专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明专利

DE112021000477T5 OBJEKTERKENNUNGSVORRICHTUNG UND MODELLMUSTERBEWERTUNGSVORRICHTUNG 未知
公开(公告)号：DE112021000477T5
公开(公告)日：2022-12-01
申请号：DE112021000477
申请日：2021-01-05
申请人： FANUC CORP
发明人： OGURA SHOUTAROU , WARASHINA FUMIKAZU
IPC分类号： G01B11/00 , G01B11/26 , G06T7/00 , G06V10/46
摘要： Bereitgestellt wird eine Objekterkennungsvorrichtung, die mit hoher Genauigkeit ein symmetrisches Zielobjekt erkennen kann, das in einem Bild dargestellt ist. Die Objekterkennungsvorrichtung umfasst einen Speicher 33, der ein Modellmuster 300, das eine Mehrzahl von vorbestimmten Merkmalen an unterschiedlichen Positionen zueinander auf einem Zielobjekt, wenn das Zielobjekt aus einer vorbestimmten Richtung betrachtet wird, darstellt, speichert, eine Merkmalsextraktionseinheit 41, die eine Mehrzahl der vorbestimmten Merkmale aus einem Bild, in dem das Zielobjekt dargestellt ist, extrahiert, und eine Abgleicheinheit 42, die einen Übereinstimmungsgrad berechnet, der einen Übereinstimmungsgrad zwischen der Mehrzahl der vorbestimmten Merkmale des Modellmusters 300 und einer Mehrzahl der vorbestimmten Merkmale darstellt, die aus einem Bereich extrahiert sind, der dem Modellmuster 300 in dem Bild entspricht, während eine relative Position und/oder ein relativer Winkel und/oder eine relative Richtung und/oder eine relative Größe des Modellmusters 300 in Bezug auf das Bild geändert wird, und die beurteilt, dass das Zielobjekt in dem Bereich des Bilds dargestellt ist, der dem Modellmuster 300 entspricht, wenn der Übereinstimmungsgrad gleich oder größer als ein vorbestimmter Schwellenwert ist, wobei die vorbestimmten Merkmale, die in dem Speicher 33 gespeichert sind, ein Merkmal von Interesse umfassen, das zum Detektieren einer Position in einer spezifischen Richtung des Zielobjekts in dem Bild verwendet werden kann oder das zum Detektieren eines Winkels in einer Drehrichtung verwendet werden kann, die um einen vorbestimmten Punkt des Zielobjekts in dem Bild zentriert ist, und die Abgleicheinheit 42 den Beitrag bei der Berechnung des Übereinstimmungsgrads erhöht, wenn das Merkmal von Interesse des Modellmusters 300 und ein vorbestimmtes Merkmal in dem Bild übereinstimmen, in dem Vergleich zu dem Fall, in dem ein vorbestimmtes Merkmal des Modellmusters 300, das nicht das Merkmal von Interesse ist, und das vorbestimmte Merkmal in dem Bild übereinstimmen, um den Übereinstimmungsgrad zu berechnen.

2. 发明专利

IL295193A System for accurate 3d modeling of gemstones 未知
公开(公告)号：IL295193A
公开(公告)日：2022-09-01
申请号：IL29519322
申请日：2022-07-28
申请人： SARINE TECH LTD
IPC分类号： G01B11/24 , G01N21/87 , G06T15/00 , G06V10/141 , G06V10/147 , G06V10/40 , G06V10/42 , G06V10/44 , G06V10/46 , G06V10/60 , G06V10/764 , G06V20/64 , H04N13/204
摘要： A computerized system, kit and method for producing an accurate 3D-Model of a gemstone by obtaining an original 3D-model of an external surface of the gemstone; imaging at least one selected junction with only portions of its associated facets and edges disposed adjacent the junction, the location of the junction being determined based on information obtained at least partially by using the original 3D model; analyzing results of the imaging to obtain information regarding details of the gemstone at the junction; and using the information for producing an accurate 3D-model of said external surface of the gemstone, which is more accurate than the original 3-D model.

