-
公开(公告)号：EP3474191A1
公开(公告)日：2019-04-24
申请号：EP18192810.2
申请日：2018-09-05
发明人： Kim, Yongjoong , Nam, Woonhyun , Boo, Sukhoon , Sung, Myungchul , Yeo, Donghun , Ryu, Wooju , Jang, Taewoong , Jeong, Kyungjoong , Je, Hongmo , Cho, Hojin
摘要： A method for constructing a table including information on a pooling type based on ranges of scale of at least one object in at least one image for constructing table is provided. The method includes steps of: generating a first pooled feature map by applying max pooling and a second pooled feature map by applying avg pooling; and acquiring a first candidate bounding box by using the first pooled feature map and acquiring a second candidate bounding box by using the second pooled feature map; and comparing a first degree of similarity between the first candidate bounding box and a GT bounding box with a second degree of similarity between the second candidate bounding box and the GT bounding box to thereby construct the table so as to include information on respective optimal pooling types by respective ranges of the scale of the object.
-
2.发明公开
公开(公告)号：EP3467774A1
公开(公告)日：2019-04-10
申请号：EP18192824.3
申请日：2018-09-05
申请人： StradVision, Inc.
发明人： Kim, Yongjoong , Nam, Woonhyun , Boo, Sukhoon , Sung, Myungchul , Yeo, Donghun , Ryu, Wooju , Jang, Taewoong , Jeong, Kyungjoong , Je, Hongmo , Cho, Hojin
摘要： A method for tracking a target object in frames of video data using Absorbing Markov Chain (AMC), including steps of: (a) acquiring a bounding box containing the target object in a current frame and a segmentation result for the target object in a previous frame; (b) obtaining obtain a region of interest (ROI) in the current frame by enlarging the bounding box to contain a portion of background information surrounding the target object; (c) acquiring information on local regions within the ROI in the current frame; (d) constructing an AMC graph using at least part of the local regions within the region of interest (ROI) in the current frame and local regions within a region of interest (ROI) in the previous frame; and (e) acquiring a segmentation result for the target object within the current frame by thresholding individual nodes in the AMC graph using absorption times thereof.
-
公开(公告)号：EP3467708A1
公开(公告)日：2019-04-10
申请号：EP18192801.1
申请日：2018-09-05
申请人： StradVision, Inc.
发明人： Kim, Yongjoong , Nam, Woonhyun , Boo, Sukhoon , Sung, Myungchul , Yeo, Donghun , Ryu, Wooju , Jang, Taewoong , Jeong, Kyungjoong , Je, Hongmo , Cho, Hojin
IPC分类号： G06K9/00
摘要： A method for acquiring a pseudo-3D box from a 2D bounding box in a training image is provided. The method includes steps of: (a) a computing device acquiring the training image including an object bounded by the 2D bounding box; (b) the computing device performing (i) a process of classifying a pseudo-3D orientation of the object, by referring to information on probabilities corresponding to respective patterns of pseudo-3D orientation and (ii) a process of acquiring 2D coordinates of vertices of the pseudo-3D box by using regression analysis; and (c) the computing device adjusting parameters thereof by backpropagating loss information determined by referring to at least one of (i) differences between the acquired 2D coordinates of the vertices of the pseudo-3D box and 2D coordinates of ground truth corresponding to the pseudo-3D box, and (ii) differences between the classified pseudo-3D orientation and ground truth corresponding to the pseudo-3D orientation.
-
公开(公告)号：EP3477554A2
公开(公告)日：2019-05-01
申请号：EP18192822.7
申请日：2018-09-05
申请人： StradVision, Inc.
