-
公开(公告)号：US20220270289A1
公开(公告)日：2022-08-25
申请号：US17743402
申请日：2022-05-12
Inventor： Wei Zhang , Xiaoqing Ye , Xiao Tan , Hao Sun , Shilei Wen , Hongwu Zhang , Errui Ding
IPC: G06T7/73 , G06T7/194 , G06T7/593 , H04N13/128
Abstract: A method and device for detecting a vehicle pose, relating to the fields of computer vision and automatic driving. The specific implementation solution comprises: inputting a vehicle left view point image and a vehicle right view point image into a part prediction and mask segmentation network model, and determining foreground pixel points and part coordinates thereof in a reference image; converting coordinates of the foreground pixels in the reference image into coordinates of the foreground pixels in a camera coordinate system so as to obtain a pseudo-point cloud, and fusing part coordinate of the foreground pixels and the pseudo-point cloud to obtain fused pseudo-point cloud; and inputting the fused pseudo-point cloud into a pre-trained pose prediction model to obtain a pose information of the vehicle to be detected.
-
公开(公告)号：US11157698B2
公开(公告)日：2021-10-26
申请号：US16176783
申请日：2018-10-31
Inventor： Jizhou Huang , Yaming Sun , Wei Zhang , Haifeng Wang
IPC: G06F40/00 , G06F40/295 , G06F16/951 , G06K9/00 , G06K9/62 , G06N7/00 , G06F40/30 , G06F40/268 , G06F40/242
Abstract: The present disclosure provides a method of training a descriptive text generating model, and a method and apparatus for generating a descriptive text, wherein the method of training a descriptive text generating model comprises: obtaining training data, the training data comprising: a notional word, a first descriptive text and a second descriptive text of the notional word, wherein the second descriptive text is a concise expression of the first descriptive text; regarding the notional word and the first descriptive text of the notional word as input of a seq2seq model, regarding the second descriptive text of the notional word as output of the seq2sequ model, and training the seq2seq model to obtain a descriptive text generating model. The descriptive text generating model according to the present disclosure can implement generation of a concise descriptive text with respect to the notional word in a deep understanding manner.
-
公开(公告)号：US11514263B2
公开(公告)日：2022-11-29
申请号：US16869024
申请日：2020-05-07
Inventor： Wei Zhang , Xiao Tan , Hao Sun , Shilei Wen , Errui Ding
IPC: G06K9/62 , G06N3/04 , G06N3/08 , G06V10/44 , G06V10/80 , G06V10/82 , G06V40/16 , G06V10/26 , G06V10/22
Abstract: Embodiments of the present disclosure disclose a method and apparatus for processing an image. A specific embodiment of the method includes: acquiring a feature map of a target image, where the target image contains a target object; determining a local feature map of a target size in the feature map; combining features of different channels in the local feature map to obtain a local texture feature map; and obtaining location information of the target object based on the local texture feature map.
-
Patent Agency Ranking
公开(公告)号：US20210174537A1
公开(公告)日：2021-06-10
申请号：US16894123
申请日：2020-06-05
Inventor： Xiaoqing Ye , Xiao Tan , Wei Zhang , Hao Sun , Errui Ding
Abstract: Embodiments of the present disclosure provide a method and apparatus for detecting a target object in an image. The method includes: performing following prediction operations using a pre-trained neural network: detecting a target object in a two-dimensional image to determine a two-dimensional bounding box of the target object; and determining a relative position constraint relationship between the two-dimensional bounding box of the target object and a three-dimensional projection bounding box obtained by projecting a three-dimensional bounding box of the target object into the two-dimensional image; and the method further including: determining the three-dimensional projection bounding box of the target object, based on the two-dimensional bounding box of the target object and the relative position constraint relationship between the two-dimensional bounding box of the target object and the three-dimensional projection bounding box.
