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. 发明申请

US20220101639A1 DENSE 6-DOF POSE OBJECT DETECTOR 有权
公开(公告)号：US20220101639A1
公开(公告)日：2022-03-31
申请号：US17427231
申请日：2020-01-17
申请人： SIEMENS AKTIENGESELLSCHAFT
发明人： Ivan Shugurov , Andreas Hutter , Sergey Zakharov , Slobodan Ilic
IPC分类号： G06V20/64 , G06T17/10 , G06T7/90 , G06N3/08
摘要： A method and a system for object detection and pose estimation within an input image. A 6-degree-of-freedom object detection and pose estimation is performed using a trained encoder-decoder convolutional artificial neural network including an encoder head, an ID mask decoder head, a first correspondence color channel decoder head and a second correspondence color channel decoder head. The ID mask decoder head creates an ID mask for identifying objects, and the color channel decoder heads are used to create a 2D-to-3D-correspondence map. For at least one object identified by the ID mask, a pose estimation based on the generated 2D-to-3D-correspondence map and on a pre-generated bijective association of points of the object with unique value combinations in the first and the second correspondence color channels is generated.

2. 发明授权

US10997450B2 Method and apparatus for detecting objects of interest in images 有权
公开(公告)号：US10997450B2
公开(公告)日：2021-05-04
申请号：US16482180
申请日：2017-11-07
申请人： SIEMENS AKTIENGESELLSCHAFT
发明人： Peter Amon , Sanjukta Ghosh , Andreas Hutter
IPC分类号： G06K9/32 , G06K9/62 , G06N3/08
摘要： A method and apparatus for detecting objects of interest in images, the method comprising the steps of supplying (S1) at least one input image to a trained deep neural network, DNN, which comprises a stack of layers; and using at least one deconvolved output of at least one learned filter or combining (S2) deconvolved outputs of learned filters of at least one layer of the trained deep neural network, DNN, to detect the objects of interest in the supplied images.

3. 发明申请

US20200090005A1 Method and Apparatus for Analysing an Image 审中-公开
公开(公告)号：US20200090005A1
公开(公告)日：2020-03-19
申请号：US16618550
申请日：2018-06-04
申请人： SIEMENS AKTIENGESELLSCHAFT
发明人： Sanjukta Ghosh , Peter Amon , Andreas Hutter
IPC分类号： G06K9/62 , G06K9/00 , G06N3/04 , G06N3/08
摘要： The present embodiments relate to analysing an image. An artificial deep neural net is pre-trained to classify images into a hierarchical system of multiple hierarchical classes. The pre-trained neural net is then adapted for one specific class, wherein the specific class is lower in the hierarchical system than an actual class of the image. The image is then processed by a forward pass through the adapted neural net to generate a processing result. An image processing algorithm is then used to analyse the processing result focused on features corresponding to the specific class.

4. 发明申请

US20130091432A1 METHOD AND USER INTERFACE FOR FORENSIC VIDEO SEARCH 有权
标题翻译：威廉视频搜索的方法和用户界面
公开(公告)号：US20130091432A1
公开(公告)日：2013-04-11
申请号：US13646867
申请日：2012-10-08
申请人： Siemens Corporation , Siemens Aktiengesellschaft
发明人： Vinay Damodar Shet , Xianjun Sam Zheng , Andreas Hutter , Xiang Gao , Cheng-Hao Kuo
IPC分类号： G06F3/0481
CPC分类号： G08B13/19645 , G06F3/04817 , G06F17/30112 , G06F17/30277 , G06F17/30781 , G06F17/30784 , G06F17/3079 , G06F17/30793 , G06F17/30823 , G06F17/30825 , G06F17/30846 , G06K9/00369 , G06K9/00771 , G06K9/3241
摘要： A forensic video search user interface is disclosed that accesses databases of stored video event metadata from multiple camera streams and facilitates the workflow of search of complex global events that are composed of a number of simpler, low complexity events.
摘要翻译：公开了一种取证视频搜索用户界面，其从多个摄像机流访问存储的视频事件元数据的数据库，并且促进由多个较简单，低复杂性事件组成的复杂全局事件的搜索工作流程。