发明人： Kim, Yongjoong , Nam, Woonhyun , Boo, Sukhoon , Sung, Myungchul , Yeo, Donghun , Ryu, Wooju , Jang, Taewoong , Jeong, Kyungjoong , Je, Hongmo , Cho, Hojin
摘要： A learning method for adjusting parameters of a CNN using loss augmentation is provided. The method includes steps of: a learning device acquiring (a) a feature map from a training image; (b) (i) proposal ROIs corresponding to an object using an RPN, and a first pooled feature map by pooling areas, on the feature map, corresponding to the proposal ROIs, and (ii) a GT ROI, on the training image, corresponding to the object, and a second pooled feature map by pooling an area, on the feature map, corresponding to the GT ROI; and (c) (i) information on pixel data of a first bounding box when the first and second pooled feature maps are inputted into an FC layer, (ii) comparative data between the information on the pixel data of the first bounding box and a GT bounding box, and backpropagating information on the comparative data to adjust the parameters.
-
5.发明公开
公开(公告)号：EP3466764A1
公开(公告)日：2019-04-10
申请号：EP18192825.0
申请日：2018-09-05
申请人： StradVision, Inc.
发明人： Kim, Yongjoong , Nam, Woonhyun , Boo, Sukhoon , Sung, Myungchul , Yeo, Donghun , Ryu, Wooju , Jang, Taewoong , Jeong, Kyungjoong , Je, Hongmo , Cho, Hojin
摘要： A method of monitoring a blind spot of a monitoring vehicle by using a blind spot monitor is provided. The method includes steps of: the blind spot monitor (a) acquiring a feature map from rear video images, on condition that video images with reference vehicles in the blind spot are acquired, reference boxes for the reference vehicles are created, and the reference boxes are set as proposal boxes; (b) acquiring feature vectors for the proposal boxes on the feature map by pooling, inputting the feature vectors into a fully connected layer, acquiring classification and regression information; and (c) selecting proposal boxes by referring to the classification information, acquiring bounding boxes for the proposal boxes by using the regression information, confirming whether the bounding boxes match their corresponding proposal boxes, and determining whether the monitored vehicle is in the proposal boxes to determine the monitored vehicle is in the blind spot.
-
公开(公告)号：EP3483793A1
公开(公告)日：2019-05-15
申请号：EP18192804.5
申请日：2018-09-05
申请人： Stradvision, Inc.
发明人： Kim, Yongjoong , Nam, Woonhyun , Boo, Sukhoon , Sung, Myungchul , Yeo, Donghun , Ryu, Wooju , Jang, Taewoong , Jeong, Kyungjoong , Je, Hongmo , Cho, Hojin
摘要： A method for configuring a CNN with learned parameters that performs activation operation of an activation module and convolution operation of one or more convolutional layer in a convolutional layer at the same time is provided. The method includes steps of: (a) allowing a comparator to compare an input value corresponding to each of pixel values of an input image as a test image with a predetermined reference value and then output a comparison result; (b) allowing a selector to output a specific parameter corresponding to the comparison result among multiple parameters of the convolutional layer; and (c) allowing a multiplier to output a multiplication value calculated by multiplying the specific parameter by the input value and allowing the multiplication value to be determined as a result value acquired by applying the convolutional layer to an output of the activation module.
-
公开(公告)号：EP3471022A1
公开(公告)日：2019-04-17
申请号：EP18192813.6
申请日：2018-09-05
申请人： StradVision, Inc.
发明人： Kim, Yongjoong , Nam, Woonhyun , Boo, Sukhoon , Sung, Myungchul , Yeo, Donghun , Ryu, Wooju , Jang, Taewoong , Jeong, Kyungjoong , Je, Hongmo , Cho, Hojin
摘要： A learning method for acquiring a bounding box corresponding to an object in a training image from multi-scaled feature maps by using a CNN is provided. The learning method includes steps of: (a) allowing an N-way RPN to acquire at least two specific feature maps and allowing the N-way RPN to apply certain operations to the at least two specific feature maps; (b) allowing an N-way pooling layer to generate multiple pooled feature maps by applying pooling operations to respective areas on the at least two specific feature maps; and (c) (i) allowing a FC layer to acquire information on pixel data of the bounding box, and (ii) allowing a loss layer to acquire first comparative data, thereby adjusting at least one of parameters of the CNN by using the first comparative data during a backpropagation process.
