T2207/20221 , G06T2207/30232
Abstract: Techniques and systems are provided for processing video data. For example, techniques and systems are provided for performing content-adaptive blob filtering. A number of blobs generated for a video frame is determined. A size of a first blob from the blobs is determined, the first blob including pixels of at least a portion of a first foreground object in the video frame.The first blob is filtered from the plurality of blobs when the size of the first blob is less than a size threshold. The size threshold is determined based on the number of the plurality of blobs generated for the video frame.
-
公开(公告)号：US09842423B2
公开(公告)日：2017-12-12
申请号：US13936867
申请日：2013-07-08
Applicant: QUALCOMM Incorporated
Inventor： Feng Guo , Ning Bi , Yingyong Qi
CPC classification number: G06T15/00 , G06K9/00208 , G06T7/593 , G06T2207/30201
Abstract: A method for three-dimensional face generation is described. An inverse depth map is calculated based on a depth map and an inverted first matrix. The inverted first matrix is generated from two images in which pixels are aligned vertically and differ horizontally. The inverse depth map is normalized to correct for distortions in the depth map caused by image rectification. A three-dimensional face model is generated based on the inverse depth map and one of the two images.
-
公开(公告)号：US20170200308A1
公开(公告)日：2017-07-13
申请号：US14993760
申请日：2016-01-12
Applicant: QUALCOMM Incorporated
Inventor： Phi Hung Nguyen , Ning Bi
CPC classification number: G06T17/20 , G06T1/20 , G06T3/0012 , G06T11/40 , G06T15/005 , G06T15/503 , G06T2210/36
Abstract: An electronic device is described. The electronic device includes a processor. The processor is configured to render a first zone of an image. The processor is also configured to render a second zone of the image. The first zone has a higher tessellated level of detail than the second zone. The processor is further configured to present the first zone and the second zone on at least one vehicle window.
-
-
-
-
-
-
-
-
-
Search Results
135
records
(took 0.05 seconds)