3. 发明专利

DE102017203276B4 Verfahren und Vorrichtung zur Ermittlung einer Trajektorie in Off-road-Szenarien 未知
公开(公告)号：DE102017203276B4
公开(公告)日：2022-10-06
申请号：DE102017203276
申请日：2017-03-01
申请人： VOLKSWAGEN AG
发明人： JOHANSSON MIKAEL , SCHOMERUS VOLKER PATRICIO
IPC分类号： B60W40/02 , G01C7/04 , G01C21/34 , G01S17/86 , G01S17/89 , G06N3/02 , G06T7/00 , G06V10/46 , G06V10/82 , G06V20/56 , G06V20/64
摘要： Verfahren zur Ermittlung einer Trajektorie (T) in Off-road-Szenarien, umfassend die folgenden Verfahrensschritte:a) Aufnehmen eines 2D-Bildes der Umgebung mittels einer ersten Sensorik (2),b) Klassifizieren von Bildpunkten des 2D-Bildes in mindestens drei Klassen, wobei eine erste Klasse „Vorgesehen zum Befahren“, eine weitere Klasse „befahrbar wenn notwendig“ und noch eine weitere Klasse „unbefahrbar“ ist,c) Ermitteln eines Höhenprofils (H) mittels einer zweiten Sensorik (3),d) Projizieren der klassifizierten Bildpunkte in das Höhenprofil (H) unde) Ermitteln einer Trajektorie (T) mittels eines Trajektorie-Planungs-Algorithmus unter Verwendung der Bildpunkte der ersten Klasse, wobei im Falle einer unvollständigen Trajektorie (T) die Bildpunkte der weiteren Klasse zusätzlich berücksichtigt werden.

4. 发明专利

IL295059A Periocular test for mixed reality calibration 未知
公开(公告)号：IL295059A
公开(公告)日：2022-09-01
申请号：IL29505922
申请日：2022-07-25
申请人： MAGIC LEAP INC
IPC分类号： G02B27/01 , G06T11/60 , G06V10/46 , G06V20/20 , G06V40/16 , G06V40/18 , G06V40/19
摘要： A wearable device can include an inward-facing imaging system configured to acquire images of a user's periocular region. The wearable device can determine a relative position between the wearable device and the user's face based on the images acquired by the inward-facing imaging system. The relative position may be used to determine whether the user is wearing the wearable device, whether the wearable device fits the user, or whether an adjustment to a rendering location of virtual object should be made to compensate for a deviation of the wearable device from its normal resting position.

5. 发明专利

CA2918947C KEYPOINT IDENTIFICATION 未知
公开(公告)号：CA2918947C
公开(公告)日：2022-07-12
申请号：CA2918947
申请日：2014-07-23
申请人： TELECOM ITALIA SPA
发明人： BALESTRI MASSIMO , FRANCINI GIANLUCA , LEPSOY SKJALG
IPC分类号： G06T7/73 , G06T5/10 , G06V10/44 , G06V10/46
摘要： A method for identifying keypoints in a digital image comprising a set of pixels is proposed. Each pixel has associated thereto a respective value of an image representative parameter. Said method comprises approximating a filtered image. Said filtered image depends on a filtering parameter and comprises for each pixel of the image a filtering function that depends on the filtering parameter to calculate a filtered value of the value of the representative parameter of the pixel. Said approximating comprises: a) generating a set of base filtered images; each base filtered image is the image filtered with a respective value of the filtering parameter; b) for each pixel of at least a subset of said set of pixels, approximating the filtering function by means of a respective approximation function based on the base filtered images; said approximation function is a function of the filtering parameter within a predefined range of the filtering parameter; the method further comprises, for each pixel of said subset, identifying such pixel as a candidate keypoint if the approximation function has a local extreme which is also a global extreme with respect to the filtering parameter in a respective sub-range internal to said predefined range. For each pixel identified as a candidate keypoint, the method further comprises: c) comparing the value assumed by the approximation function at the value of the filtering parameter corresponding to the global extreme of the pixel with the values assumed by the approximation functions of the adjacent pixels in the image at the values of the filtering parameters of the respective global extremes of such adjacent pixels, and d) selecting such pixel based on this comparison.

