-
1.发明授权公开(公告)号：US12130887B2
公开(公告)日：2024-10-29
申请号：US17515180
申请日：2021-10-29
发明人： Peng Sun , Jiaxiang Wu
IPC分类号： G06K9/62 , G06F18/21 , G06F18/214 , G06F18/25 , G06N3/04 , G06N3/082 , G06T7/70 , G06V10/26 , G06V10/70 , G06V10/80 , G06V10/82 , G06V20/40 , G06V20/70
CPC分类号： G06F18/214 , G06F18/217 , G06F18/253 , G06N3/04 , G06N3/082 , G06T7/70 , G06V10/267 , G06V10/70 , G06V10/806 , G06V10/82 , G06V20/41 , G06V20/70 , G06T2207/20084
摘要： This application provides a semantic segmentation network structure generation method performed by an electronic device, and a non-transitory computer-readable storage medium. The method includes: generating a corresponding architectural parameter for cells that form a super cell in a semantic segmentation network structure; optimizing the semantic segmentation network structure based on image samples, and removing a redundant cell from a super cell to which a target cell pertains, to obtain an improved semantic segmentation network structure; performing, by an aggregation cell in the improved semantic segmentation network structure, feature fusion on an output of the super cell; performing recognition processing on a fused feature map, to determine positions corresponding to objects that are in the image samples; and training the improved semantic segmentation network structure based on the positions corresponding to the objects that are in the image samples and annotations corresponding to the image samples, to obtain a trained semantic segmentation network structure.
-
公开(公告)号：US12130632B2
公开(公告)日：2024-10-29
申请号：US17945659
申请日：2022-09-15
发明人： Yu Zheng , Xinyang Jiang , Wanchao Chi , Zhengyou Zhang
IPC分类号： G05D1/00 , B62D57/032
CPC分类号： G05D1/0251 , B62D57/032
摘要： A legged robot motion control method, apparatus, and device, and a storage medium. The method includes: acquiring center of mass state data corresponding to a spatial path starting point and spatial path ending point of a motion path; determining a candidate foothold of each foot in the motion path based on the spatial path starting point and the spatial path ending point; determining a variation relationship between a center of mass position variation coefficient and a foot contact force based on the center of mass state data; screening out, under restrictions of a constraint set, a target center of mass position variation coefficient and target foothold that satisfy the variation relationship; determining a target motion control parameter according to the target center of mass position variation coefficient and the target foothold; and controlling a legged robot based on the target motion control parameter to move according to the motion path.
-
公开(公告)号：US12130366B2
公开(公告)日：2024-10-29
申请号：US17973080
申请日：2022-10-25
发明人： Jinglan Su
CPC分类号： G01S19/071 , G01S19/235 , G01S19/254
摘要： An error model calibration method can analyze discrete distribution situations of a pseudo-range measurement error and a Doppler measurement error under different carrier-to-noise ratios and altitude helping to calibrate and improve the universality of error model calibration. Observation data is received and satellite data is acquired based on the observation data. A pseudo-range error array and a Doppler error array are calibrated based on the observation data, geometric parameters, and the satellite data. The pseudo range error array describes errors of two terminals under a carrier-to-noise ratio and altitude angle of a satellite. The Doppler error array describes a discrete distribution of the two terminals. The pseudo-range error models respectively corresponding to the at least two terminals are fit using the pseudo-range error array. The Doppler error models respectively corresponding to the at least two terminals are fit using the Doppler error array.
-
公开(公告)号：US12128310B2
公开(公告)日：2024-10-29
申请号：US17891998
申请日：2022-08-19
发明人： Weixi Jia
IPC分类号： A63F13/56 , A63F13/67 , A63F13/795
CPC分类号： A63F13/56 , A63F13/67 , A63F13/795
摘要： Disclosed is a virtual character interaction method, including: displaying a viewing-only picture of a virtual character interaction scene; switching from the viewing-only picture to a virtual character simulation interaction interface in response to an interaction simulation operation triggered during displaying of the viewing-only picture; simulating, in the virtual character simulation interaction interface, virtual characters in the virtual character interaction scene, and displaying a scene status of interaction between the virtual characters, wherein the virtual characters include a simulated virtual character controlled by a user of the computer device; and controlling the simulated virtual character to perform a corresponding action in response to a control operation triggered on the virtual character simulation interaction interface by the user of the computer device.
-
公开(公告)号：US12128307B2
公开(公告)日：2024-10-29
申请号：US18117567
申请日：2023-03-06
发明人： Han Wang
IPC分类号： A63F13/537 , G01C21/04 , G06T11/20
CPC分类号： A63F13/537 , G01C21/04 , G06T11/206
摘要： The present disclosure describes methods, devices, and storage medium for displaying an azimuth in a virtual scene, which belongs to the field of computer technologies. The method includes obtaining, by a device, an orientation azimuth of a virtual object in a virtual scene. The device includes a memory storing instructions and a processor in communication with the memory. The method further includes obtaining, by the device, a plurality of azimuths, angles between the plurality of azimuths and the orientation azimuth being no larger than a preset angle, the plurality of azimuths comprising first azimuths and second azimuths. The method also includes symmetrically distributing, by the device, the first azimuths and the second azimuths centered and on two sides of the orientation azimuth to obtain a target horizontal bar dial; and displaying, by the device, the target horizontal bar dial in a visual field image of the virtual object.
