-
1.发明授权公开(公告)号：US11734841B2
公开(公告)日：2023-08-22
申请号：US17349952
申请日：2021-06-17
发明人： Yachong Xue , Hao Zhang , Lili Chen , Jiankang Sun , Guixin Yan , Xiaolei Liu , Yaoyu Lv , Menglei Zhang , Xinkai Li
CPC分类号： G06T7/292 , G06F3/013 , G06T3/40 , G06T7/73 , G06V40/161 , G06V40/19 , H04N23/90 , G06T2207/20212 , G06T2207/30201
摘要： A method for tracking eye gaze, a system, a processing device and a computer readable storage medium are provided. The method includes: acquiring original images acquired by multiple image acquisition devices, splicing the multiple original images into a spliced image, and determining a responsible region of each image acquisition device in the spliced image; performing preliminary face locating on the spliced image, and determining one or more original images corresponding to a preliminarily located face position according to the preliminarily located face position and the responsible region; and performing secondary face locating on the one or more determined original images to obtain face pose information and a positional relation of pupils with respect to human eyes, and calculating coordinates of gaze points of the human eyes according to the obtained face pose information and the positional relation of the pupils with respect to the human eyes.
-
公开(公告)号：US11699303B2
公开(公告)日：2023-07-11
申请号：US17319933
申请日：2021-05-13
发明人： Yachong Xue , Hao Zhang , Lili Chen , Jiankang Sun , Xinkai Li , Guixin Yan , Xiaolei Liu , Yaoyu Lv , Menglei Zhang
CPC分类号： G06V40/193 , G06T7/80 , G06V40/171 , G06V40/19
摘要： A system and a method of calculating coordinates of a pupil center point are provided. The system for acquiring the coordinates of the pupil center point includes a first camera, a second camera, a storage and a processor. The first camera is configured to capture a first image including a face and output the first image to the processor, the second camera is configured to capture a second image including a pupil and output the second image to the processor, a resolution of the first camera is smaller than a resolution of the second camera, and the storage is configured to store processing data, and the processor is configured to: acquire the first image and the second image; extract a first eye region corresponding to an eye from the first image; convert the first eye region into the second image, to acquire a second eye region corresponding to the eye in the second image; and detect a pupil in the second eye region and acquire the coordinates of the pupil center point.
-
公开(公告)号：US20220084102A1
公开(公告)日：2022-03-17
申请号：US17471649
申请日：2021-09-10
发明人： Menglei Zhang
摘要： A commodity recommendation method includes: receiving at least one image of a first commodity sent by a shopping cart, and the first commodity being a commodity placed in the shopping cart; inputting the at least one image into a commodity recognition model for commodity recognition to obtain commodity recognition information; inputting the commodity recognition information into a commodity recommendation model for purchase demand prediction to obtain at least one target recommended commodity; and sending information of the at least one target recommended commodity to the shopping cart.
-
4.发明授权公开(公告)号：US12020655B2
公开(公告)日：2024-06-25
申请号：US18014184
申请日：2021-08-16
发明人： Yachong Xue , Xue Dong , Hao Zhang , Lili Chen , Jiankang Sun , Guixin Yan , Yaoyu Lv , Menglei Zhang , Xinkai Li
CPC分类号： G09G3/3426 , G06F3/013 , G09G2320/0626 , G09G2320/0686 , G09G2354/00 , G09G2360/16
摘要： Provided is a method for controlling a display apparatus. In the method, the display apparatus receives at least two pieces of data to be displayed from at least two terminals respectively, wherein the at least two pieces of data to be displayed include screen projection data and status parameters of the at least two terminals, and then displays the status parameter, and performs a screen projection based on the screen projection data.
-
公开(公告)号：US12125093B2
公开(公告)日：2024-10-22
申请号：US17471649
申请日：2021-09-10
发明人： Menglei Zhang
IPC分类号： G06Q30/0601 , G06N3/08 , G06T7/70 , G06V10/46 , G06V20/64
CPC分类号： G06Q30/0633 , G06N3/08 , G06Q30/0631 , G06T7/70 , G06V10/462 , G06V20/64
摘要： A commodity recommendation method includes: receiving at least one image of a first commodity sent by a shopping cart, and the first commodity being a commodity placed in the shopping cart; inputting the at least one image into a commodity recognition model for commodity recognition to obtain commodity recognition information; inputting the commodity recognition information into a commodity recommendation model for purchase demand prediction to obtain at least one target recommended commodity; and sending information of the at least one target recommended commodity to the shopping cart.
