-
公开(公告)号：US20220388501A1
公开(公告)日：2022-12-08
申请号：US17889867
申请日：2022-08-17
Inventor： Huiling JIAN , Xinjing LI , Jia SONG , Pengfei WEI
Abstract: A method for automated parking, a device, and a storage medium, which relate to a field of automated parking. The method for automated parking includes: determining, based on a historical location of a vehicle over a first time period, a frequented region associated with one or more candidate parking routes for the vehicle; acquiring the one or more candidate parking routes for the vehicle based on one or more historical parking routes of the vehicle in the frequented region, where the one or more historical parking routes include a driving-in route and/or a driving-out route; and providing the vehicle with the acquired one or more candidate parking routes in response to determining that the vehicle is in the frequented region, for the vehicle to drive in or drive out.
-
公开(公告)号：US11521653B2
公开(公告)日：2022-12-06
申请号：US17541822
申请日：2021-12-03
Inventor： Yafei Zhao , Shichang Zhang , Ziyuan Guo , Chao Chen
IPC: G11B27/031 , G06V20/40 , G11B27/00
Abstract: A video sequence layout method, electronic device and storage medium are provided, and relate to fields of deep learning, virtual reality, cloud computing, video layout processing and the like. The method includes: acquiring a first video sequence, the first video sequence including a main sequence for describing a first posture of a human body and a subordinate sequence for describing a plurality of second postures of the human body; extracting the main sequence and the subordinate sequence from the first video sequence; and in a case that it is detected that a sequencing identification frame exists in the first video sequence, performing random mixed sequencing processing on video frames in the main sequence and the subordinate sequence based on the sequencing identification frame and taking a sequence combination obtained by the random mixed sequencing processing as a second video sequence.
-
公开(公告)号：US11521495B2
公开(公告)日：2022-12-06
申请号：US16704005
申请日：2019-12-05
Inventor： Fan Yang , Fan Zhu , Weicheng Zhu , Leibing Lv , Lin Ma
Abstract: The present disclosure provides a method, an apparatus, a device and a readable storage medium for planning a pass path. The method includes: acquiring current road environment information in front of a vehicle; setting pass candidate points according to the current road environment information and a driving strategy; and determining a current optimal passable path according to the pass candidate points. Since the pass candidate points are set according to the current road environment information and the driving strategy, and the current optimal passable path is determined according to the pass candidate points, thereby effectively decreasing the calculation amount of the impassable path calculation in prior art due to direct setting of pass candidate points in all areas in front of an unmanned vehicle.
-
公开(公告)号：US20220375453A1
公开(公告)日：2022-11-24
申请号：US17875529
申请日：2022-07-28
Inventor： Junteng Zhang , Jianmin Wu , Tao Sun , Lei Jia
IPC: G10L13/10 , G10L13/06 , G10L13/047 , G10L25/18 , G10L13/08
Abstract: A method for speech synthesis includes obtaining text to be synthesized and an identifier of a speaker, the text being written in a first language; obtaining pronunciation information of each character in the text; generating linguistic features of the text by performing feature extraction on the pronunciation information of each character in the text based on the first language; and obtaining a target speech in a second language other than the first language, by performing speech synthesis based on the linguistic features and the identifier of the speaker.
-
785.发明申请公开(公告)号：US20220375118A1
公开(公告)日：2022-11-24
申请号：US17880931
申请日：2022-08-04
Inventor： Yingying LI , Xinyi DAI , Xiao TAN , Hao SUN
Abstract: Provided is a method and apparatus for identifying a vehicle cross-line. The method may include: determining, in each road condition image of a plurality of road condition images, position information of a target lane line and position information of a target vehicle; determining, based on the position information of the target lane line and the position information of the target vehicle, a relative positional relationship between the target vehicle and the target lane line corresponding to the each road condition image; and determining that the target vehicle crosses the line, if the relative positional relationships corresponding to the plurality of road condition images meet a preset condition.
