-
81.发明授权公开(公告)号：US11593958B2
公开(公告)日：2023-02-28
申请号：US17064580
申请日：2020-10-06
申请人： FUJIFILM Corporation
发明人： Shuji Ono
摘要： There are provided an imaging device, a distance measurement method, a distance measurement program, and a recording medium capable of accurately measuring a distance to a subject without depending on a color of the subject.
A bifocal imaging lens, a first pixel and a second pixel that respectively pupil-divide and selectively receive luminous flux incident through a first region of the first region and a second region having different focusing distances of the imaging lens, an image sensor having a third pixel and a fourth pixel corresponding to the second region, a first image acquisition unit (41-1) and a second image acquisition unit (41-2) that acquire a first image and a second image having asymmetric blurs from a first pixel group (22A) and a third pixel group (22C) of the image sensor, a third image acquisition unit (43-1) and a fourth image acquisition unit (43-2) that add pixel values of adjacent pixels of the first and second pixels of the image sensor and add pixel values of adjacent pixels of the third and fourth pixels to acquire a third image and a fourth image having symmetric blurs, and a distance calculation unit (45) that calculates a distance to a subject in the image based on the acquired first and third images or the acquired second and fourth images are included.-
公开(公告)号：US20230033177A1
公开(公告)日：2023-02-02
申请号：US17390174
申请日：2021-07-30
申请人： Zoox, Inc.
发明人： Kratarth Goel
摘要： Techniques are discussed herein for generating three-dimensional (3D) representations of an environment based on two-dimensional (2D) image data, and using the 3D representations to perform 3D object detection and other 3D analyses of the environment. 2D image data may be received, along with depth estimation data associated with the 2D image data. Using the 2D image data and associated depth data, an image-based object detector may generate 3D representations, including point clouds and/or 3D pixel grids, for the 2D image or particular regions of interest. In some examples, a 3D point cloud may be generated by projecting pixels from the 2D image into 3D space followed by a trained 3D convolutional neural network (CNN) performing object detection. Additionally or alternatively, a top-down view of a 3D pixel grid representation may be used to perform object detection using 2D convolutions.
-
公开(公告)号：US20230032791A1
公开(公告)日：2023-02-02
申请号：US17870463
申请日：2022-07-21
发明人： Lukas BUSCHLE , Simon HAAG , Jasmin KEUSER , Benedikt KÖHLER
摘要： An exemplary embodiment relates to a measuring method (50) and to a measuring device (10) in order to determine a length or an area within a scene (32) which are characterized at least partially by a real start point (40-2) and a real end point (42-2), wherein the measurement takes place using at least two images (18, 20) and it is thereby not necessary for the real start point (40-2) and the real end point (42-2) to be imaged in one of the images (18, 20).
-
公开(公告)号：US20220414912A1
公开(公告)日：2022-12-29
申请号：US17356553
申请日：2021-06-24
发明人： Hsueh-Tsung Lu , Ching-Wen Wang , Cheng-Che Tsai , Wu-Feng Chen
摘要： A method for performing region-of-interest (ROI)-based depth detection with aid of a pattern-adjustable projector and associated apparatus are provided. The method includes: utilizing a first camera to capture a first image, wherein the first image includes image contents indicating one or more objects; utilizing an image processing circuit to determine a ROI of the first image according to the image contents of the first image; utilizing the image processing circuit to perform projection region selection to determine a selected projection region corresponding to the ROI among multiple predetermined projection regions, wherein the selected projection region is selected from the multiple predetermined projection regions according to the ROI; utilizing the pattern-adjustable projector to project a predetermined pattern according to the selected projection region, for performing depth detection; utilizing a second camera to capture a second image; and performing the depth detection according to the second image to generate a depth map.
