-
公开(公告)号：US20220343100A1
公开(公告)日：2022-10-27
申请号：US17238832
申请日：2021-04-23
发明人： Xinyi Wu , Yiwei Wang , Tian Xia , Peng Chang , Mei Han , Jing Xiao
摘要： A method for cutting or extracting video clips from a video, including the audio content relevant to points of particular interest, and combining the same for instruction or training on particular points; a computing device applying the method extracts text information from the spoken audio content of a video to be cut and obtains multiple paragraph segmentation positions as candidates for inclusion in a desired and finished presentation by analyzing the information from text representing the spoken audio content, the analysis being carried out by a semantic segmentation model. Candidate items of text are obtained by isolating pieces of text according to the paragraph segmentation positions. Time stamps of the candidate text segments are acquired, and candidate video clips are obtained by cutting the video according to the acquired time stamps.
-
公开(公告)号：US11386589B2
公开(公告)日：2022-07-12
申请号：US17122680
申请日：2020-12-15
发明人： Yuchuan Gou , Minghao Li , Bo Gong , Mei Han
IPC分类号： G06T11/00 , G06N3/04 , G06V10/56 , G06V30/262
摘要： A method for image generation and colorization includes displaying a drawing board interface; obtaining semantic labels of an image to be generated based on user input on the drawing board interface, each semantic label indicating a content of a region in the image to be generated; obtaining a color feature of the image to be generated; and automatically generating the image using a generative adversarial network (GAN) model according to the semantic labels and the color feature. The color feature is a latent vector input to the GAN model.
-
公开(公告)号：US20210201564A1
公开(公告)日：2021-07-01
申请号：US16729117
申请日：2019-12-27
发明人： Minghao Li , Jinghong Miao , Yuchuan Gou , Bo Gong , Mei Han
摘要： A method for generating a model for facial sculpture based on a generative adversarial network (GAN) includes training a predetermined GAN based on a three dimensional (3D) face dataset of multiple 3D face images to obtain an initial sculpture generation model. A curvature conversion on each of the multiple 3D face images is performed to obtain a distribution map of curvature value and the distribution map of curvature value of each of the multiple 3D face images is added as attention information to the initial sculpture generation model, to train and generate a face sculpture generation model. A target 3D face data and predetermined face curvature parameters are received, and the target 3D face data and the predetermined face curvature parameters are inputted into the face sculpture generation model to generate a face sculpture model. A computing device using the method is also provided.
-
公开(公告)号：US20240020977A1
公开(公告)日：2024-01-18
申请号：US17867667
申请日：2022-07-18
发明人： Xinyi Wu , Tian Xia , Xinlu Yu , Ziyi Chen , Iek-Heng Chu , Sirui Xu , Mei Han , Jing Xiao , Peng Chang
CPC分类号： G06V20/49 , G10L17/18 , G10L17/02 , G10L17/14 , G10L25/60 , G06V40/172 , G06V40/161 , G06F40/284
摘要： A system and method for multimodal video segmentation in a multi-speaker scenario are provided. A transcript of a video with a plurality of speakers is segmented into a plurality of sentences. Speaker change information is detected between each two adjacent sentences of the plurality of sentences based on at least one of audio content or visual content of the video. The video is segmented into a plurality of video clips based on the transcript of the video and the speaker change information.
-
公开(公告)号：US11830167B2
公开(公告)日：2023-11-28
申请号：US17353792
申请日：2021-06-21
发明人： Yuchuan Gou , Juihsin Lai , Mei Han
IPC分类号： G06V10/50 , G06T3/40 , G06V20/10 , G06F18/214 , G06F18/25
CPC分类号： G06T3/4076 , G06F18/214 , G06F18/253 , G06T3/4046 , G06V10/50 , G06V20/188
摘要： A system and a method for super-resolution image processing in remote sensing are disclosed. One or more sets of multi-temporal images with an input resolution and one or more first target images with a first output resolution are generated from one or more data sources. The first output resolution is higher than the input resolution. Each set of multi-temporal images is processed to improve an image match in the corresponding set of multi-temporal images. The one or more sets of multi-temporal images are associated with the one or more first target images to generate a training dataset. A deep learning model is trained using the training dataset. The deep learning model is provided for subsequent super-resolution image processing.