-
Patent Agency Ranking
公开(公告)号：US20220374678A1
公开(公告)日：2022-11-24
申请号：US17817449
申请日：2022-08-04
Inventor： Teng Xi , Can Cao , Gang Zhang
IPC: G06N3/04
Abstract: The disclosure provides a method for determining a pre-training model, an electronic device and a storage medium, relates to a technical field of computer vision and deep learning, and can be applied to scenes such as image processing and image recognition. The method includes: obtaining a plurality of candidate models; obtaining a structural code of each candidate model by performing structural coding according to model structures of the plurality of candidate models; obtaining a frequency domain code of each candidate model by mapping the structural code of each candidate model using a trained encoder; predicting a model performance parameter of each candidate model according to the frequency domain code of each candidate model; and determining a target model from the plurality of candidate models as a pre-training model according to the model performance parameter of each candidate model.
-
公开(公告)号：US20220363290A1
公开(公告)日：2022-11-17
申请号：US17871217
申请日：2022-07-22
Inventor： Xinjing LI , Pengfei WEI , Huiling JIAN , Jia SONG
Abstract: The present disclosure provides a method for parking a vehicle, an electronic device and a medium. The method comprises: acquiring parking environment data of a parking environment related to a vehicle and historical parking data in the parking environment; selecting, according to the parking environment data and the historical parking data, a constraint set for parking the vehicle from a plurality of constraint sets, the plurality of constraint sets corresponding to a corresponding parking risk level; and controlling the vehicle to park according to the selected constraint set.
-
公开(公告)号：US20220361379A1
公开(公告)日：2022-11-10
申请号：US17814625
申请日：2022-07-25
Inventor： Zhiming Luo
IPC: H05K7/20
Abstract: A refrigeration system for a data center includes an indoor module, a main outdoor heat-dissipation module and an auxiliary outdoor heat-dissipation module, inlets of the first compressor and the second compressor are respectively connected to an outlet of the indoor module, outlets of the first compressor and the second compressor are respectively connected to a gaseous refrigerant inlet of the first condenser, liquid refrigerant outlets of the first condenser and the second condenser are respectively connected to an inlet of the indoor module, in which a refrigeration cycle passage for the data center is formed by the indoor module, the first condenser and the first compressor when the main outdoor heat-dissipation module is in a normal condition, and the refrigeration cycle passage for the data center is formed by the indoor module, the second condenser and the second compressor when the main outdoor heat-dissipation module fails.
-
公开(公告)号：US20220351493A1
公开(公告)日：2022-11-03
申请号：US17868630
申请日：2022-07-19
Inventor： Xiangbo SU , Qiman Wu , Shuai KANG , Jian WANG , Hao SUN
Abstract: A method and apparatus for detecting an object. The method includes: inputting a to-be-detected picture into a target detection model, marking at least one region of interest in the picture using the target detection model, and determining an initial confidence that each region of interest contains a preset target object; determining concentration information of an interferent in the picture; and determining, based on the concentration information and the initial confidence corresponding to the region of interest, a target confidence that the region of interest contains the preset target object.
-
790.发明申请公开(公告)号：US20220351398A1
公开(公告)日：2022-11-03
申请号：US17813870
申请日：2022-07-20
Inventor： Zhikang Zou , Xiaoqing Ye , Hao Sun
Abstract: A depth detection method, a method for training a depth estimation branch network, an electronic device, and a storage medium are provided, which relate to the field of artificial intelligence, particularly to the technical fields of computer vision and deep learning, and may be applied to intelligent robot and automatic driving scenarios. The specific implementation includes: extracting a high-level semantic feature in an image to be detected, wherein the high-level semantic feature is used to represent a target object in the image to be detected; inputting the high-level semantic feature into a pre-trained depth estimation branch network, to obtain distribution probabilities of the target object in respective sub-intervals of a depth prediction interval; and determining a depth value of the target object according to the distribution probabilities of the target object in the respective sub-intervals and depth values represented by the respective sub-intervals.
-
-
-
-
-
-
-
-
-
Search Results
1526
records
(took 0.033 seconds)
