-
公开(公告)号：US11915439B2
公开(公告)日：2024-02-27
申请号：US17353634
申请日：2021-06-21
Inventor： Xiaoqing Ye , Hao Sun
CPC classification number: G06T7/55 , G06N3/08 , G06T7/174 , G06T7/70 , G06T11/60 , G06T2207/20081 , G06T2207/20084
Abstract: The present disclosure provides a method of training a depth estimation network, which relates to fields of computer vision, deep learning, and image processing technology. The method includes: performing a depth estimation on an original image by using a depth estimation network, so as to obtain a depth image for the original image; removing a moving object from the original image so as to obtain a preprocessed image for the original image; estimating a pose based on the original image and modifying the pose based on the preprocessed image; and adjusting parameters of the depth estimation network according to the original image, the depth image and the pose modified. The present disclosure further provides an apparatus of training a depth estimation network, a method and apparatus of estimating a depth of an image, an electronic device, and a storage medium.
-
公开(公告)号：US11823437B2
公开(公告)日：2023-11-21
申请号：US17658508
申请日：2022-04-08
Inventor： Xiao Tan , Xiaoqing Ye , Hao Sun
CPC classification number: G06V10/7715 , G06T3/0031 , G06V10/80 , G06V10/82 , G06V20/56
Abstract: The present disclosure provides a target detection and model training method and apparatus, a device and a storage medium, and relates to the field of artificial intelligence, and in particular, to computer vision and deep learning technologies, which may be applied to smart city and intelligent transportation scenarios. The target detection method includes: performing feature extraction processing on an image to obtain image features of a plurality of stages of the image; performing position coding processing on the image to obtain a position code of the image; obtaining detection results of the plurality of stages of a target in the image based on the image features of the plurality of stages and the position code; and obtaining a target detection result based on the detection results of the plurality of stages.
-
公开(公告)号：US20230122373A1
公开(公告)日：2023-04-20
申请号：US18083272
申请日：2022-12-16
Inventor： Xiaoqing Ye , Hao Sun
IPC: G06T7/55
Abstract: A method for training a depth estimation model includes: obtaining sample images; generating sample depth images and sample residual maps corresponding to the sample images; determining sample photometric error information corresponding to the sample images based on the sample depth images; and obtaining a target depth estimation model by training an initial depth estimation model based on the sample images, the sample residual maps and the sample photometric error information.
-
公开(公告)号：US20230368523A1
公开(公告)日：2023-11-16
申请号：US18152119
申请日：2023-01-09
Inventor： Xiaoqing Ye , Deguo Xia , Jizhou Huang , Haifeng Wang
CPC classification number: G06V20/182 , G06V10/7715 , G06V20/13 , G06V10/25 , G01C21/3852 , G01C21/3819 , G06V10/42
Abstract: Provided are a road network extraction method, a device, and a storage medium, which relate to the technical field of artificial intelligence and, in particular, to the fields of image processing, computer vision, and the like and are specifically applicable to scenarios such as intelligent transportation and a smart city. A specific implementation scheme includes: extracting a first road network of a target region according to user trajectories of the target region; extracting a second road network of the target region according to a satellite aerial image of the target region; and extract a target road network of the target region according to the first road network, the second road network, and the user trajectories. Efficient and accurate road network extraction can be achieved through techniques in embodiments of the present disclosure.
-
Patent Agency Ranking
公开(公告)号：US20220343603A1
公开(公告)日：2022-10-27
申请号：US17862588
申请日：2022-07-12
Inventor： Bo Ju , Xiaoqing Ye , Xiao Tan , Hao Sun
Abstract: Three-dimensional reconstruction method, three-dimensional reconstruction apparatus, device, and storage medium are provided. An implementation of the method may include: determining, based on an initial three-dimensional human body model, a target two-dimensional image corresponding to the three-dimensional human body model; semantically segmenting the target two-dimensional image, and determining semantic labels of pixels in the target two-dimensional image; determining semantic labels of skinned mesh vertices according to corresponding relationships between the skinned mesh vertices in the initial three-dimensional human body model and the pixels in the target two-dimensional image; determining target weights of the skinned mesh vertices according to the semantic labels of the skinned mesh vertices; and determining a target three-dimensional human body model according to the target weights.
-
公开(公告)号：US20220230343A1
公开(公告)日：2022-07-21
申请号：US17709291
申请日：2022-03-30
Inventor： Xiaoqing Ye , Xiao Tan , Hao Sun
IPC: G06T7/593
Abstract: A computer-implemented stereo matching method includes: obtaining a first binocular image; inputting the first binocular image into an object model for a first operation to obtain a first initial disparity map and a first offset disparity map with respect to the first initial disparity map; and performing aggregation on the first initial disparity map and the first offset disparity map to obtain a first target disparity map of the first binocular image. The first initial disparity map is obtained through stereo matching on a second binocular image corresponding to the first binocular image, a size of the second binocular image is smaller than a size of the first binocular image, and the first offset disparity map is obtained through stereo matching on the first binocular image within a predetermined disparity offset range.
-
7.发明申请公开(公告)号：US20220222951A1
公开(公告)日：2022-07-14
申请号：US17709283
申请日：2022-03-30
Inventor： Xiaoqing Ye , Hao Sun
Abstract: A 3D object detection method includes: obtaining a first monocular image; and inputting the first monocular image into an object model, and performing a first detection operation to obtain first detection information in a 3D space, wherein the first detection operation includes performing feature extraction in accordance with the first monocular image to obtain a first point cloud feature, adjusting the first point cloud feature in accordance with a target learning parameter to obtain a second point cloud feature, and performing 3D object detection in accordance with the second point cloud feature to obtain the first detection information, wherein the target learning parameter is used to present a difference degree between the first point cloud feature and a target point cloud feature of the first monocular image.
-
公开(公告)号：US20230095114A1
公开(公告)日：2023-03-30
申请号：US17658508
申请日：2022-04-08
Inventor： Xiao Tan , Xiaoqing Ye , Hao Sun
Abstract: The present disclosure provides a target detection and model training method and apparatus, a device and a storage medium, and relates to the field of artificial intelligence, and in particular, to computer vision and deep learning technologies, which may be applied to smart city and intelligent transportation scenarios. The target detection method includes: performing feature extraction processing on an image to obtain image features of a plurality of stages of the image; performing position coding processing on the image to obtain a position code of the image; obtaining detection results of the plurality of stages of a target in the image based on the image features of the plurality of stages and the position code; and obtaining a target detection result based on the detection results of the plurality of stages.
-
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
9
records
(took 0.018 seconds)