5. 发明授权

US11126894B2 Method and apparatus for analysing an image 有权
公开(公告)号：US11126894B2
公开(公告)日：2021-09-21
申请号：US16618550
申请日：2018-06-04
申请人： SIEMENS AKTIENGESELLSCHAFT
发明人： Sanjukta Ghosh , Peter Amon , Andreas Hutter
IPC分类号： G06K9/62 , G06K9/00 , G06N3/04 , G06N3/08
摘要： The present embodiments relate to analysing an image. An artificial deep neural net is pre-trained to classify images into a hierarchical system of multiple hierarchical classes. The pre-trained neural net is then adapted for one specific class, wherein the specific class is lower in the hierarchical system than an actual class of the image. The image is then processed by a forward pass through the adapted neural net to generate a processing result. An image processing algorithm is then used to analyse the processing result focused on features corresponding to the specific class.

6. 发明授权

US09872032B2 Autogressive pixel prediction in the neighborhood of image borders 有权
公开(公告)号：US09872032B2
公开(公告)日：2018-01-16
申请号：US14763082
申请日：2013-12-19
申请人： SIEMENS AKTIENGESELLSCHAFT
发明人： Peter Amon , Andreas Hutter , André Kaup , Johannes Rehm , Andreas Weinlich
IPC分类号： H04N7/12 , H04N19/182 , H04N19/593 , H04N19/11 , H04N19/90 , H04N19/136 , H04N19/169 , H04N19/44 , H04N19/70 , H04N19/91
CPC分类号： H04N19/182 , H04N19/11 , H04N19/136 , H04N19/169 , H04N19/44 , H04N19/593 , H04N19/70 , H04N19/90 , H04N19/91
摘要： For each array of pixels, an autoregressive pixel-prediction method is performed based on a weighted sum of reconstructed pixel values of reconstructed pixels in a specific neighborhood region adjacent to the current pixel to be coded. For determining the weights, the pixel values in a specific training region adjacent to the current pixel are taken into account. The coding method is characterized by an appropriate determination of the specific neighborhood region and the specific training region in case that reconstructed pixel values do not exist for all pixels in the neighborhood region and the training region. In such a case, the number of pixels in the neighborhood region is reduced to a number of reconstructed pixels until the ratio between the number of pixels in the training region and the number of pixels in the neighborhood region exceeds a predetermined threshold.

7. 发明申请

US20200012923A1 COMPUTER DEVICE FOR TRAINING A DEEP NEURAL NETWORK 审中-公开
公开(公告)号：US20200012923A1
公开(公告)日：2020-01-09
申请号：US16340114
申请日：2017-09-05
申请人： SIEMENS AKTIENGESELLSCHAFT
发明人： Sanjukta Ghosh , Peter Amon , Andreas Hutter
IPC分类号： G06N3/04 , G06N3/08 , G06K9/00 , G06K9/62
摘要： A computer device for training a deep neural network is provided. The computer device includes a receiving unit for receiving a two-dimensional input image frame, and a deep neural network for examining the two-dimensional input image frame in view of objects being included in the two-dimensional input image frame. The deep neural network includes a plurality of hidden layers and an output layer representing a decision layer. The computer device includes a training unit for training the deep neural network using transfer learning based on synthetic images for generating a model comprising trained parameters, and an output unit for outputting a result of the deep neural network based on the model.

8. 发明授权

US10250874B2 Method for coding sequence of digital images 有权
公开(公告)号：US10250874B2
公开(公告)日：2019-04-02
申请号：US14783731
申请日：2013-07-26
申请人： SIEMENS AKTIENGESELLSCHAFT
发明人： Peter Amon , Andreas Hutter , André Kaup , Eugen Wige
IPC分类号： H04N19/103 , H04N19/105 , H04N19/176 , H04N19/593 , H04N19/14 , H04N19/124 , H04N19/167 , H04N19/44 , H04N19/61 , H04N19/65 , H04N19/70 , G06K9/62 , H04N19/46 , H04N19/11
摘要： In a method for coding a sequence of digital images, a prediction error between predicted values and the original values of pixels is processed for generating the coded sequence of digital images. A preset prediction mode is an intra-prediction mode based on pixels of a single image and includes, for a region of pixels with reconstructed values in the single image and for a template of an image area, comparing a first patch of pixels in the region that surround a first pixel to be predicted based on the template with several second patches. A predicted value of the first pixel is determined based on the values of one or more second pixels that have the highest similarity described by the similarity measure among all second pixels of the plurality of second pixels in the region.

