-
公开(公告)号:US20220413509A1
公开(公告)日:2022-12-29
申请号:US17900622
申请日:2022-08-31
申请人: NVIDIA Corporation
发明人: Michael Grabner , Jeremy Furtek , David Nister
摘要: Systems and methods for performing visual odometry more rapidly. Pairs of representations from sensor data (such as images from one or more cameras) are selected, and features common to both representations of the pair are identified. Portions of bundle adjustment matrices that correspond to the pair are updated using the common features. These updates are maintained in register memory until all portions of the matrices that correspond to the pair are updated. By selecting only common features of one particular pair of representations, updated matrix values may be kept in registers. Accordingly, matrix updates for each common feature may be collectively saved with a single write of the registers to other memory. In this manner, fewer write operations are performed from register memory to other memory, thus reducing the time required to update bundle adjustment matrices and thus speeding the bundle adjustment process.
-
2.
公开(公告)号:US11537277B2
公开(公告)日:2022-12-27
申请号:US16040220
申请日:2018-07-19
IPC分类号: G06F3/04845 , G06T7/11 , G06F3/04847 , G06N3/08 , G06T5/00 , G06T11/00 , G06N3/04 , G06T7/143 , G06T7/35
摘要: Embodiments described herein provide a system for generating semantically accurate synthetic images. During operation, the system generates a first synthetic image using a first artificial intelligence (AI) model and presents the first synthetic image in a user interface. The user interface allows a user to identify image units of the first synthetic image that are semantically irregular. The system then obtains semantic information for the semantically irregular image units from the user via the user interface and generates a second synthetic image using a second AI model based on the semantic information. The second synthetic image can be an improved image compared to the first synthetic image.
-
3.
公开(公告)号:US11443438B2
公开(公告)日:2022-09-13
申请号:US16888931
申请日:2020-06-01
发明人: Yi Li , Zhanghui Kuang , Yimin Chen , Wei Zhang
摘要: A distribution method includes: distributing, when multiple feature maps exist in an image processing model, to each feature map a neuron through which the feature map passes; filtrating, according to importance of neurons of multiple convolution layers in an image processing model, the neurons to obtain a first result; collecting, according to a position attribute of the each neuron in the first result, statistics on a scale of the feature map corresponding to each neuron to obtain a distribution relationship; the distribution relationship indicates a correspondence between the each feature map and the neuron through which the feature map passes; and distributing, according to the distribution relationship, to the each feature map the neuron through which the feature map passes.
-
公开(公告)号:US20220180541A1
公开(公告)日:2022-06-09
申请号:US17457119
申请日:2021-12-01
发明人: Oliver Zweigle , Mark Brenner , Aleksej Frank , Ahmad Ramadneh , Mufassar Waheed , Muhammad Umair Tahir
摘要: A three dimensional coordinate measurement device and method of measuring is provided. The device including a housing having a first axis and a second axis. A first depth camera is coupled to the housing, the first depth camera having a first optical axis aligned with the first axis. A second depth camera is coupled to the housing, the second depth camera having a second optical axis disposed on a first angle relative to the first axis. A third depth camera is coupled to the housing, the third depth camera having a third optical axis disposed on a second angle relative to the first axis, the second angle being different than the first angle. A rotational device is coupled to rotate the housing about the second axis.
-
公开(公告)号:US11335021B1
公开(公告)日:2022-05-17
申请号:US16437180
申请日:2019-06-11
申请人: Cognex Corporation
发明人: Nitin M. Vaidya , Hongwei Zhu , Daniel Moreno , Ben R. Carey , Nickolas J. Mullan , Gilbert Chiang , Yukang Liu , David J. Michael
摘要: A system and method for estimating dimensions of an approximately cuboidal object from a 3D image of the object acquired by an image sensor of the vision system processor is provided. An identification module, associated with the vision system processor, automatically identifies a 3D region in the 3D image that contains the cuboidal object. A selection module, associated with the vision system processor, automatically selects 3D image data from the 3D image that corresponds to approximate faces or boundaries of the cuboidal object. An analysis module statistically analyzes, and generates statistics for, the selected 3D image data that correspond to approximate cuboidal object faces or boundaries. A refinement module chooses statistics that correspond to improved cuboidal dimensions from among cuboidal object length, width and height. The improved cuboidal dimensions are provided as dimensions for the object. A user interface displays a plurality of interface screens for setup and runtime operation.
