-
1.发明申请公开(公告)号：US20210074012A1
公开(公告)日：2021-03-11
申请号：US16975242
申请日：2019-04-23
申请人： Tsinghua University
摘要： Provided are a three-dimensional reconstruction method, apparatus and system of a dynamic scene, a server and a medium. The method includes: acquiring multiple continuous depth image sequences of the dynamic scene, where the multiple continuous depth image sequences are captured by an array of drones equipped with depth cameras; fusing the multiple continuous depth image sequences to establish a three-dimensional reconstruction model of the dynamic scene; obtaining target observation points of the array of drones through calculation according to the three-dimensional reconstruction model and current poses of the array of drones; and instructing the array of drones to move to the target observation points to capture, and updating the three-dimensional reconstruction model according to multiple continuous depth image sequences captured by the array of drones at the target observation points.
-
公开(公告)号：US20200241273A1
公开(公告)日：2020-07-30
申请号：US16357838
申请日：2019-03-19
申请人： TSINGHUA UNIVERSITY
发明人： Qionghai Dai , You ZHOU , Jiamin Wu , Guoxun Zhang
摘要： Provided are a microscopic imaging system and a microscopic imaging method. The system includes: an illumination module configured to generate a laser illumination, an LCOS device located in a Fourier plane of the laser illumination and configured to modulate a phase of the laser illumination, a 4-F system configured to adjust a size of a light beam of the laser illumination, an excitation lens group configured to generate a point illumination focused in a sample plane, a detecting lens group configured to capture an image of a PSF of the point illumination, a camera sensor, and a controller configured to synchronously control a change in a phase pattern of the LCOS device and an image capture of the camera sensor.
-
公开(公告)号：US10539771B2
公开(公告)日：2020-01-21
申请号：US15629220
申请日：2017-06-21
申请人： TSINGHUA UNIVERSITY
发明人： Qionghai Dai , Jiamin Wu , Jijun He
摘要： An imaging system is provided, which includes: a microscope; a field diaphragm; a one-dimensional beam-splitting grating, configured to duplicate a beam after passing through the first 4f system into beams with different angles; a phase modulation component, configured to perform different phase modulations to the beams with different angles respectively; a blazed grating, configured to perform dispersion to the beams with different angles passing through the phase modulation component at a dimension orthogonal to the beam-splitting grating; a micro lens array, configured to make the beams with different angles passing through the blazed grating to map to different locations on a back focal plane of the micro lens array; an image sensor, configured to image the back focal plane of the micro lens array. The system may recover three-dimensional information and multispectral information of the sample simultaneously from a single image.
-
公开(公告)号：US20180203221A1
公开(公告)日：2018-07-19
申请号：US15581731
申请日：2017-04-28
申请人： TSINGHUA UNIVERSITY
发明人： Qionghai Dai , Mingjie Zhang , Jiamin Wu
CPC分类号： G02B21/365 , G02B21/086 , G02B21/14
摘要： A phase microscopy system and method are provided in the present disclosure. The system includes: an optical source, configured to generate collimated light; an object arrangement component, configured to provide a mask and a sample; a microscopic imaging component, including a microscope and a sensor, the microscope being configured to project light that passes successively through the mask and the sample into the sensor to capture an image; and a control component, configured to reconstruct phase information of the sample based on the image through both the sample and the mash and a pre-stored reference image of the mask, in which the pre-stored reference image is pre-acquired by the phase microscopy system without providing the sample under a same light condition. With the present disclosure, dynamic phase information of the microscopic sample can be acquired accurately and rapidly with high resolution.
-
公开(公告)号：US20180203218A1
公开(公告)日：2018-07-19
申请号：US15629220
申请日：2017-06-21
申请人： TSINGHUA UNIVERSITY
发明人： Qionghai Dai , Jiamin Wu , Jijun He
IPC分类号： G02B21/00
CPC分类号： G02B21/0024 , G02B21/0032 , G02B21/0064
摘要： An imaging system is provided, which includes: a microscope; a field diaphragm; a one-dimensional beam-splitting grating, configured to duplicate a beam after passing through the first 4f system into beams with different angles; a phase modulation component, configured to perform different phase modulations to the beams with different angles respectively; a blazed grating, configured to perform dispersion to the beams with different angles passing through the phase modulation component at a dimension orthogonal to the beam-splitting grating; a micro lens array, configured to make the beams with different angles passing through the blazed grating to map to different locations on a back focal plane of the micro lens array; an image sensor, configured to image the back focal plane of the micro lens array. The system may recover three-dimensional information and multispectral information of the sample simultaneously from a single image.