-
公开(公告)号：US20240355110A1
公开(公告)日：2024-10-24
申请号：US18752567
申请日：2024-06-24
发明人： Yawen HUANG , Ziyun CAI , Dandan ZHANG , Yuexiang LI , Hong WANG , Yefeng ZHENG
IPC分类号： G06V10/82 , G06T11/60 , G06V10/44 , G06V10/764
CPC分类号： G06V10/82 , G06T11/60 , G06V10/44 , G06V10/764
摘要： A method for training an image classification model performed by an electronic device and includes: obtaining a plurality of sample source-domain images, a plurality of sample target-domain images, modal tagging results of the sample source-domain images, and category tagging results of the sample source-domain images; determining first category prediction results of the sample source-domain images by using a neural network model; determining first category prediction results of the sample target-domain images by using the neural network model; for a category tagging result, determining a first loss of the category tagging result based on source-domain image feature pairs corresponding to the category tagging result; and training the neural network model based on first losses of category tagging results, the first category prediction results of the sample source-domain images, and the first category prediction results of the sample target-domain images, to obtain an image classification model.
-
公开(公告)号：US20240355025A1
公开(公告)日：2024-10-24
申请号：US18761158
申请日：2024-07-01
发明人： Yingjie MEI , Meng WEI , Xianqi JING , Lili HAO , Xingyu XIAO , Hongjiang WANG , Ruowei JIANG , Jun ZHANG , Xiaogiang HONG , Lichao WU
IPC分类号： G06T13/00 , A63F13/30 , A63F13/53 , G06F3/04817
CPC分类号： G06T13/00 , A63F13/30 , A63F13/53 , G06F3/04817
摘要： This application provides an inter-account interaction method performed by a computer device. The method includes: displaying a battle preparation interface of a virtual battle, the battle preparation interface comprising a first icon representing a first account associated with the computer device and at least one second icon representing an account other than the first account; in response to a trigger operation on one of the at least one second icon as a target icon, displaying a prop selection area on the battle preparation interface and at least one interactive prop owned by the first account in the prop selection area; and in response to a selection of one of the at least one interactive prop as a target interactive prop, playing a target special effect animation of transmitting a special effect resource of the target interactive prop pointing from the first icon to the target icon.
-
公开(公告)号：US20240350926A1
公开(公告)日：2024-10-24
申请号：US18751588
申请日：2024-06-24
发明人： Haosheng Xue , Jinlong Tu , Zhipeng Luo
IPC分类号： A63F13/803 , A63F13/537
CPC分类号： A63F13/803 , A63F13/537
摘要： A method and an apparatus for controlling a virtual vehicle in a virtual scene, an electronic device, and a storage medium relate to the field of virtual scene technologies. In this application, A prop storage mechanism in which special effect action is performed to accumulate acceleration energy and an acceleration prop is added when the accumulated acceleration energy satisfies a prop addition condition is provided, one acceleration prop is consumed to accelerate a virtual vehicle when a first trigger operation is detected, and in a first period of time after the first trigger operation, if it is detected that a second trigger operation can further consume another acceleration prop, the virtual vehicle is accelerated at a higher acceleration, so that a user can flexibly select, according to a requirement, whether to consume a plurality of acceleration props each time to obtain a higher acceleration, thereby helping the user adjust a racing policy based on the virtual vehicle at any time.
-
9.发明公开公开(公告)号：US20240350919A1
公开(公告)日：2024-10-24
申请号：US18763869
申请日：2024-07-03
IPC分类号： A63F13/56 , A63F13/537
CPC分类号： A63F13/56 , A63F13/537
摘要： Disclosed is a method for controlling a virtual object performed by a computer device. The method includes: displaying at least two skill controls sharing a same skill point set, the skill point set including at least two skill points, and each skill control corresponding to one skill group, each skill group including at least one skill; determining a target first skill point in the at least two skill points in response to an operation on a first skill control in the at least two skill controls; and controlling a first virtual object to cast a skill corresponding to the first skill point in the skill group corresponding to the first skill control. In this application, a skill group corresponding to skill points is set for each skill control, and a skill can be added without adding a skill control, thereby improving the diversity of skill casting without affecting a user experience.
-
公开(公告)号：US20240350918A1
公开(公告)日：2024-10-24
申请号：US18763843
申请日：2024-07-03
IPC分类号： A63F13/56 , A63F13/537
CPC分类号： A63F13/56 , A63F13/537
摘要： This application provides a virtual character control method performed by a computer device. The method includes: displaying a movement control and an attack control on a virtual scene; in response to a first operation on the movement control by a user of the computer device, controlling the first virtual character to move at a movement speed in the virtual scene; while the first virtual character remains in a moving state in the virtual scene, increasing rush energy corresponding to the first virtual character in response to a second operation on the attack control by the user of the computer device; and when the rush energy satisfies a first condition, controlling the first virtual character to accelerate the movement speed until the rush energy corresponding to the first virtual character is drained.
-
-
-
-
-
-
-
-
-
搜索结果
9640 条记录 (耗时 0.055 秒)
