-
1.发明公开公开(公告)号：US20240161474A1
公开(公告)日：2024-05-16
申请号：US18284076
申请日：2023-01-10
Applicant: BOE Technology Group Co., Ltd.
Inventor： Chunshan ZU
IPC: G06V10/776 , G06V10/70 , G06V10/82
CPC classification number: G06V10/776 , G06V10/82 , G06V10/87
Abstract: A neural network inference acceleration method includes: acquiring a neural network model to be accelerated and an accelerated data set; automatically performing accelerating process on the neural network model to be accelerated by using the accelerated data set to obtain the accelerated neural network model, wherein the accelerating process includes at least one of the following: model compression, graph optimization and deployment optimization, wherein the model compression includes at least one of the following: model quantification, model pruning and model distillation, wherein the graph optimization is the optimization for the directed graph of the neural network model to be accelerated, and the deployment optimization is the optimization for the deployment platform of the neural network model to be accelerated; and performing inference evaluation on the accelerated neural network model.
-
2.发明申请公开(公告)号：US20220211327A1
公开(公告)日：2022-07-07
申请号：US17438597
申请日：2021-02-02
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor： Chunshan ZU
Abstract: A measurement method and an apparatus for period information of a biological signal, an electronic device and a computer-readable storage medium are provided. The measurement method includes: acquiring a feature tensor of a biological signal, classifying the feature tensor by using each of a plurality of binary classifiers to obtain a plurality of classification results, classification parameters of each of the plurality of binary classifiers being different, and determining a first measurement value of the period information of the biological signal based on the plurality of classification results.
-
公开(公告)号：US20240346813A1
公开(公告)日：2024-10-17
申请号：US18294134
申请日：2022-07-27
Applicant: BOE Technology Group Co., Ltd.
Inventor： Chunshan ZU , Weiyang HU
IPC: G06V10/82 , G06V10/77 , G06V10/776 , G06V10/80
CPC classification number: G06V10/82 , G06V10/7715 , G06V10/776 , G06V10/806
Abstract: A target detection optimization method and device are disclosed. The method includes: inputting an image including an object into a trained target detection model for detection, and determining coordinates of the object in the image and a category of the object; the target detection model includes a plurality of depthwise convolutional network layers, and the target detection model is obtained by: training using a first training sample set to obtain a to-be-optimized model, pruning model parameters in the to-be-optimized model using an optimal pruning scheme, and training the pruned to-be-optimized model using a second training sample set; where the optimal pruning scheme is obtained by screening pruning schemes determined according to different pruning methods and pruning rates.
-
公开(公告)号：US20240161461A1
公开(公告)日：2024-05-16
申请号：US17772923
申请日：2021-04-01
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor： Chunshan ZU
IPC: G06V10/774 , G06T7/73 , G06V10/77 , G06V10/80 , G06V10/82
CPC classification number: G06V10/774 , G06T7/73 , G06V10/7715 , G06V10/806 , G06V10/82 , G06T2207/10016 , G06T2207/20081 , G06T2207/20084 , G06V2201/07
Abstract: An object detection method includes: obtaining a video to be detected; preprocessing the video to be detected to obtain an image to be detected; inputting the image to be detected into an object detection network; extracting, by the object detection network, a feature map of the image to be detected; performing, by the object detection network, an object prediction on the extracted feature map to obtain a position of an object in the image to be detected and a confidence degree corresponding to the position; and generating a marked object video according to the position of the object in the image to be detected, the confidence degree corresponding to the position, and the video to be detected.
-
公开(公告)号：US20220237938A1
公开(公告)日：2022-07-28
申请号：US17578252
申请日：2022-01-18
Applicant: BOE Technology Group Co., Ltd.
Inventor： Chunshan ZU
Abstract: The present disclosure relates to a method of performing real-time object detection using an object real-time detection model and a performance optimization method of object real-time detection model. According to an embodiment, the method of performing real-time object detection using an object real-time detection model includes: obtaining an identification image of a preset size by pre-processing an input image; obtaining object central point data and object size data by processing the identification image using the object real-time detection model; and obtaining an object detection result by determining an object region in the input image according to the object central point data and the object size data.