-
公开(公告)号：US20210064919A1
公开(公告)日：2021-03-04
申请号：US16869024
申请日：2020-05-07
Inventor： Wei Zhang , Xiao Tan , Hao Sun , Shilei Wen , Errui Ding
Abstract: Embodiments of the present disclosure disclose a method and apparatus for processing an image. A specific embodiment of the method includes: acquiring a feature map of a target image, where the target image contains a target object; determining a local feature map of a target size in the feature map; combining features of different channels in the local feature map to obtain a local texture feature map; and obtaining location information of the target object based on the local texture feature map.
-
公开(公告)号：US11776155B2
公开(公告)日：2023-10-03
申请号：US16894123
申请日：2020-06-05
Inventor： Xiaoqing Ye , Xiao Tan , Wei Zhang , Hao Sun , Errui Ding
IPC: G06T7/73 , G06N3/04 , G06N3/08 , G06T7/70 , G06T11/20 , G06V10/764 , G06V10/82 , G06V20/58 , G06V20/64 , G06V10/25 , G06F18/24 , G06F18/214
CPC classification number: G06T7/73 , G06F18/214 , G06F18/24 , G06N3/04 , G06N3/08 , G06T7/70 , G06T11/20 , G06V10/764 , G06V10/82 , G06V20/58 , G06V20/647 , G06T2207/20081 , G06T2207/20084 , G06T2210/12
Abstract: Embodiments of the present disclosure provide a method and apparatus for detecting a target object in an image. The method includes: performing following prediction operations using a pre-trained neural network: detecting a target object in a two-dimensional image to determine a two-dimensional bounding box of the target object; and determining a relative position constraint relationship between the two-dimensional bounding box of the target object and a three-dimensional projection bounding box obtained by projecting a three-dimensional bounding box of the target object into the two-dimensional image; and the method further including: determining the three-dimensional projection bounding box of the target object, based on the two-dimensional bounding box of the target object and the relative position constraint relationship between the two-dimensional bounding box of the target object and the three-dimensional projection bounding box.
-
7.发明授权公开(公告)号：US11538286B2
公开(公告)日：2022-12-27
申请号：US16710464
申请日：2019-12-11
Inventor： Wei Zhang , Xiao Tan , Hao Sun , Shilei Wen , Errui Ding
Abstract: A method and apparatus for vehicle damage assessment, an electronic device, and a computer-readable storage medium are provided. The method may include: extracting, from an input image, a first feature characterizing a part of a vehicle and a second feature characterizing a damage type of the vehicle; integrating the first feature and the second feature to generate a third feature characterizing a corresponding relation between the part and the damage type; converting the third feature into a characteristic vector; and determining a damage recognition result based on the characteristic vector. According to the technical solution of the disclosure, users can rapidly and accurately learn about the damage condition of the vehicle by providing pictures or videos of the damaged vehicle, thus providing an objective basis for subsequent damage assessment, claim settlement, and repair.
-
公开(公告)号：US10896188B2
公开(公告)日：2021-01-19
申请号：US16278651
申请日：2019-02-18
Inventor： Jizhou Huang , Wei Zhang , Yaming Sun , Haifeng Wang
IPC: G06F16/2457 , G06F16/248 , G06N3/04 , G06N3/08
Abstract: The present disclosure provides a method and apparatus for determining search results, a device and a computer storage medium, wherein the method comprises: obtaining a current query, a historical query sequence of the current query and candidate search results of the current query; inputting the current query, the historical query sequence of the current query and candidate search results of the current query into a search result-sorting model, scoring the candidate search results according to the search result-sorting model, and determining search results corresponding to the current query; wherein the scores rendered by the search result-sorting model for the candidate search results are determined according to a similarity degree between an integrated vector representation of the current query and the historical query sequence of the current query and vector representations of the candidate search results. The present disclosure can provide the user with search results which more accurately reflect the user's demands.
-
-
-
-
-
-
-
Search Results
8
records
(took 0.04 seconds)
