公开(公告)号：US20230316511A1

公开(公告)日：2023-10-05

申请号：US18176497

申请日：2023-03-01

Applicant: HTC Corporation

Inventor： Chen-Han TSAI ,  Yu-Shao PENG

IPC: G06T7/00 ,  G06T5/50 ,  G06V10/25 ,  G06V10/44 ,  G06V10/764 ,  G06V10/771 ,  G06V10/82

CPC classification number: G06T7/0012 ,  G06T5/50 ,  G06V10/25 ,  G06V10/454 ,  G06V10/764 ,  G06V10/771 ,  G06V10/82 ,  G06T2207/10081 ,  G06T2207/10088 ,  G06T2207/20016 ,  G06T2207/20221 ,  G06T2207/30096 ,  G06V2201/07

Abstract: A medical image detection system includes a memory and a processor. The processor is configured to execute the neural network model stored in the memory. The neural network model includes a feature extractor, a feature pyramid network, a first output head and a second output head. The feature extractor is configured for extracting intermediate tensors from a medical image. The feature pyramid network is associated with the feature extractor. The feature pyramid network is configured for generating multi-resolution feature maps according to the intermediate tensors. The first output head is configured for generating a global prediction according to the multi-resolution feature maps. The second output head is configured for generating local predictions according to the multi-resolution feature maps. The processor is configured to generate output information based on the medical image, the global prediction and the local predictions.

公开(公告)号：US20230314162A1

公开(公告)日：2023-10-05

申请号：US18124518

申请日：2023-03-21

Applicant: Honda Motor, Co., Ltd.

Inventor： Naoki Mori

IPC: G01C21/00 ,  G06V20/56 ,  G06T7/11 ,  G06T7/70 ,  G06V10/44 ,  G06V10/771

CPC classification number: G01C21/3804 ,  G06T7/11 ,  G06T7/70 ,  G06V10/44 ,  G06V10/771 ,  G06V20/56 ,  G06T2207/30252 ,  G06V2201/07

Abstract: A vehicle control apparatus includes a microprocessor configured to perform: extracting feature points from detection information detected by an in-vehicle detection unit; selecting feature points for which three-dimensional positions are to be calculated from extracted feature points; based on a plurality of detection information, calculating three-dimensional positions of same feature points in the plurality of detection information for the selected feature points using a position and posture of the in-vehicle detection unit; and generating a map including information of each of the three-dimensional positions using the calculated three-dimensional positions of the plurality of the feature points. The selecting includes selecting the feature points so as to reduce a bias in a number of feature points on objects located in a first distance range unit and a number of feature points on objects located in a second distance range farther than the first distance range.

公开(公告)号：US20230314156A1

公开(公告)日：2023-10-05

申请号：US18127216

申请日：2023-03-28

Applicant: PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO., LTD.

Inventor： Hiroshi YAHATA ,  Tomoyuki HIROTA ,  Yusaku NAOI

IPC: G01C21/36 ,  G06T15/00 ,  G06V20/59 ,  G06F3/01 ,  G06F3/04842

CPC classification number: G01C21/3638 ,  G06T15/00 ,  G06V20/59 ,  G06F3/013 ,  G06F3/04842 ,  G06V2201/07

Abstract: An information presentation method includes: acquiring position information indicating a current position of a vehicle; acquiring vehicle inside information indicating a situation in a compartment of the vehicle; determining whether a first operation indicating that a first user in the compartment shows an interest in an object present around the vehicle is performed based on the vehicle inside information; in a case in which it is determined that the first operation is performed, displaying, on a display mounted on the vehicle, a 3D map image simulating a field of view of the first user at a first time point when the first operation is performed based on the position information and the vehicle inside information at the first time point, and map information; and displaying a first virtual object so as to be discriminable on the display, the first virtual object being estimated to correspond to the object.

公开(公告)号：US11776258B1

公开(公告)日：2023-10-03

申请号：US17945969

申请日：2022-09-15

Applicant: Apple Inc.

