公开(公告)号：US20220292344A1

公开(公告)日：2022-09-15

申请号：US17200090

申请日：2021-03-12

Applicant: QUALCOMM Incorporated

Inventor： David HANSEN ,  Alireza SHOA HASSANI LASHDAN ,  Sivakumar CHIDAMBARAM ,  Haoping XU ,  Jeffrey Kar Fai WONG ,  Stone YUN ,  Darren GNANAPRAGASAM

IPC: G06N3/08 ,  G06K9/62

Abstract: Technologies are provided for processing data in neural networks. An example method can include processing, by each layer of a neural network, a row in a first stripe of a data input, the row being processed sequentially in a horizontal direction and according to a layer-by-layer sequence; after processing the row, processing, by each layer, subsequent rows in the first stripe on a row-by-row basis, each subsequent row being processed sequentially in the horizontal direction and according to the layer-by-layer sequence; generating an output stripe based on the processing of the row and subsequent rows; processing, by each layer, a second stripe of the data input, each row in the second stripe being processed in the horizontal direction and according to the layer-by-layer sequence, wherein rows in the second stripe are processed on a row-by-row basis; and generating another output stripe based on the processing of the second stripe.

公开(公告)号：US20210105442A1

公开(公告)日：2021-04-08

申请号：US16591462

申请日：2019-10-02

Applicant: QUALCOMM Incorporated

Inventor： Alireza SHOA HASSANI LASHDAN ,  Darren GNANAPRAGASAM ,  Evgenii KRASNIKOV ,  Adrian LEUNG ,  David HANSEN

IPC: H04N7/18 ,  H04N3/14 ,  G06K9/00 ,  G06N3/02

Abstract: A camera image processor receives frames from an image sensor of the camera. While continuing to receive frames from the image sensor, the camera image processor detecting an action within one or more frames of the received frames, for example using a convolution neural network trained to recognize one or more actions. While continuing to receive frames from the image sensor, the camera image processor captures the one or more frames with the detected action, for example as a still image, or as a slow-motion portion of a video that includes the received frames.

公开(公告)号：US20240087140A1

公开(公告)日：2024-03-14

申请号：US17931859

申请日：2022-09-13

Applicant: QUALCOMM Incorporated

Inventor： Qureshi ASMA ,  Darren GNANAPRAGASAM ,  Alireza SHOA HASSANI LASHDAN ,  David HANSEN

IPC: G06T7/215 ,  G06T7/194

CPC classification number: G06T7/215 ,  G06T7/194 ,  G06T2207/20081

Abstract: Systems and techniques are described herein for processing video data. For instance, a technique can include receiving a first image after a previous image. The process can further include receiving a first segmentation mask associated with the previous image. The process can also include estimating a first set of forward motion vectors between the previous image and the first image. The process can further include estimating a reliability of the first set of forward motion vectors. The process can also include extrapolating a second segmentation mask associated with the first image using the first set of forward motion vectors and first segmentation mask based on the estimated reliability of the first set of forward motion vectors.

公开(公告)号：US20220130015A1

公开(公告)日：2022-04-28

申请号：US17083146

申请日：2020-10-28

Applicant: QUALCOMM Incorporated

Inventor： Stone YUN ,  Alireza SHOA HASSANI LASHDAN ,  Darren GNANAPRAGASAM ,  David HANSEN

IPC: G06T5/00 ,  G06T5/50

Abstract: A device includes a memory configured to store an adapted network that is configured to generate a modified image based on a single image. The device includes a processor configured to obtain, from a stream of video data, a first distorted image depicting an object, and to provide the first distorted image to the adapted network to generate a first modified image. The processor is configured to obtain, from the stream of video data, a second distorted image depicting the object, and to provide the second distorted image to the adapted network to generate a second modified image. The object is distorted differently in the second distorted image than in the first distorted image. The processor is configured to generate a video output including the first modified image and the second modified image without visible artifacts due to distortion differences between the first distorted image and the second distorted image.

公开(公告)号：US20210099756A1

公开(公告)日：2021-04-01

申请号：US16589379

申请日：2019-10-01

Applicant: QUALCOMM Incorporated

Inventor： Darren Gnanapragasam ,  George SHEHATA ,  Adrian LEUNG ,  Alireza SHOA HASSANI LASHDAN ,  Evgenii KRASNIKOV ,  David HANSEN

IPC: H04N21/44 ,  H04N5/232 ,  G06K9/00 ,  H04N21/472 ,  G06T7/20 ,  H04N21/845

Abstract: Methods, systems, and devices for low-cost video segmentation are described. A media file may include multiple frames. Information for pixels in a first frame and pixels in a subsequent frame may be discarded based on segmentation maps computed for the first and subsequent frame. After discarding the pixel information, motion information may be determined for the remaining pixels in the first and subsequent frame. The segmentation maps generated for the first and subsequent frames and the determined motion information may be used to compute one or more additional segmentation maps for one or more additional frames that are temporally located between the first and subsequent frame. After computing segmentation maps for all or a portion of the frames in the media file, a modified version of the frames may be output based on the computed segmentation maps.