-
公开(公告)号:US20240087279A1
公开(公告)日:2024-03-14
申请号:US18511462
申请日:2023-11-16
Applicant: QUALCOMM Incorporated
Inventor: Edwin Chongwoo PARK , Soman Ganesh NIKHARA , Bapineedu Chowdary GUMMADI , Pradeep VEERAMALLA , Ravi Shankar KADAMBALA
Abstract: Methods, systems, computer-readable media, and apparatuses for region-of-interest (ROI) automatic gain or exposure control are presented. In one example, a method includes receiving a first image from an image sensor captured with a first field of view (FOV) and comprising a first plurality of pixels, receiving a second image from the image sensor captured with a second FOV and comprising a second plurality of pixels, determining an ROI in the second image, the ROI comprising a subset of the second plurality of pixels in the second image, determining an ROI weight for the ROI in the second image, determining statistics based on the first plurality of pixels in the first image, the subset of the second plurality of pixels in the second image, and the ROI weight for the ROI in the second image, and adjusting a gain or exposure setting for the image sensor based on the statistics.
-
公开(公告)号:US20230388673A1
公开(公告)日:2023-11-30
申请号:US17804014
申请日:2022-05-25
Applicant: QUALCOMM Incorporated
Inventor: Edwin Chongwoo PARK
CPC classification number: H04N5/3696 , H04N5/378 , H04N5/351
Abstract: In some aspects, an image sensor may include a plurality of pixels. The plurality of pixels may be grouped into a plurality of patches configured to provide input to a transformer model. The image sensor may include a read-out component configured to read out data from the plurality of pixels on a patch-by-patch basis. Numerous other aspects are described.
-
公开(公告)号:US20220191411A1
公开(公告)日:2022-06-16
申请号:US17119779
申请日:2020-12-11
Applicant: QUALCOMM Incorporated
Inventor: Russell GRUHLKE , Edwin Chongwoo PARK , Naga Chandan Babu GUDIVADA
Abstract: In some aspects, a spectral image capturing device may receive, from a filter array, visible light and infrared light, wherein the filter array includes a quantity of color filters to block the infrared light and pass the visible light and a quantity of infrared filters to block the visible light and pass the infrared light. The spectral image capturing device may produce, using an image sensor that includes an array of pixel sensors, a spectral image based at least in part on the visible light and the infrared light passed by the filter array. Numerous other aspects are provided.
-
公开(公告)号:US20220092986A1
公开(公告)日:2022-03-24
申请号:US17540852
申请日:2021-12-02
Applicant: QUALCOMM Incorporated
Inventor: Benjamin LUND , Edwin Chongwoo PARK , Anthony BLOW , Garrett SHRIVER
Abstract: Disclosed is a method and apparatus for operating a first device. The first device obtains environment information in proximity to the first device and receives one or more communication messages from a second device and the message(s) includes relevance criteria, wherein the relevance criteria indicates one or more devices, one or more sets of device characteristics, one or more lanes, one or more intersections or areas, one or more pedestrian paths or bicycle paths, one or more signal characteristics from the second device or any combination thereof. The first device determines whether the one or more communication messages are relevant to the first device based on the relevance criteria and the environment information and performs an operation in response to the determination of whether the one or more communication messages are relevant.
-
公开(公告)号:US20220030430A1
公开(公告)日:2022-01-27
申请号:US16936428
申请日:2020-07-23
Applicant: QUALCOMM Incorporated
Inventor: Benjamin LUND , Soumya DAS , Edwin Chongwoo PARK , Garrett SHRIVER
Abstract: Techniques described herein include utilizing a mobile device as a proxy receiver and/or transmitter for a vehicle in a V2X network. In some embodiments, the mobile device associated mobile device capabilities may be configured to obtain vehicle capabilities and store such data in memory at the mobile device. The mobile device may obtain any suitable combination of a reception credential and one or more transmission credentials. In some embodiments, the one or more transmission credentials may be generated by a credential authority based at least in part on determining that the vehicle capabilities and mobile device capabilities indicate that the sensor(s) and/or processing resources of the vehicle and/or mobile device meet transmission requirement thresholds for the network. The mobile device may subsequently transmit any suitable data message on behalf of the vehicle using at least one of the transmission credentials.