-
公开(公告)号：US11854170B2
公开(公告)日：2023-12-26
申请号：US17436648
申请日：2020-12-24
发明人： Yaoyu Lv , Yachong Xue , Menglei Zhang , Xiaolei Liu , Lili Chen , Hao Zhang
CPC分类号： G06T5/006 , G06F3/013 , G06T7/70 , G06T2207/30201
摘要： An image distortion processing method, including: determining a first relationship between a position of a human eye and a viewing position of the human eye on the VR screen; displaying an initially distorted image on the VR screen; determining a first feature point located at a first initial position in the initially distorted image; determining a first human eye position of the human eye in a case of viewing the first feature point located at a first target position; determining the first target position according to the first relationship and the first human eye position; determining a first target distortion parameter corresponding to the first feature point located at the first target position according to a relationship between a position of the feature point on the VR screen and a distortion parameter; and performing distortion on an image displayed on the VR screen according to the first target distortion parameter.
-
公开(公告)号：US12056943B2
公开(公告)日：2024-08-06
申请号：US17507609
申请日：2021-10-21
发明人： Menglei Zhang
IPC分类号： G06V20/64 , G06T3/4007 , G06T3/4046 , G06T7/50 , G06V10/46
CPC分类号： G06V20/64 , G06T3/4007 , G06T3/4046 , G06T7/50 , G06V10/462 , G06T2207/20016 , G06T2207/20084
摘要： An object recognition method, an object recognition system, and a readable storage medium are provided. The object recognition method is to recognize an object from a first image, and includes: acquiring a first image; calculating depth information of the first image; performing superpixel segmentation on the first image, to obtain a superpixel image; generating three-dimensional image data of the first image according to the depth information and the image data of the superpixel image; and inputting the three-dimensional image data into a depth neural network for object recognition, to obtain a recognition result.
-
公开(公告)号：US11705045B2
公开(公告)日：2023-07-18
申请号：US17417237
申请日：2020-09-11
发明人： Yaoyu Lv , Zhanshan Ma , Yachong Xue , Menglei Zhang , Lili Chen , Hao Zhang
CPC分类号： G09G3/2007 , G09G3/001
摘要： Disclosed are a method for generating display data by a rotatory stereoscopic display apparatus, a display driving method, a computer device, a rotatory stereoscopic display apparatus, and a stereoscopic display system. The method for generating display data includes: generating, based on display parameters of the rotatory stereoscopic display apparatus and a model to be displayed, an image array for displaying the model; generating, for an image in the image array, an initial data stream of the image, the initial data stream including: grayscale datum of each pixel in the image; and performing data compression on the initial data stream to generate a compressed data stream, the compressed data stream including: data units of pixels whose grayscale data is non-zero data, each data unit including: grayscale datum of the pixel and an order of the grayscale datum in the initial data stream.
-
9.发明授权公开(公告)号：US11967181B2
公开(公告)日：2024-04-23
申请号：US17435306
申请日：2021-02-09
发明人： Menglei Zhang
CPC分类号： G06V40/197 , G06T7/0012 , G06V10/25 , G06V10/267 , G06V10/7715 , G06V10/82 , G06T2207/20081 , G06T2207/20084 , G06T2207/30041 , G06T2207/30096 , G06V2201/03
摘要： The present disclosure provides a method and a device for retina image recognition, an electronic equipment, and a storage medium, the method including: acquiring a retinal image; classifying the retinal image by using a first neural network model to obtain an image classification result; if the image classification result meets a preset condition, segmenting the retinal image by using a second neural network model to obtain an image segmentation result; generating a recognition result of the retinal image according to the image segmentation result and in combination with a decision tree model.
-
公开(公告)号：US11941171B1
公开(公告)日：2024-03-26
申请号：US17765612
申请日：2021-05-28
发明人： Menglei Zhang , Jiankang Sun , Guixin Yan , Yaoyu Lv , Yachong Xue , Xinkai Li
IPC分类号： G06F3/01 , G06T7/215 , G06T7/292 , G06T7/73 , G06T11/00 , G06V10/22 , G06V10/764 , G06V10/82 , G06V40/10
CPC分类号： G06F3/013 , G06T7/215 , G06T7/292 , G06T7/74 , G06T11/00 , G06V10/235 , G06V10/764 , G06V10/82 , G06V40/10 , G06T2207/20084 , G06T2207/30201
摘要： An eye gaze tracking method, apparatus and system are provided, which belong to the technical field of image processing. The eye gaze tracking method includes: capturing, by at least two cameras, frames of facial images when a viewer views display screen; segmenting a current frame of facial image with pre-trained eye detection model to obtain an image for left and right eyes; calculating a similarity between the current frame of facial image and each of previous N frames of facial images; if the similarity between the current frame of facial image and each of previous N frames of facial images is less than the preset threshold, detecting a position on display screen at which the eyes of the viewer gaze with pre-trained eye detection model. Embodiments of the present disclosure can improve accuracy and efficiency of eye gaze tracking.
-
-
-
-
-
-
-
-
-
搜索结果
11 条记录 (耗时 0.028 秒)
