-
公开(公告)号:US20190244011A1
公开(公告)日:2019-08-08
申请号:US15889229
申请日:2018-02-06
申请人: Kneron Inc.
发明人: Chun-Chen Liu
CPC分类号: G06K9/00255 , G06K9/00201 , G06K9/6256
摘要: A low-power face identification method includes emitting at least one first light signal to an object, receiving at least one second light signal reflected by the object, decoding the at least one second light signal to generate a decoded light signal, extracting two-dimensional image information from the decoded light signal, performing a two-dimensional face detection function by an artificial intelligence chip according to the two-dimensional image information and two-dimensional face training data, inhibiting a two-dimensional face recognition function when a two-dimensional face is undetected, and disabling an image converter by the artificial intelligence chip in order to inhibit a three-dimensional face recognition function when the two-dimensional face recognition function is inhibited.
-
">2.
公开(公告)号:US20190236373A1
公开(公告)日:2019-08-01
申请号:US16245756
申请日:2019-01-11
发明人: Hesong HU , Jian SU , Zhongtian LU , Junyi WEN , Zhuo YANG , Lingsheng TAN , Chaowen WANG , Jieming LI
CPC分类号: G06K9/00718 , G06K9/00201 , G08B7/066
摘要: The present disclosure discloses a data transmission system of safety patrol on construction project site based on “internet plus” according to the present disclosure comprises a patrol apparatus for collecting and transmitting an on-site panorama image, 3D point cloud data of the scene, location information and construction on-site data; a cloud computing platform for receiving the on-site panorama image, the 3D point cloud data of the scene, the location information and the construction on-site data, and reconstructing a 3D model of a patrol scene based on the panorama images, the 3D point cloud data of the scene, the location information and the construction on-site data; a safety patrol data terminal providing inspection/browse to construction site; the present disclosure enable users to patrol in construction project remotely, reducing workload of the safety production management personnel, improving patrol efficiency, enhancing the intuitive reality of the patrol and the safety patrol level of the construction project; the inspection result is transferred electronically, ensuring the time efficiency of project patrol inspection.
-
公开(公告)号:US20190236360A1
公开(公告)日:2019-08-01
申请号:US15883355
申请日:2018-01-30
申请人: Mashgin Inc.
CPC分类号: G06K9/00671 , G06K9/00201 , G06K9/6272 , G06K9/6289 , G06K9/78 , G06K2209/17 , G06N20/00 , G06Q20/201 , G06Q20/208
摘要: Methods, systems, and computer programs are presented for providing a feedback loop to improve object image-based recognition based on transaction data. In one method, instructions are received defining items to be visually recognized by a terminal. For each item, a check is made to determine if item image information is in a global database or if it is a new item. The global database includes item images captured during transactions performed at several terminals. For each item in the global database, item image information is downloaded from the global database. For new items, terminal cameras capture pose images for several poses of the new items, each camera taking an image for each pose. A machine-learning program is trained with the downloaded image information and the pose images, where the machine-learning program performs image-based recognition of the items that are presented at the terminal, based on images captured by the cameras.
-
公开(公告)号:US20190235830A1
公开(公告)日:2019-08-01
申请号:US15884706
申请日:2018-01-31
申请人: Vocollect, Inc.
发明人: Curtis Earhart
CPC分类号: G06F3/167 , G06F16/5838 , G06F16/5854 , G06F16/5866 , G06K9/00201 , G06Q10/0633 , G06Q10/087 , G06T7/62 , G06T7/90 , G06T2207/10024 , G06T2207/30204
摘要: A method for visual inspection includes scanning an object with an imaging device, capturing triggering metrics of the scanned object, and searching for a workflow associated with the metrics. If the workflow is located, the located workflow is initiated; otherwise, a user is prompted for vocal input. In an embodiment, scanning can be performed with a wearable imaging device, such as Google glasses, and vocal input can be provided via a voice-controllable device (for example, a Voice device), configured to communicate with the imaging device.
-
公开(公告)号:US20190221043A1
公开(公告)日:2019-07-18
申请号:US16335079
申请日:2017-09-27
申请人: Duke University
发明人: Regis Kopper , Derek Nankivil , David Zielinski
CPC分类号: G06T19/006 , A61B6/03 , A61B6/12 , G06F3/011 , G06F3/013 , G06F3/014 , G06F17/5009 , G06K9/00201 , G06T7/70 , G06T15/005 , G06T15/20
摘要: Systems and methods for using positions of detected, real object boundaries to enable user interaction with a virtual object are disclosed. A system can include one or more sensors or trackers configured to detect boundaries of a transparent, real object within a three-dimensional coordinate system. A computing device configured to track positions of the detected boundaries of the real object within the three-dimensional coordinate system. The computing device may also track a position of a virtual object within the three-dimensional coordinate system. The computing device may determine whether the position of the virtual object is within the positions of the detected boundaries of the real object. The computing device may also enable user interaction with the virtual object via user interface and receive input for interacting with the virtual object in response to determining that the position of the virtual object is within the positions of the detected boundaries.
-
公开(公告)号:US20190221042A1
公开(公告)日:2019-07-18
申请号:US16231035
申请日:2018-12-21
申请人: Outward, Inc.