6. 发明专利

IL298488A Mapping of breast arterial calcifications and prediction of heart disease 未知
公开(公告)号：IL298488A
公开(公告)日：2023-01-01
申请号：IL29848822
申请日：2022-11-22
申请人： CUREMETRIX INC
IPC分类号： G06V10/20 , G06V10/25 , G06V10/26 , G06V10/30 , G06V10/42 , G06V10/46 , G06V10/75 , G06V10/764 , G06V20/69 , G16H30/40
摘要： A method includes receiving an image from a mammogram, removing noise from the image thereby creating a de-noised image, computing a point of interest on the de-noised image, creating a mesoscale region of interest on the de-noised image, computing a connectivity for the mesoscale region of interest, identifying a connected component using the computed connectivity, where the connected component represents a branch of a global curvilinear structure, selecting a set of branches based on a physical property for each branch of the global curvilinear structure, pruning each branch based on an error-tolerant, adaptive polynomial fit, identifying remaining regions of interest in each pruned branch, and growing a chain formed by remaining points of interest included in the remaining regions of interest, where the chain represents a macroscopic, global curvilinear calcified arterial structure. In an aspect of the invention, the quantitation of the calcified arterial structures may be used as a biomarker for risk stratification of heart disease.

7. 发明专利

AU2021103359A4 REAL TIME FARMER ASSISTIVE FLOWER HARVESTING AGRICULTURAL ROBOT 未知
公开(公告)号：AU2021103359A4
公开(公告)日：2022-06-30
申请号：AU2021103359
申请日：2021-06-15
申请人： M N AVINASH , M PRADEEP , RAJA D BINO PRINCE DR , S B HARSHINI MS , S BHASKAR DR
发明人： S BHASKAR , M PRADEEP , M N AVINASH , S B HARSHINI , RAJA D BINO PRINCE
IPC分类号： A01D46/30 , A01G25/16 , A01M7/00 , B25J5/00 , B25J9/16 , B25J11/00 , B25J15/00 , G05B19/18 , G06N3/02 , G06N20/00 , G06T1/00 , G06V10/46 , G06V20/10 , H04W4/38
摘要： REAL TIME FARMER ASSISTIVE FLOWER HARVESTING AGRICULTURAL ROBOT The Flower Harvesting AGROBOT is an innovative concept which is developed primarily to address the issue of Farm Labours, in order to reduce the both time and work of farmers. As a result, we have developed a new, innovative model that helps the farmers. We affirm the statement that "Farmers are the backbone of our country" hence we come up with new innovative model which helps the farmers. Flower plants generally have thorns, which can harm the flower plucking labours as they pluck the flowers. Using the AGROBOT we can reduce the risk and harms. AGROBOT has been trained with more than 400 flower images, so it can detect flowers in plants and recognize healthy flowers using high resolution camera. Sampled flower images from Raspberry Pi memory will be compared with this identified flower. In this process if there are any damaged or dry flowers occurs then it will avoids the plucking of such flowers and hence reduces the time. By matching the detected flower with the sampled flower, the AGROBOT will become static and operates its arm to pluck and store the flowers in the basket using LBP, machine learning and neural network algorithms. By interfacing Raspberry Pi and a camera, the AGROBOT can detect harmful pests and insects in the plants. As soon as the harmful pests and insects are identified, the AGROBOT sprays the pesticides and insecticides to the ROI in real time. AGROBOT is also capable of doing multiple operations such as measuring water content in soil with a soil moisture detector and measuring acidity or alkalinity of a moisture sample with a pH sensor. The system also alerts the owners via their smart phones when crops are damaged due to trespassing by intruders or animals. Using electrochemical sensors, it can also measure soil fertility. Keywords AGROBOT, ROI, LBI, Raspberry pi 3 b+, NodeMCU - ESP8266, Arduino Uno - ATmega320p, pH sensor, Raspberry pi display, Moisture hygrometer, PIR sensors, IR sensor, Electro chemical sensor, Image processing, RTS, LBP, Artificial Intelligence, Machine Learning, Tensor Flow and loT. Figures 700mmA /DISTANCE BETWEEN ROBOT C AND FLOWERS SENSOR AN PH Fig 1: 2D) model of AGROBOT

