-
公开(公告)号：US20210192696A1
公开(公告)日：2021-06-24
申请号：US17151783
申请日：2021-01-19
Inventor： Qunyi XIE , Xiameng QIN , Yulin LI , Junyu HAN , Shengxian ZHU
Abstract: Embodiments of the present disclosure provide a method and apparatus for correcting a distorted document image, where the method for correcting a distorted document image includes: obtaining a distorted document image; and inputting the distorted document image into a correction model, and obtaining a corrected image corresponding to the distorted document image; where the correction model is a model obtained by training with a set of image samples as inputs and a corrected image corresponding to each image sample in the set of image samples as an output, and the image samples are distorted. By inputting the distorted document image to be corrected into the correction model, the corrected image corresponding to the distorted document image can be obtained through the correction model, which realizes document image correction end-to-end, improves accuracy of the document image correction, and extends application scenarios of the document image correction.
-
公开(公告)号：US20210192209A1
公开(公告)日：2021-06-24
申请号：US17173142
申请日：2021-02-10
Inventor： Xinjiang LU , Nengjun ZHU , Hui XIONG
Abstract: This disclosure discloses a resident area prediction method, apparatus, device and storage medium, involving artificial intelligence technology, big data, deep learning and multi-task learning. The specific implementation plan is: acquiring a resident area data of a target user, and the resident area data including the resident area of the target user and the corresponding resident time; obtaining an association relationship between the resident areas of the target user by inputting the resident area data into an area relationship model, and the area relationship model is used to reflect a position relationship between the areas; determining a time-sequence relationship between the areas visited by the target user, according to the association relationship, the resident time and the visiting POI data; predicting a target resident area of the target user, according to the time-sequence relationship and the basic attribute information of the target user.
-
公开(公告)号：US20210192194A1
公开(公告)日：2021-06-24
申请号：US17022219
申请日：2020-09-16
Inventor： Zhizhen Chi , Fu Li , Hao Sun , Dongliang He , Xiang Long , Zhichao Zhou , Ping Wang , Shilei Wen , Errui Ding
Abstract: The present application discloses a video-based human behavior recognition method, apparatus, device and storage medium, and relates to the technical field of human recognitions. The specific implementation scheme lies in: acquiring a human rectangle of each video frame of the video to be recognized, where each human rectangle includes a plurality of human key points, and each of the human key points has a key point feature; constructing a feature matrix according to the human rectangle of the each video frame; convolving the feature matrix with respect to a video frame quantity dimension to obtain a first convolution result and convolving the feature matrix with respect to a key point quantity dimension to obtain a second convolution result; inputting the first convolution result and the second convolution result into a preset classification model to obtain a human behavior category of the video to be recognized.
-
公开(公告)号：US20210192044A1
公开(公告)日：2021-06-24
申请号：US17124557
申请日：2020-12-17
Inventor： Zhiyang CUI
Abstract: The present disclosure discloses a method, apparatus, device, and storage medium for defending against attacks, which relate to the technical field of information security, and can be used in intelligent traffic or an autonomous driving scenario. The specific implementation solution is: acquiring an instruction set including at least one instruction for controlling vehicle state; comparing each instruction in the instruction set with at least one attack instruction in an attack behavior knowledge base respectively to determine a maximum similarity value corresponding to each instruction; and determining the type of the instruction and of the processing tactics for the instruction according to the maximum similarity value corresponding to each instruction and a preset similarity range.
-
575.发明申请公开(公告)号：US20210191962A1
公开(公告)日：2021-06-24
申请号：US17088053
申请日：2020-11-03
IPC: G06F16/33 , G06F40/40 , G06K9/00 , G06F16/332 , G06F16/338 , G06N3/08
Abstract: Provided are a question answering method and language model training method, apparatus, device, and storage media, including: acquiring at least one candidate table matching a question to be queried, each candidate table includes a candidate answer corresponding to the question; processing the at least one candidate table to obtain at least one table text, the table text includes textual content of respective fields in the candidate table; inputting the question and each table text into a preset language model respectively to obtain a degree of matching between the question and each candidate table; and outputting a reply table according to the degree of matching of each candidate table, the reply table is a candidate table out of the at least one candidate table whose degree of matching with the question is greater than a preset value or a candidate table that corresponds to a maximum degree of matching.