发明人: Clarence Chui , Marc Mignard
IPC分类号: G06T19/00 , H04N5/232 , G06K9/00 , H04N21/81 , G06T11/00 , H04N21/2343 , H04N7/01 , H04N21/4223
CPC分类号: G06T19/006 , G06K9/00201 , G06T11/00 , H04N5/23229 , H04N7/0125 , H04N21/234318 , H04N21/4223 , H04N21/8126
摘要: Techniques for virtualizing content are disclosed. One or more objects comprising source video content are determined. The one or more objects comprising the source video content are virtualized by mapping each to and representing each with a corresponding database object. Data comprising the corresponding database objects is provided for rendering the source video content instead of any original pixel information of the source video content so that a virtualized version of the source video content is rendered.
-
公开(公告)号:US20190221041A1
公开(公告)日:2019-07-18
申请号:US16222546
申请日:2018-12-17
发明人: Xingsheng LIN
CPC分类号: G06T19/006 , G06K9/00201 , G06K9/00671 , G06T7/55 , G06T7/70 , G06T11/00 , G06T2207/10028 , G06T2207/30244 , H04N21/4728
摘要: A method for synthesizing virtual and real objects, includes: acquiring a target object in an image captured by a terminal device; in a depth information fusion mode, acquiring the depth information of the target object by a camera apparatus of the terminal device, wherein the depth information fusion mode is configured to superimpose a virtual object generated by computer modeling on the image, and the depth information of the target object is configured to indicate a distance between the target object and the terminal device; acquiring the depth information of the virtual object; and superimposing the virtual object on the image based on the depth information of the target object and the depth information of the virtual object.
-
公开(公告)号:US20190219806A1
公开(公告)日:2019-07-18
申请号:US16246333
申请日:2019-01-11
申请人: IBALLISTIX, LLC
发明人: Robert H. Poole
CPC分类号: G02B21/0008 , F42B35/00 , G02B21/32 , G02B21/362 , G06K9/00201 , H04W4/025
摘要: A computing system for dynamic forensic data capture and analysis is provided. The computing system may include a processor coupled to a memory to execute forensic analysis detection scheme using a forensic analysis agent of a client node and a forensic analysis module at a networked server node. The processor may be operable to receive a user request for a computer activity and sensed image data associated with the forensic evidence while the client node is coupled within a forensic microscope assembly that optically aligns an image sensor of the client node with the forensic evidence. The processor may also be operable to generate and send ballistic specimen data including images, video, GPS data and the like to the networked server, wherein the processor is operable to generate ballistic imaging metadata. Further, the processor may be operable to detect matching records of spent ballistics and generate a hit report thereby.
-
公开(公告)号:US20190213545A1
公开(公告)日:2019-07-11
申请号:US16354178
申请日:2019-03-15
发明人: Yair Adato , Nir Hemed , Yotam Michael , Alon Grubshtein , David M. Gottlieb
CPC分类号: H04N5/2253 , G06K9/00201 , G06K9/00362 , G06K9/00624 , G06K9/00671 , G06K9/00771 , G06K9/325 , G06K2209/17 , G06Q10/06311 , G06Q10/06316 , G06Q10/087 , G06Q10/0875 , G06Q20/203 , G06Q30/0629 , G06Q50/28 , G06T7/0002 , G06T7/20 , G06T7/521 , G06T7/55 , G06T7/70 , G06T2207/30196 , G06T2207/30232 , G08B21/18 , G08B21/182 , H04N5/2252 , H04N5/23203 , H04N5/23219 , H04N5/23229 , H04N5/247
摘要: The present disclosure relates to systems and for identifying products and tracking inventory in a retail store based on analysis of image data. In one implementation, the system may include processor configured to receive image data from a plurality of image sensors mounted in a retail store; analyze the image data to estimate a current inventory of at least one product type in the retail store; receive product supply information associated with the at least one product type in the retail store; determine that an online order from a virtual store made during a first time period will be fulfilled by an employee of the retail store during a second time period; and determine, based on the current inventory estimated by analyzing the image data and the product supply information, a predicted inventory of the at least one product type during the second time period.
-
公开(公告)号:US20190213535A1
公开(公告)日:2019-07-11
申请号:US16353621
申请日:2019-03-14
发明人: Yair Adato , Ziv Mhabary , Yotam Michael , Paul Yudkin
CPC分类号: H04N5/2253 , G06K9/00201 , G06K9/00362 , G06K9/00624 , G06K9/00671 , G06K9/00771 , G06K9/325 , G06K2209/17 , G06Q10/06311 , G06Q10/06316 , G06Q10/087 , G06Q10/0875 , G06Q20/203 , G06Q30/0629 , G06Q50/28 , G06T7/0002 , G06T7/20 , G06T7/521 , G06T7/55 , G06T7/70 , G06T2207/30196 , G06T2207/30232 , G08B21/18 , G08B21/182 , H04N5/2252 , H04N5/23203 , H04N5/23219 , H04N5/23229 , H04N5/247
摘要: A system for processing images captured in a retail store is provided. The system may comprise at least one processor configured receive at least one image depicting part of at least one store shelf having a plurality of products displayed thereon, the plurality of products including a group of first products associated with a first product size and a group of second products associated with a second product size, analyze the at least one image to detect the plurality of products, identify one or more vacant spaces associated with the plurality of products, determine that by rearranging the group of second products to partially eliminate the one or more identified vacant spaces, at least one additional first product may be displayed on the at least one store shelf next to the group of first products, and provide information to a user indicative of the identified vacant spaces.
-
-
-
-
-
-
-
-
-