-
公开(公告)号:US20200344413A1
公开(公告)日:2020-10-29
申请号:US16857045
申请日:2020-04-23
Applicant: QUALCOMM Incorporated
Inventor: Jon LASITER , Evgeni GOUSEV , Ravindra Vaman SHENOY , Russell GRUHLKE , Khurshid Syed ALAM , Kebin LI , Edwin Chongwoo PARK
Abstract: In one example, an image sensor module comprises one or more covers having at least a first opening and a second opening, a first lens mounted in the first opening and having a first field of view (FOV) centered at a first axis having a first orientation, a second lens mounted in the second opening and having a second FOV centered at a second axis having a second orientation different from the first orientation, a first image sensor housed within the one or more covers and configured to detect light via the first lens, and a second image sensor housed within the one or more covers and configured to detect light via the second lens. The first image sensor and the second image sensor are configured to provide, based on the detected light, image data of a combined FOV larger than each of the first FOV and the second FOV.
-
公开(公告)号:US20240039339A1
公开(公告)日:2024-02-01
申请号:US17815916
申请日:2022-07-28
Applicant: QUALCOMM Incorporated
Inventor: Edwin Chongwoo PARK
Abstract: Systems and techniques are provided for providing power for target devices. For example, a process can include performing, at an environment infrastructure system, a device discovery procedure to discover a target device in an environment; obtaining power requirement information corresponding to the target device; obtaining a distance between a power providing component of the environment infrastructure system and the target device; determining a power amount to transmit to the target device based at least in part on the distance, the power requirement information, and an operation to be performed at the target device; determining a direction from the power providing component to the target device; transmitting the power amount in the direction to provide power to the target device for performing the operation; and receiving an operation result from the target device based on the operation.
-
公开(公告)号:US20220383018A1
公开(公告)日:2022-12-01
申请号:US17303241
申请日:2021-05-25
Applicant: QUALCOMM Incorporated
Inventor: Russell GRUHLKE , Ravishankar SIVALINGAM , Donald William KIDWELL, JR. , Edwin Chongwoo PARK
Abstract: In some aspects, a device may detect that an object is contacting a display of the device. The device may illuminate, based at least in part on detecting that the object is contacting the display, a plurality of pixel regions of the display. The plurality of pixel regions may be illuminated sequentially. The device may obtain, using one or more photosensors, a set of data relating to light that is reflected from at least a portion of the object based at least in part on illuminating the plurality of pixel regions. The set of data may include respective data for each sequential illumination of the plurality of pixel regions. The device may generate an image of at least the portion of the object based at least in part on the set of data. Numerous other aspects are described.
-
公开(公告)号:US20210398314A1
公开(公告)日:2021-12-23
申请号:US16904466
申请日:2020-06-17
Applicant: QUALCOMM Incorporated
Inventor: Ravishankar SIVALINGAM , Donald William KIDWELL, JR. , Russell GRUHLKE , Edwin Chongwoo PARK , Khurshid Syed ALAM
IPC: G06T7/73 , G06F3/01 , G06F3/0346 , H04N5/247
Abstract: Systems, methods, and non-transitory media are provided for low-power visual tracking systems. An example method can include receiving one or more images captured by each image sensor system from a set of image sensor systems on a first device, the one or more images capturing a set of patterns on a second device, wherein the first device has lower power requirements than the second device, the set of patterns having a predetermined configuration on the second device; determining, from the one or more images captured by each image sensor system, a set of pixels corresponding to the set of patterns on the second device; determining, based on the set of pixels corresponding to the set of patterns, a location and relative pose in space of each pattern; and determining, based on the location and relative pose of each pattern, a pose of the first device relative to the second device.
-
公开(公告)号:US20200160106A1
公开(公告)日:2020-05-21
申请号:US16193970
申请日:2018-11-16
Applicant: QUALCOMM Incorporated
Inventor: Ravishankar SIVALINGAM , Edwin Chongwoo PARK
Abstract: Cameras with large field-of-view lenses can cause significant geometric distortions of the images acquired. Training for object detection normally takes place on undistorted images. Thus, in order to detect objects of interest within the acquired images, an undistortion procedure is applied on the acquired images and an object detection is then performed on the undistorted images. Unfortunately, such undistortion procedure is too computationally expensive to be run on some edge devices. To remove the need to perform the undistortion procedure, it is proposed to train for object detection directly from distorted acquired images.
-
-
-
-
-
-
-
-
-