Inventor： Paul X. Wang

IPC: G06V20/20 ,  G06F3/16 ,  G10L15/22

CPC classification number: G06V20/20 ,  G06F3/165 ,  G06F3/167 ,  G10L15/22 ,  G06V2201/07 ,  G10L2015/223

Abstract: A head-mounted device can be operated to detect and respond to a user's behavior. The head-mounted device can be regularly and frequently worn while the user performs regular daily tasks, allowing the head-mounted device to collect a large volume of data across a long duration of time. The head-mounted device can provide feedback that can guide and direct a user to correct actions.

公开(公告)号：US11776158B2

公开(公告)日：2023-10-03

申请号：US17715194

申请日：2022-04-07

Applicant: Science Applications International Corporation

Inventor： Stephen Eric Bramlett ,  Michael Harris Rodgers

IPC: G06T7/70 ,  G06T7/73 ,  G06T3/40 ,  G06T7/33 ,  G06T7/80 ,  G06T7/246 ,  G06V10/25 ,  G06V10/20 ,  G06V10/46 ,  G06V10/75 ,  G06T7/174 ,  G06V20/60 ,  G06V20/52 ,  H04N23/80 ,  H04N23/90 ,  H04N23/695

CPC classification number: G06T7/74 ,  G06T3/4038 ,  G06T7/174 ,  G06T7/246 ,  G06T7/33 ,  G06T7/70 ,  G06T7/80 ,  G06V10/25 ,  G06V10/255 ,  G06V10/462 ,  G06V10/751 ,  G06V20/52 ,  G06V20/60 ,  H04N23/695 ,  H04N23/80 ,  H04N23/90 ,  G06T2207/10016 ,  G06T2207/20021 ,  G06T2207/20068 ,  G06T2207/30212 ,  G06T2207/30232 ,  G06T2207/30244 ,  G06V2201/07

Abstract: Search points in a search space may be projected onto images from cameras imaging different parts of the search space. Subimages, corresponding to the projected search points, may be selected and processed to determine if a target object has been detected. Based on subimages in which target objects are detected, as well as orientation data from cameras capturing images from which the subimages were selected, positions of the target objects in the search space may be determined.

公开(公告)号：US20230308744A1

公开(公告)日：2023-09-28

申请号：US18185297

申请日：2023-03-16

Applicant: CANON KABUSHIKI KAISHA

Inventor： TAKAYUKI HOSHINA

IPC: H04N23/63 ,  H04N23/60 ,  H04N23/65 ,  H04N23/67 ,  G06V10/25

CPC classification number: H04N23/632 ,  H04N23/64 ,  H04N23/651 ,  H04N23/67 ,  G06V10/25 ,  G06V2201/07

Abstract: An image pickup apparatus includes a first image sensor configured to perform imaging, and a control unit configured to perform precapture imaging, when acquiring a first imaging instruction, to cause the first image sensor to repeatedly perform imaging, and causes the first image sensor to perform main imaging when acquiring a second imaging instruction during the precapture imaging, and a first detecting unit configured to detect a change in a main object to be focused, and to output information about the change in the main object. The control unit changes control in the precapture imaging using the information about the change in the main object.

公开(公告)号：US20230306763A1

公开(公告)日：2023-09-28

申请号：US17840635

申请日：2022-06-15

Applicant: Wistron Corporation

Inventor： Yin-Zong Chen

IPC: G06V20/70 ,  G06T7/70 ,  G06T3/40 ,  G06V10/22 ,  G06F16/51

CPC classification number: G06V20/70 ,  G06T7/70 ,  G06T3/40 ,  G06V10/22 ,  G06F16/51 ,  G06V2201/07 ,  G06T2207/20212 ,  G06T2200/24

Abstract: An image processing method, an image processing apparatus, and an image processing system are provided. In the method, a target object is determined in an original image to generate a labeling result. The labeling result includes a position of the target object in the original image. Multiple target images of the target object are generated according to the labeling result. The target images are generated by extracting image of the target object from the original image and changing an image size of the image of the target object. A corresponding target image is combined with the original image according to a zoom operation. The zoom operation is configured to change an image size for displaying the original image.