-
公开(公告)号：US11328506B2
公开(公告)日：2022-05-10
申请号：US16727788
申请日：2019-12-26
发明人： Ruei-Sung Lin , Nan Qiao , Yi Zhao , Bo Gong , Mei Han
摘要： In a crop identification method, multi-temporal sample remote sensing images labeled with first planting blocks of a specific crop are acquired. NDVI data of the sample remote sensing images are calculated. Noise of the NDVI data is reduced. A first multivariate Gaussian model is fitted based on de-noised NDVI data of the sample remote sensing image. Multi-temporal target remote sensing images are acquired. An NDVI time series of each pixel in the target remote sensing image is constructed. The NDVI time series is input to the first multivariate Gaussian model to obtain a likelihood value of each pixel displaying the specific crop in the remote sensing images. Second planting blocks of the specific crop in the target remote sensing images are determined accordingly. An accurate and robust identification result is thereby achieved.
-
公开(公告)号：US11157737B2
公开(公告)日：2021-10-26
申请号：US16727753
申请日：2019-12-26
发明人： Yi Zhao , Nan Qiao , Ruei-Sung Lin , Bo Gong , Mei Han
摘要： A cultivated land recognition method in a satellite image includes: segmenting a satellite image of the Earth into a plurality of standard images; and recognizing cultivated land area in each of the standard images using a cultivated land recognition model to obtain a plurality of first images. Edges of ground level entities in each of the standard images are detected using an edge detection model to obtain a plurality of second images. Each of the first images and a corresponding one of the second images is merged to obtain a plurality of third images; and cultivated land images is obtained by segmenting each of the third images using a watershed segmentation algorithm. Not only can a result of recognizing cultivated land in satellite images of the Earth be improved, but an efficiency of recognizing the cultivated land also be improved. A computing device employing the method is also disclosed.
-
公开(公告)号：US20210201024A1
公开(公告)日：2021-07-01
申请号：US16727788
申请日：2019-12-26
发明人： Ruei-Sung Lin , Nan Qiao , Yi Zhao , Bo Gong , Mei Han
摘要： In a crop identification method, multi-temporal sample remote sensing images labeled with first planting blocks of a specific crop are acquired. NDVI data of the sample remote sensing images are calculated. Noise of the NDVI data is reduced. A first multivariate Gaussian model is fitted based on de-noised NDVI data of the sample remote sensing image. Multi-temporal target remote sensing images are acquired. An NDVI time series of each pixel in the target remote sensing image is constructed. The NDVI time series is input to the first multivariate Gaussian model to obtain a likelihood value of each pixel displaying the specific crop in the remote sensing images. Second planting blocks of the specific crop in the target remote sensing images are determined accordingly. An accurate and robust identification result is thereby achieved.
-
公开(公告)号：US11048971B1
公开(公告)日：2021-06-29
申请号：US16726785
申请日：2019-12-24
发明人： Jinghong Miao , Bo Gong , Mei Han
IPC分类号： G06K9/62
摘要： In a method for training an image generation model, a first generator generates a first sample matrix, a first converter generates a sample contour image, a first discriminator optimizes the first generator and the first converter, a second generator generates a second sample matrix according to the first sample matrix, a second converter generates a first sample grayscale image, a second discriminator optimizes the second generator and the second converter, a third generator generates a third sample matrix according to the second sample matrix, a third converter generates a second sample grayscale image, a third discriminator optimizes the third generator and the third converter, a fourth generator generates a fourth sample matrix according to the third sample matrix, a fourth converter generates a sample color image, and a fourth discriminator optimizes the fourth generator and the fourth converter. The image generation model can be trained easily.
-
公开(公告)号：US20210166058A1
公开(公告)日：2021-06-03
申请号：US16701484
申请日：2019-12-03
发明人： Jinghong Miao , Yuchuan Gou , Ruei-Sung Lin , Bo Gong , Mei Han
IPC分类号： G06K9/48 , G06K9/62 , G06K9/46 , G06T7/13 , G06T3/40 , G06K9/42 , G06F16/538 , G06F16/56 , G06N3/04 , G06N3/08
摘要： An image generation method and a computing device using the method, includes creating an image database with a plurality of original images, and obtaining a plurality of first outline images of an object by detecting an outline of the object in each of the original images. Numerous first feature matrixes are obtained by calculating a feature matrix of each of the first outline images. A second feature matrix of a second outline image input by a user is calculated. A target feature matrix is selected from the plurality of first feature matrixes, the target feature matrix has a minimum difference as the second feature matrix. A target image corresponding to the target feature matrix is matched and displayed from the image database. The method and device allow detection of an object outline in an image input by users and the generation of an image with the detected outline.
-
-
-
-
-
-
-
-
-
搜索结果
32 条记录 (耗时 0.022 秒)