-
Patent Agency Ranking
公开(公告)号：US20210190531A1
公开(公告)日：2021-06-24
申请号：US17123753
申请日：2020-12-16
Inventor： Yinghui LI
Abstract: The present application discloses an AR navigation method and apparatus, relating to the field of intelligent transportation technologies. The solution is as follows: acquiring a calibration parameter of a camera on a vehicle and information of a maneuvering point on a navigation route that the vehicle is about to pass through as well as information of an actual location point of the vehicle; in response to receiving a signal of the vehicle entering a turning status, determining a first turning guidance track of the vehicle according to information of a current actual location point of the vehicle and the information of the maneuvering point; and converting the first turning guidance track according to the calibration parameter to obtain a second turning guidance track.
-
公开(公告)号：US20210190510A1
公开(公告)日：2021-06-24
申请号：US17171999
申请日：2021-02-09
Inventor： DAYUN SHEN
Abstract: Embodiments of the present application disclose a vehicle positioning method, an apparatus, an electronic device, a vehicle and a storage medium, and relate to the field of automatic driving technology. A specific implementation includes: obtaining perceptual information of a lane where a vehicle is located, and obtaining high-precision information of the lane from a preset high-precision map, where the perceptual information and the high-precision information both include lane line information, and both include curb information and/or guardrail information; determining matching information of the perceptual information and the high-precision information; generating position information of the vehicle according to the matching information.
-
公开(公告)号：US20210108943A1
公开(公告)日：2021-04-15
申请号：US17130209
申请日：2020-12-22
Inventor： Jiaqi LIANG , Gao YU , Gaifan LI
IPC: G01C21/00
Abstract: The present application provides a map data updating method, an apparatus, a system and a storage medium. The method includes: determining a road section identifier of a road section to be updated in a map; sending data collection instruction information to an unmanned vehicle, where the data collection instruction information includes: the road section identifier, and a current number of collection times of the road section corresponding to the road section identifier; receiving road section information which is sent by the unmanned vehicle and which corresponds to the road section identifier; acquiring a road section updated map according to the road section information; sending the road section updated map to the unmanned vehicle.
-
公开(公告)号：US20210108941A1
公开(公告)日：2021-04-15
申请号：US16864648
申请日：2020-05-01
Inventor： Xinjiang LU , Yanyan LI , Jianguo DUAN , Hui XIONG , Guanglei DU
IPC: G01C21/36
Abstract: The present disclosure discloses a method, an apparatus, a device, and a storage medium for determining a point of interest area, and relates to the field of automatic driving. The implementation solution is that the method is applied to an electronic device, and includes: receiving a point of interest area determination request input by a first user, the point of interest area determination request including a target area coverage; and acquiring grid data of at least one block within the target area coverage in response to the point of interest area determination request; acquiring, for each block, positioning data of a second user within each preset time period and number of parent points of interest; clustering corresponding grid data according to the positioning data, the grid data and the number of the parent points of interest; determining at least one POI area in each block according to a clustering result.
-
公开(公告)号：US20210101622A1
公开(公告)日：2021-04-08
申请号：US17124537
申请日：2020-12-17
Inventor： Gao YU , Jingjing XUE , Gaifan LI , Donghui SHEN , Tong WU , Jiaqi LIANG
Abstract: Embodiments of the present disclosure provide a method for processing vehicle driving mode switching, a vehicle and a server. The method includes: determining (S103) a target switching reason upon detecting that a driving mode of a vehicle is switched from unmanned driving to manned driving; acquiring (S104) status information and/or traveling environment information of the vehicle corresponding to the target switching reason; and sending the status information and/or the traveling environment information, and the target switching reason to a server, to enable the server to analyze the target switching reason, and improve the automatic driving system continuously according to the analysis result.
-
-
-
-
-
-
-
-
-
Search Results
1522
records
(took 0.031 seconds)