8. 发明专利

AU2021103274A4 Design and Analysis of Image Forgery Detection Techniques for Innovative methodologies. 未知
公开(公告)号：AU2021103274A4
公开(公告)日：2022-03-24
申请号：AU2021103274
申请日：2021-06-10
申请人： CHIKTE SHUBHANGI DIGAMBER DR , PRATAPUR SATISH
发明人： CHIKTE SHUBHANGI DIGAMBER , PRATAPUR SATISH
IPC分类号： G06F21/10 , G06K9/00 , G06T1/00 , G06V10/46
摘要： [754] Our invention is a digital image forgery has turned out to be unsophisticated because of capable mobile, PCs, propelled image editing advanced defined software's and high resolution 128-bit, 255- bit or more capturing gadgets. Our Checking the quality of a respectability of color, non-color pictures and identifying hints of altering without requiring additional pre embedded data / information of the picture or installed unique watermarks are essential examine defined domain. [756] The Passive techniques do-not require pre-embedded data/ information in the image. The Several image forgery detection techniques are arranged first and after that their summed up local and global organization is produced. Our Invention increasingly dependent on the internet and so does it become more and more vulnerable to very harmful threats and also the threats are becoming vigorous. [758] These threats distort the valid authenticity of data transmitted through the internet and the as we all completely or partially rely upon this transmitted information data hence its authenticity needs to be develop. Our Images have the potential of conveying much more information as compared to the textual defined content and the I user ratty much believe everything that we see. The order to preserve/check the authenticity of images, image forgery detection techniques are expanding its domain. [760] The Detection of forgeries in digital images is in great need in order to recover the peoples trust in visual media and also our research is going to discuss all image forgery and defined blind methods for image forgery unique detection. TOTAL NO OF SHEET: 03 NO OF FIG: 03 blok-bFidmetod:oreyetoint-oresicmaeosflw Overlapping blocks Keyo4 t anftm Efficent Methodo agie [etr xr \110 11. r atcing114 1i8 Fig.1: Forgery Detection in Forensic Images flow.

9. 实用新型

CN218069047U 一种货车司机危险驾驶行为检测报警设备有权
公开(公告)号：CN218069047U
公开(公告)日：2022-12-16
申请号：CN202221394922.1
申请日：2022-06-07
申请人：郑州轻工业大学
发明人：陈志武 , 周何彬 , 吉康宁 , 赵耀祖 , 吴国伟
IPC分类号： G08B21/06 , G06V20/52 , G06V20/59 , G06V40/16 , G06V10/46 , A61H7/00 , B60Q9/00
摘要：本实用新型提出了一种货车司机危险驾驶行为检测报警设备，包括箱体、视觉识别系统、按摩机构、警示系统、人机交互机与中心控制系统，视觉识别系统、按摩机构、警示系统、人机交互机均与中心控制系统相连接；按摩机构设置在箱体底部，警示系统设置在箱体外部，中心控制系统设置在箱体内部，人机交互机与视觉识别系统均设置独立设置。本实用新型实现了在对疲劳驾驶行为进行监测的同时对其它不安全驾驶行为进行监测与警告，辅助司机在驾驶途中集中注意力，提高驾驶安全程度，通过利用按摩机构，可以为司机在休息时提供按摩服务，提高了监测报警设备的智能化程度并拓宽了监测报警设备的应用场景。

10. 实用新型

CN218995188U 用于圆柱类药瓶标签的视觉检测装置有权
公开(公告)号：CN218995188U
公开(公告)日：2023-05-09
申请号：CN202223541856.9
申请日：2022-12-30
申请人：河北吉星医药包装有限公司
发明人：王满
IPC分类号： G01N21/892 , G01N21/13 , G01N21/01 , G01V8/10 , G06T7/00 , G06T3/40 , G06V10/46
摘要：本实用新型公开了一种用于圆柱类药瓶标签的视觉检测装置，由安装在基板上的负压输送带、以负压输送带上预设点为中心均匀布置的四个视觉检测单元以及与负压输送带及四个上视觉检测单元相连的控制单元，负压输送带用于输送带标签的圆柱类药瓶，控制单元通过光电感应器以及负压输送带的行走速度计算得到控制信号，使药瓶在行经预设点时停顿，四个视觉检测单元在药瓶到达预设点并停顿时进行拍摄。本实用新型利用四个摄像头对药瓶同时拍摄，形成360度无死角的全景影像，并利用激光水平射线配合可以实现在图像拼接前预先以水平射为基准对标签是否贴正进行快速预检，只需要少量的计算就可以判断。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式