9. 发明授权

US09269243B2 Method and user interface for forensic video search 有权
标题翻译：法医视频搜索的方法和用户界面
公开(公告)号：US09269243B2
公开(公告)日：2016-02-23
申请号：US13646867
申请日：2012-10-08
申请人： Siemens Corporation , Siemens Aktiengesellschaft
发明人： Vinay Damodar Shet , Xianjun Sam Zheng , Andreas Hutter , Xiang Gao , Cheng-Hao Kuo
IPC分类号： G06F3/00 , G08B13/196 , G06K9/32 , G06F3/0481 , G06F17/30 , G06K9/00
CPC分类号： G08B13/19645 , G06F3/04817 , G06F17/30112 , G06F17/30277 , G06F17/30781 , G06F17/30784 , G06F17/3079 , G06F17/30793 , G06F17/30823 , G06F17/30825 , G06F17/30846 , G06K9/00369 , G06K9/00771 , G06K9/3241
摘要： A forensic video search user interface is disclosed that accesses databases of stored video event metadata from multiple camera streams and facilitates the workflow of search of complex global events that are composed of a number of simpler, low complexity events.
摘要翻译：公开了一种取证视频搜索用户界面，其从多个摄像机流访问存储的视频事件元数据的数据库，并且促进由多个较简单，低复杂性事件组成的复杂全局事件的搜索工作流程。

10. 发明申请

US20150365682A1 AUTOGRESSIVE PIXEL PREDICTION IN THE NEIGHBORHOOD OF IMAGE BORDERS 有权
标题翻译：图像边界自动像素预测
公开(公告)号：US20150365682A1
公开(公告)日：2015-12-17
申请号：US14763082
申请日：2013-12-19
申请人： SIEMENS AKTIENGESELLSCHAFT
发明人： Peter Amon , Andreas Hutter , André Kaup , Johannes Rehm , Andreas Weinlich
IPC分类号： H04N19/182 , H04N19/169 , H04N19/70 , H04N19/91 , H04N19/44 , H04N19/593 , H04N19/136
CPC分类号： H04N19/182 , H04N19/11 , H04N19/136 , H04N19/169 , H04N19/44 , H04N19/593 , H04N19/70 , H04N19/90 , H04N19/91
摘要： The invention refers to a method for coding digital image data (I), the data comprising one or more arrays of pixels (p0, p112) with corresponding pixel values (i0, . . . , i112). For each array of pixels, an autoregressive pixel-prediction method is performed based on a weighted sum of reconstructed pixel values (i1, . . . , i12) of reconstructed pixels (p1, . . . , p12) in a specific neighborhood region (SN) adjacent to the current pixel (p0) to be coded. For determining the weights, the pixel values (p1, . . . , p12) in a specific training region (ST) adjacent to the current pixel (p0) are taken into account. The coding method is characterized by an appropriate determination of the specific neighborhood region (SN) and the specific training region (ST) in case that reconstructed pixel values do not exist for all pixels in the neighborhood region and the training region, e.g. at borders of the array of pixels. In such a case, the number of pixels in the neighborhood region is reduced to a number of reconstructed pixels until the ratio between the number of pixels in the training region and the number of pixels in the neighborhood region exceeds a predetermined threshold. The coding method of the invention provides a prediction with high accuracy and, thus, leads to an efficient coding of the image data.
摘要翻译：本发明涉及用于对数字图像数据（I）进行编码的方法，该数据包括具有对应像素值（i0，...，i112）的一个或多个像素阵列（p0，p112）。对于每个像素阵列，基于特定邻域中的重构像素（p1，...，p12）的重构像素值（i1，...，i12）的加权和来执行自回归像素预测方法 SN）与要编码的当前像素（p0）相邻。为了确定权重，考虑与当前像素（p0）相邻的特定训练区域（ST）中的像素值（p1，...，p12）。编码方法的特征在于，对于邻近区域和训练区域中的所有像素，不存在重构像素值的情况，适当确定特定邻域（SN）和特定训练区域（ST）。在像素数组的边界。在这种情况下，邻域中的像素数目减少到重建像素数，直到训练区域中的像素数与邻域中的像素数之间的比率超过预定阈值。本发明的编码方法提供高精度的预测，从而导致图像数据的有效编码。

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