公开(公告)号：US11768876B2

公开(公告)日：2023-09-26

申请号：US17161466

申请日：2021-01-28

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Xiameng Qin ,  Yulin Li ,  Qunyi Xie ,  Ju Huang ,  Junyu Han

IPC: G06F16/9032 ,  G06F16/583 ,  G06F16/532 ,  G06F40/279 ,  G06N3/04 ,  G06N3/088 ,  G06F18/213 ,  G06F18/25 ,  G06V10/25 ,  G06V10/764 ,  G06V10/80 ,  G06V10/82 ,  G06V10/44

CPC classification number: G06F16/90332 ,  G06F16/532 ,  G06F16/583 ,  G06F18/213 ,  G06F18/253 ,  G06F40/279 ,  G06N3/04 ,  G06N3/088 ,  G06V10/25 ,  G06V10/454 ,  G06V10/764 ,  G06V10/806 ,  G06V10/82 ,  G06V2201/07

Abstract: The present disclosure provides a method for visual question answering, which relates to a field of computer vision and natural language processing. The method includes: acquiring an input image and an input question; constructing a Visual Graph based on the input image, wherein the Visual Graph comprises a Node Feature and an Edge Feature; updating the Node Feature by using the Node Feature and the Edge Feature to obtain an updated Visual Graph; determining a question feature based on the input question; fusing the updated Visual Graph and the question feature to obtain a fused feature; and generating a predicted answer for the input image and the input question based on the fused feature. The present disclosure further provides an apparatus for visual question answering, a computer device and a non-transitory computer-readable storage medium.

公开(公告)号：US20230298374A1

公开(公告)日：2023-09-21

申请号：US18200041

申请日：2023-05-22

Applicant: SHANGHAI MIDU INFORMATION TECHNOLOGY CO., LTD.

Inventor： Ou KONG ,  Yidong LIU ,  Jun WANG

IPC: G06V30/414 ,  G06V10/771

CPC classification number: G06V30/414 ,  G06V10/771 ,  G06V2201/07

Abstract: A method and a device for determining a picture with texts are provided. The method includes: acquiring an original picture for determining the picture with the texts; determining the quantity and/or position coordinate information of textboxes in the original picture based on the original picture and a textbox detection network; and determining whether the original picture is the picture with the texts based on the quantity and/or position coordinate information of the textboxes.

公开(公告)号：US20230298335A1

公开(公告)日：2023-09-21

申请号：US18101133

申请日：2023-01-25

Applicant: Fujitsu Limited

Inventor： David Nicholson GRIFFITHS

IPC: G06V10/82 ,  G06V10/764

CPC classification number: G06V10/82 ,  G06V10/765 ,  G06V2201/07

Abstract: A computer-implemented method of training an object detector, the method comprising: training an embedding neural network using, as an input, cropped images from an image dataset, wherein training the embedding neural network is performed using a self-supervised learning approach and the trained embedding neural network translates input images into a lower dimensional representation; and training an object detector neural network by, for images of the image dataset, repeatedly: passing an image through the object detector neural network to obtain proposed coordinates of an object within the image, cropping the image to the proposed coordinates to obtain a cropped image, passing the cropped image through the trained embedding neural network to obtain a cropped image representation, passing an exemplar through the trained embedding neural network to obtain an exemplar representation, wherein the exemplar is a cropped manually labelled image bounding a known object, computing a distance in embedding space between the cropped image representation and the exemplar representation, computing a gradient of the cropped image representation and the exemplar representation with respect to the distance, and passing the gradient into the object detector neural network for use in backpropagation to optimise the object detector neural network.