-
公开(公告)号：US20220327674A1
公开(公告)日：2022-10-13
申请号：US17629984
申请日：2020-04-17
发明人： Ruirong YOU
摘要： A method for fusing images and apparatus, a storage medium, and a terminal are provided. The method for fusing images includes: obtaining a long-focal image to be fused and a wide-angle image to be fused; detecting feature points of the long-focal image and wide-angle image with a same scale, and matching the feature points to obtain matching feature point pairs; determining a fusion area based on position distributions of the matching feature point pairs; calculating a mapping matrix from the long-focal image to the wide-angle image at least based on coordinates of the matching feature point pairs in the long-focal image and the wide-angle image; and resampling the long-focal image based on the mapping matrix, and fusing the resampled long-focal image and the wide-angle image in the fusion area to obtain a fused image.
-
公开(公告)号：US20220301210A1
公开(公告)日：2022-09-22
申请号：US17466794
申请日：2021-09-03
发明人： Nao Mishima , Naoki Nishizawa
IPC分类号： G06T7/571
摘要： According to one embodiment, a learning method for causing a statistical model to learn is provided. The statistical model is generated by learning a bokeh caused in a first image captured in a first domain in accordance with a distance to a first subject included in the first image, the method includes acquiring a plurality of second images by capturing a second subject from multiple viewpoints in a second domain other than the first domain, and causing the statistical model to learn using the second images.
-
公开(公告)号：US11367209B2
公开(公告)日：2022-06-21
申请号：US17078490
申请日：2020-10-23
申请人： X Development LLC
发明人： Barnaby John James
摘要： Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for visually detecting a halocline. In some implementations, a method includes moving a camera through different depths of water within a fish enclosure, capturing, at the different depths, images of fish, determining that changes in focus in the images correspond to changes in depth that the images were captured, and based on determining that the changes in focus in the images correspond to the changes in depths that the images were captured, detecting a halocline at a particular depth.
-
公开(公告)号：US20220166921A1
公开(公告)日：2022-05-26
申请号：US17437958
申请日：2020-02-06
申请人： NEC Corporation
发明人： Yuka OGINO , Keiichi CHONO
摘要： The image processing apparatus 10 includes image storage means 11 for sequentially storing images continuously captured in time, thinning means 12 for performing a thinning process for the images continuously captured in time, first image evaluation means 13 for performing first focus evaluation on the images after the thinning process is performed, selection means 14 for selecting a plurality of in-focus frame candidates from the images continuously captured in time, based on an evaluation result of the first focus evaluation, second image evaluation means 15 for reading the images of the in-focus frame candidates selected by the selection means 14 from the image storage means 11 and performing second focus evaluation on the read images, and matching image determination means 16 for selecting a matching image for an authentication process from the images of the in-focus frame candidates, based on an evaluation result of the second focus evaluation.
-
公开(公告)号：US11270459B2
公开(公告)日：2022-03-08
申请号：US16854977
申请日：2020-04-22
申请人： Dell Products L.P.
摘要： A system, method, and computer-readable medium are disclosed for augmented reality detection of enterprise systems in a data center. An augmented reality view is captured of an enterprise system and objects of the enterprise system. Significant areas are detected of the enterprise. In the captured augmented reality view bounding boxes are added around the significant areas. Determination is performed of three-dimensional orientation of the significant areas. Depth of the signification areas is determined based on the three-dimensional orientation.
-
公开(公告)号：US11257229B2
公开(公告)日：2022-02-22
申请号：US16701257
申请日：2019-12-03
发明人： Harel Haim , Emanuel Marom , Alexander Bronstein
摘要： A method of processing an image is disclosed. The method comprises decomposing the image into a plurality of channels, each being characterized by a different depth-of-field, and accessing a computer readable medium storing an in-focus dictionary defined over a plurality of dictionary atoms, and an out-of-focus dictionary defined over a plurality of sets of dictionary atoms, each set corresponding to a different out-of-focus condition. The method also comprises computing one or more sparse representations of the decomposed image over the dictionaries.
-
-
-
-
-
-
-
-
-
搜索结果
388 条记录 (耗时 0.026 秒)