-
6.发明授权公开(公告)号：US11514607B2
公开(公告)日：2022-11-29
申请号：US17036457
申请日：2020-09-29
申请人： TSINGHUA UNIVERSITY
发明人： Lu Fang , Dawei Zhong , Qionghai Dai
摘要： The disclosure provides 3D reconstruction methods and devices. The method includes: obtaining data captured by the camera and data captured by the inertial measurement unit; obtaining a pose of the camera based on the data; obtaining an adjustment value of the pose of the camera and an adjustment value of bias of the inertial measurement unit; updating the pose of the camera based on the adjustment value of the pose of the camera; determining whether the adjustment value of bias of the inertial measurement unit is less than a preset value; in response to the adjustment value of bias of the inertial measurement unit being greater than or equal to the preset value, determining that a current loop for 3-dimensional reconstruction is an error loop; removing the error loop; and constructing a 3-dimensional model for surroundings of the camera based on the updated pose of the camera and remaining loops.
-
公开(公告)号：US11461911B2
公开(公告)日：2022-10-04
申请号：US17034563
申请日：2020-09-28
申请人： Tsinghua University
发明人： Lu Fang , Dingjian Jin , Anke Zhang , Qionghai Dai
IPC分类号： G06T7/557 , G06T7/80 , H04N13/128 , H04N13/246 , H04N13/00
摘要： A depth information calculation method and device based on a light-field-binocular system. The method includes obtaining a far-distance disparity map based on binocular information of calibrated input images, setting respective first confidences pixels in the disparity map, and obtaining a first target confidence; detecting the first confidence of a pixel being smaller than a preset value and responsively determining a new disparity value based on light field information of the input images, determining an update depth value based on the new disparity value, and obtaining a second target confidence of the pixel; and combining the far-distance disparity map and a disparity map formed by the new disparity value on a same unit into an index map, combining the first confidence and the first target confidence into a confidence map, optimizing the index and confidence maps to obtain a final disparity map, which is converted to a final depth map.
-
8.发明授权公开(公告)号：US11450017B1
公开(公告)日：2022-09-20
申请号：US17742821
申请日：2022-05-12
申请人： Tsinghua University
发明人： Lu Fang , Zhihao Xu , Xiaoyun Yuan , Tiankuang Zhou , Qionghai Dai
IPC分类号： G06T7/557 , H04N13/128 , G06N3/04 , H04N13/00 , H04N13/239 , H04N13/271 , G06T7/593 , G02B27/14
摘要： A method for intelligent light field depth classification based on optoelectronic computing includes capturing and identifying binocular images of a scene within a depth range through a pair of binocular cameras; mapping each depth value in the depth range to a disparity value between the binocular images, to obtain a disparity range of the scene within the depth range; labeling training data based on the disparity range to obtain a pre-trained diffraction neural network model; loading a respective weight for each layer of a network obtained after training into a corresponding optical element based on the pre-trained diffraction neural network model; and after the respective weight for each layer of the network is loaded, performing forward propagation inference on new input data of the scene, and outputting a depth classification result corresponding to each pixel in the binocular images of the scene.
-
9.发明申请公开(公告)号：US20210110599A1
公开(公告)日：2021-04-15
申请号：US16977899
申请日：2019-04-28
申请人： Tsinghua University
发明人： Lu Fang , Mengqi Ji , Lei Han , Zhuo Su , Qionghai Dai
摘要： Provided are a depth camera based three-dimensional reconstruction method and apparatus, a device and a storage medium. The method includes: acquiring at least two frames of images obtained by capturing a target scenario by a depth camera; determining, according to the at least two frames of images, relative camera poses in response to capturing the target scenario by the depth camera; by adopting a manner of at least two levels of nested screening, determining at least one feature voxel from each frame of image, where each level of screening adopts a respective voxel partitioning rule; fusing and calculating the at least one feature voxel of each frame of image according to a respective relative camera pose of each frame of image to obtain a grid voxel model of the target scenario; and generating an isosurface of the grid voxel model to obtain a three-dimensional reconstruction model of the target scenario.
-
公开(公告)号：US20210097648A1
公开(公告)日：2021-04-01
申请号：US17036493
申请日：2020-09-29
申请人： TSINGHUA UNIVERSITY
发明人： Lu Fang , Yinheng Zhu , Qionghai Dai
摘要： The present disclosure provides a multi-image-based image enhancement method and device, an electronic device and a non-transitory computer readable storage medium. The method includes: aligning a low-resolution target image and a reference image in an image domain; performing, an alignment in a feature domain; and synthesizing features corresponding to the low-resolution target image and features corresponding to the reference image to generate a final output.
-
-
-
-
-
-
-
-
-
搜索结果
49 条记录 (耗时 0.014 秒)
