-
-
公开(公告)号：EP3147863B1
公开(公告)日：2020-09-23
申请号：EP16182510.4
申请日：2016-08-03
发明人： DING, Haoda , GUO, Hongyu , HU, Hongbing
-
公开(公告)号：EP3143768B1
公开(公告)日：2020-09-23
申请号：EP15792459.8
申请日：2015-04-28
申请人： Intel Corporation
发明人： SOCEK, Daniel , PURI, Atul
-
公开(公告)号：EP2761590B1
公开(公告)日：2020-09-23
申请号：EP12770096.1
申请日：2012-09-28
发明人： GOODING, Mark , KADIR, Timor , MCCABE, David
-
95.发明授权
公开(公告)号：EP3457355B1
公开(公告)日：2020-08-26
申请号：EP17795494.8
申请日：2017-05-05
发明人： QI, Chunchao , LIU, Yanli , CHEN, Hanjiang , WU, Guangsheng , ZHAO, Shukai , DING, Qing
-
公开(公告)号：EP3690797A3
公开(公告)日：2020-08-12
申请号：EP20153297.5
申请日：2020-01-23
申请人： Stradvision, Inc.
发明人： KIM, Kye-Hyeon , KIM, Yongjoong , KIM, Hak-Kyoung , NAM, Woonhyun , BOO, SukHoon , SUNG, Myungchul , SHIN, Dongsoo , YEO, Donghun , RYU, Wooju , LEE, Myeong-Chun , LEE, Hyungsoo , JANG, Taewoong , JEONG, Kyungjoong , JE, Hongmo , CHO, Hojin
摘要： A method for learning an automatic labeling device for auto-labeling a base image of a base vehicle using sub-images of nearby vehicles is provided. The method includes steps of: a learning device inputting the base image and the sub-images into previous trained dense correspondence networks to generate dense correspondences; and into encoders to output convolution feature maps, inputting the convolution feature maps into decoders to output deconvolution feature maps; with an integer k from 1 to n, generating a k-th adjusted deconvolution feature map by translating coordinates of a (k+1)-th deconvolution feature map using a k-th dense correspondence; generating a concatenated feature map by concatenating the 1-st deconvolution feature map and the adjusted deconvolution feature maps; and inputting the concatenated feature map into a masking layer to output a semantic segmentation image and instructing a 1-st loss layer to calculate 1-st losses and updating decoder weights and encoder weights.
-
公开(公告)号：EP3690797A2
公开(公告)日：2020-08-05
申请号：EP20153297.5
申请日：2020-01-23
申请人： Stradvision, Inc.
发明人： KIM, Kye-Hyeon , KIM, Yongjoong , KIM, Hak-Kyoung , NAM, Woonhyun , BOO, SukHoon , SUNG, Myungchul , SHIN, Dongsoo , YEO, Donghun , RYU, Wooju , LEE, Myeong-Chun , LEE, Hyungsoo , JANG, Taewoong , JEONG, Kyungjoong , JE, Hongmo , CHO, Hojin
摘要： A method for learning an automatic labeling device for auto-labeling a base image of a base vehicle using sub-images of nearby vehicles is provided. The method includes steps of: a learning device inputting the base image and the sub-images into previous trained dense correspondence networks to generate dense correspondences; and into encoders to output convolution feature maps, inputting the convolution feature maps into decoders to output deconvolution feature maps; with an integer k from 1 to n, generating a k-th adjusted deconvolution feature map by translating coordinates of a (k+1)-th deconvolution feature map using a k-th dense correspondence; generating a concatenated feature map by concatenating the 1-st deconvolution feature map and the adjusted deconvolution feature maps; and inputting the concatenated feature map into a masking layer to output a semantic segmentation image and instructing a 1-st loss layer to calculate 1-st losses and updating decoder weights and encoder weights.
-
公开(公告)号：EP3676750A1
公开(公告)日：2020-07-08
申请号：EP18766162.4
申请日：2018-08-31
-
99.发明公开
公开(公告)号：EP3636063A1
公开(公告)日：2020-04-15
申请号：EP19187980.8
申请日：2019-07-24
摘要： Die vorliegende Erfindung betrifft ein Verfahren und eine Vorrichtung zum Erkennen des Verschleißes eines Bauteils, insbesondere eines Verschleißteils einer landwirtschaftlichen Maschine, anhand einer visuellen Beurteilung des Bauteils. Erfindungsgemäß wird von einem mobilen Endgerät mit einer optischen Erfassungseinrichtung, insbesondere einer Kamera, ein Ist-Bild des Bauteils erfasst und von einer Datenkommunikationseinrichtung an eine Auswerteeinheit übertragen, die das Ist-Bild des Bauteils mit zumindest einem Referenzbild des Bauteils, das in einem Referenzbild-Speicher bereitgehalten wird, vergleicht und anhand des Bildvergleichs den Verschleißzustand des Bauteils bestimmt.
-
100.发明授权
公开(公告)号：EP3143585B1
公开(公告)日：2020-03-25
申请号：EP15722492.4
申请日：2015-05-05
-
-
-
-
-
-
-
-
-
搜索结果
306 条记录 (耗时 0.014 秒)