-
公开(公告)号：EP3477554A3
公开(公告)日：2019-06-05
申请号：EP18192822.7
申请日：2018-09-05
申请人： StradVision, Inc.
发明人： Kim, Yongjoong , Nam, Woonhyun , Boo, Sukhoon , Sung, Myungchul , Yeo, Donghun , Ryu, Wooju , Jang, Taewoong , Jeong, Kyungjoong , Je, Hongmo , Cho, Hojin
摘要： A learning method for adjusting parameters of a CNN using loss augmentation is provided. The method includes steps of: a learning device acquiring (a) a feature map from a training image; (b) (i) proposal ROIs corresponding to an object using an RPN, and a first pooled feature map by pooling areas, on the feature map, corresponding to the proposal ROIs, and (ii) a GT ROI, on the training image, corresponding to the object, and a second pooled feature map by pooling an area, on the feature map, corresponding to the GT ROI; and (c) (i) information on pixel data of a first bounding box when the first and second pooled feature maps are inputted into an FC layer, (ii) comparative data between the information on the pixel data of the first bounding box and a GT bounding box, and backpropagating information on the comparative data to adjust the parameters.
-
9.发明公开
公开(公告)号：EP3467713A8
公开(公告)日：2019-06-05
申请号：EP18192803.7
申请日：2018-09-05
申请人： StradVision, Inc.
发明人： Kim, Yongjoong , Nam, Woonhyun , Boo, Sukhoon , Sung, Myungchul , Yeo, Donghun , Ryu, Wooju , Jang, Taewoong , Jeong, Kyungjoong , Je, Hongmo , Cho, Hojin
摘要： A method for improving image segmentation by using a learning device is disclosed. The method includes steps of: (a) if a training image is obtained, acquiring (2- K) th to (2-1) th feature maps through an encoding layer and a decoding layer, and acquiring 1 st to H th losses from the 1 st to the H th loss layers respectively corresponding to H feature maps, obtained from the H filters, among the (2-K) th to the (2-1) th feature maps; and (b) upon performing a backpropagation process, performing processes of allowing the (2-M) th filter to apply a convolution operation to (M-1) 2 -th adjusted feature map relayed from the (2-(M-1)) th filter to obtain M 1 -th temporary feature map; relaying, to the (2-(M+1)) th filter, M 2 -th adjusted feature map obtained by computing the M th loss with the M 1 -th temporary feature map; and adjusting at least part of parameters of the (1-1) th to the (1-K) th filters and the (2-K) th to the (2-1) th filters.
-
公开(公告)号：EP3467772A1
公开(公告)日：2019-04-10
申请号：EP18192807.8
申请日：2018-09-05
申请人： StradVision, Inc.
发明人： Kim, Yongjoong , Nam, Woonhyun , Boo, Sukhoon , Sung, myungchul , Yeo, Donghun , Ryu, Wooju , Jang, Taewoong , Jeong, Kyungjoong , Je, Hongmo , Cho, Hojin
摘要： A method for segmenting an image using a CNN is provided. The method includes steps of: a segmentation device acquiring (i) a first segmented image for a t -th frame by a CNN_PREVIOUS, having at least one first weight learned at a t -( i +1)-th frame, segmenting the image, (ii) optical flow images corresponding to the ( t -1)-th to the ( ti )-th frames, including information on optical flows from pixels of the first segmented image to corresponding pixels of segmented images of the ( t -1)-th to the ( t-i ) - th frames, and (iii) warped images for the t -th frame by replacing pixels in the first segmented image with pixels in the segmented images referring to the optical flow images, (iv) losses by comparing the first segmented image with the warped images, (v) a CNN_CURRENT with at least one second weight obtained by adjusting the first weight to thereby segment an image of the t -th frame and frames thereafter by using the CNN_CURRENT.
-
-
-
-
-
-
-
-
-
搜索结果
10 条记录 (耗时 0.009 秒)
