-
11.发明公开
公开(公告)号：EP3410714A1
公开(公告)日：2018-12-05
申请号：EP17885721.5
申请日：2017-06-30
发明人： WANG, Jianzong , XIAO, Jing
IPC分类号： H04N19/30
摘要： The present disclosure provides a video compressed sensing reconstruction method, including: step B, after receiving to-be-reconstructed compressed video frames, extracting frame fragments of the compressed video frames according to a predetermined extraction rule; step C, inputting the frame fragments into an input layer of a pre-trained video frame reconstruction model, performing feature abstraction to the frame fragments through multiple hidden layers of the video frame reconstruction model, and building a nonlinear mapping between each frame fragment and a corresponding frame fragment block; and step D, reconstructing the input frame fragments to frame fragment blocks by the hidden layers according to the nonlinear mapping, and outputting the frame fragment blocks by an output layer of the video frame reconstruction model, and generating a reconstructed video based on the reconstructed frame fragment blocks. The present disclosure can render and reconstruct video frames quickly with a high quality.
-
公开(公告)号：EP3407229A1
公开(公告)日：2018-11-28
申请号：EP17741021.4
申请日：2017-01-16
发明人： WANG, Jianzong , LI, Hongjie , XIAO, Jing
IPC分类号： G06F19/00
CPC分类号： G06Q40/08 , G06F19/00 , G06K9/4609 , G06K9/4671 , G06K9/6211 , G06K9/6256 , G06K9/6268 , G06K9/628 , G06T7/0002 , G06T2207/30248
摘要： The present disclosure provides a method, system, apparatus, and storage medium for realizing antifraud in insurance claim based consistency of multiple images. The provided method includes: classifying damage assessing images of a same vehicle portion into one same image set; obtaining keypoint features of each image set, diving every two damage assessing images in each image set into one image group, matching multiple relevant keypoints from the damage assessing images in each image group; according to the relevant keypoints of each image group, calculating a feature point transform matrix of each image, and converting one of the two damage assessing images in each image group to a to-be-verified image which has the same shooting angle as the other damage assessing image in the image group; matching feature parameters of the to-be-verified image with those of the other damage assessing image in the same image group; and generating reminder information, when there are unmatched parameters, to remind the user of frauds of the damage assessing images received from the terminal. The embodiments of the present disclosure are capable of automatically identifying the fraudulent insurance claim.
-
搜索结果
12 条记录 (耗时 0.008 秒)