-
Patent Agency Ranking
公开(公告)号：US20220171962A1
公开(公告)日：2022-06-02
申请号：US17359621
申请日：2021-06-27
Applicant: BOE Technology Group Co., Ltd.
Inventor： Chunshan ZU
IPC: G06K9/00
Abstract: Provided are a method and an apparatus for recognizing a gesture, an electronic device and a storage medium. In one or more embodiments, the method includes: detecting at least one hand region from a video image and obtaining hand image information of each of the at least one hand region; obtaining hand motion information of each of the at least one hand region by tracking the at least one hand region; determining a gesture corresponding to each of the at least one hand region according to the hand image information and/or the hand motion information of each of the at least one hand region; wherein the gesture comprises at least one of a single-hand static gesture, a single-hand dynamic gesture, a double-hand static gesture or a double-hand dynamic gesture.
-
公开(公告)号：US20240420500A1
公开(公告)日：2024-12-19
申请号：US18814984
申请日：2024-08-26
Applicant: BOE Technology Group Co., Ltd.
Inventor： Chunshan ZU
Abstract: The present disclosure relates to a performance optimization method of object real-time detection model. According to an embodiment, the method includes: obtaining a plurality of processing resources of an electronic device; establishing a search space of the object real-time detection model according to the processing resources; and obtaining target processing resources corresponding to the object real-time detection model by searching the search space.
-
8.发明公开公开(公告)号：US20230154192A1
公开(公告)日：2023-05-18
申请号：US17995269
申请日：2021-09-10
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor： Chunshan ZU , Xiaojun TANG
CPC classification number: G06V20/53 , G06V10/225 , G06V2201/07
Abstract: The present disclosure provides a person flow analysis method and system, an electronic device, and a readable storage medium. The method includes: obtaining a video image of a target area; identifying and tracking target features of persons in the video image; generating person flow data for the target area according to movement states of the target features of the persons relative to a specific position in the target area. By identifying and monitoring the target features in the video images of the target area, it does not need to analyze and identify all features of the persons, thereby reducing the amount of calculation and increasing the scope of application . By analyzing a movement state of the target feature relative to the specific position, a movement mode of a user in the target area can be obtained, thereby improving accuracy of analysis of the person flow in the target area.
-
公开(公告)号：US20230153391A1
公开(公告)日：2023-05-18
申请号：US17621665
申请日：2021-02-25
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor： Chunshan ZU
IPC: G06F18/241 , G06F17/16
CPC classification number: G06F18/241 , G06F17/16
Abstract: An electrocardiogram data classification method includes: obtaining a plurality of pieces of heartbeat data according to electrocardiogram data; convolving and pooling the plurality of pieces of heartbeat data to obtain a first feature vector; obtaining a second feature vector, the second feature vector representing frequency domain feature data of the plurality of pieces of heartbeat data and time domain feature data of the plurality of pieces of heartbeat data; fusing the first feature vector and the second feature vector to generate a fusion feature vector; and obtaining classification information of the electrocardiogram data according to the fused feature vector.
-
公开(公告)号：US20220253976A1
公开(公告)日：2022-08-11
申请号：US17555129
申请日：2021-12-17
Applicant: BOE Technology Group Co., Ltd.
Inventor： Chunshan ZU
Abstract: An image processing method and a display apparatus are provided. The image processing method includes: acquiring an input image and an image output specification; determining image processing information for the input image; performing image processing, in accordance with the image processing information, on a plurality of images in the input image in a parallel and matrix manner. The performing image processing on the plurality of images in the parallel and matrix manner is referred to as performing processing on the plurality of images in parallel, and processes performed on each image include a preprocessing process, an image quality enhancement process and a post-processing process.
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.02 seconds)