-
公开(公告)号:US11278256B2
公开(公告)日:2022-03-22
申请号:US16081854
申请日:2017-02-24
申请人: 4DMEDICAL LIMITED
IPC分类号: A61B6/00 , G06T7/143 , A61B5/08 , A61B5/00 , G06T7/187 , G06T7/62 , A61B5/02 , G06T7/35 , G06T7/00 , G06T7/11 , A61B6/03 , A61B5/026 , A61B5/113
摘要: The present invention relates to the field of medical imaging in the absence of contrast agents. In one form, the invention relates to the field of imaging vessels, particularly blood vessels such as the pulmonary vasculature and is suitable for use as a technique for detecting pulmonary embolism (PE), such as acute PE. Embodiments of the present invention provide improved image processing techniques having the capability to extract and use image data to overcome the need for contrast agents to distinguish between different types of tissue. Furthermore, it has also been realised that the image data accessed by the improved image processing can be used to identify irregularities in vessels.
-
公开(公告)号:US11257240B2
公开(公告)日:2022-02-22
申请号:US16666448
申请日:2019-10-29
IPC分类号: G06T7/62 , G06T7/33 , G06T7/35 , G06K9/62 , G06N3/08 , G06K9/46 , G06K9/32 , G06K9/42 , G06K9/40 , G06K9/36 , G06N3/04
摘要: In an approach for propagating labels of objects in an image, a processor receives the image. A processor performs a normalization of the image. A processor runs the image through a pre-trained object detector. A processor receives a set of detected objects from the pre-trained object detector. A processor determines a width dimension and a height dimension of a bounding box for each detected object of the set of detected objects. A processor propagates a label for each instance of each detected object in the image with the respective bounding box using prior geometric knowledge of bounding box placement. A processor inverses the normalization of the labeled image. A processor outputs the labeled image.
-
8.
公开(公告)号:US11044390B2
公开(公告)日:2021-06-22
申请号:US15040688
申请日:2016-02-10
发明人: Jonathan Bormet
摘要: An imaging system includes an imaging scope, a camera, an image processor, and a system controller. The imaging scope is configured to illuminate an object and capture light reflected from the object. The camera has a light sensor with a light-sensitive surface configured to receive the captured light from the imaging scope, and generate a digital image representative of the captured light. The image processor is configured to receive the digital image from the camera, and use at least one of a random sample consensus (RANSAC) technique and a Hough Transform technique to (i) identify a boundary between an active portion and an inactive portion of the digital image and (ii) generate boundary data indicative of a characteristic of the boundary. The system controller is configured to receive the boundary data from the image processor, and use the boundary data to select and/or adjust a setting of the imaging system.
-
公开(公告)号:US20210125364A1
公开(公告)日:2021-04-29
申请号:US16666448
申请日:2019-10-29
摘要: In an approach for propagating labels of objects in an image, a processor receives the image. A processor performs a normalization of the image. A processor runs the image through a pre-trained object detector. A processor receives a set of detected objects from the pre-trained object detector. A processor determines a width dimension and a height dimension of a bounding box for each detected object of the set of detected objects. A processor propagates a label for each instance of each detected object in the image with the respective bounding box using prior geometric knowledge of bounding box placement. A processor inverses the normalization of the labeled image. A processor outputs the labeled image.
-
公开(公告)号:US20210125359A1
公开(公告)日:2021-04-29
申请号:US16663695
申请日:2019-10-25
发明人: James Dolce , Nathaniel Curry , Ryan Moore
IPC分类号: G06T7/38 , H04N5/14 , G06T7/35 , G06T3/40 , H04N19/154 , H04N19/172
摘要: A system for producing a flipbook includes a processor that receives a video comprising a plurality of frames, selects a start frame and an end frame, and a plurality of frames therebetween. The processor can analyze the frames of the segment to determine an average rate of change of the plurality of frames and a threshold of relative image difference based on the average rate of change of the plurality of frames and a baseline frame rate. The processor can select, based on the results of its analysis, a plurality of selected frames, each of the selected frames being separated from two other selected frames by a sub-segment of the video, wherein each pair of adjacent frames comprises a relative image difference above the threshold and wherein each selected frame meets quality criteria not met by one or more local frames. The processor arranges the selected frames in temporal order, adds a protruding edge to each of the selected frames, and transmits data representing each of the selected frames to a printer for printing and binding a flipbook.
-
-
-
-
-
-
-
-
-