Synthetic aperture radar (SAR) tomography (TomoSAR) has attracted remarkable interest for its ability in achieving three-dimensional reconstruction along the elevation direction from multiple observations. In recent y...
详细信息
作者：
Liu, SenZhao, ShuxinPang, YingxueChen, ZhiboCAS
Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China
There is plenty of human-machine joint decision-making scenarios in the real world applications, such as driving assistant, suspect identification, medical diagnosis, etc. Existing algorithms propose that machine shou...
详细信息
We propose an end-to-end learned video compression scheme for low-latency scenarios. Previous methods are limited in using the previous one frame as reference. Our method introduces the usage of the previous multiple ...
详细信息
ISBN:
(数字)9781728171685
ISBN:
(纸本)9781728171692
We propose an end-to-end learned video compression scheme for low-latency scenarios. Previous methods are limited in using the previous one frame as reference. Our method introduces the usage of the previous multiple frames as references. In our scheme, the motion vector (MV) field is calculated between the current frame and the previous one. With multiple reference frames and associated multiple MV fields, our designed network can generate more accurate prediction of the current frame, yielding less residual. Multiple reference frames also help generate MV prediction, which reduces the coding cost of MV field. We use two deep auto-encoders to compress the residual and the MV, respectively. To compensate for the compression error of the auto-encoders, we further design a MV refinement network and a residual refinement network, taking use of the multiple reference frames as well. All the modules in our scheme are jointly optimized through a single rate-distortion loss function. We use a step-by-step training strategy to optimize the entire scheme. Experimental results show that the proposed method outperforms the existing learned video compression methods for low-latency mode. Our method also performs better than H.265 in both PSNR and MS-SSIM. Our code and models are publicly available.
Video stitching remains a challenging problem in computer vision. In this paper, we propose a novel edge-guided method to stitch multiple videos that have small overlapped regions. Our algorithm consists of three step...
详细信息
In this paper, we consider a novel image coding paradigm, termed semantically scalable coding. In the new paradigm, coded bitstream serves for multiple different semantic analysis tasks, and different tasks require di...
详细信息
ISBN:
(数字)9781728163956
ISBN:
(纸本)9781728163963
In this paper, we consider a novel image coding paradigm, termed semantically scalable coding. In the new paradigm, coded bitstream serves for multiple different semantic analysis tasks, and different tasks require different semantic granularities of the image. Thus, the bitstream is designed to be scalable in the sense that progressive decoding of the bitstream provides coarse-to-fine semantic granularities. As a concrete example, we consider the task of coarse-grained and fine-grained image classification. We present a method to compress the multiple deep feature maps that are intermediate representations of an image passing a trained deep network. The deep-layer feature maps can serve for coarse-grained image classification while the shallow-layer feature maps can serve for fine-grained image classification. Experimental results demonstrate the feasibility of the proposed method, as well as the advantage of the semantically scalable coding paradigm.
Imagery geometry models (IGMs) of the high-resolution satellite images (HRSIs) are always of great interest in the photogrammetry and remote sensing community for the raising new kinds of sensors and imaging systems. ...
详细信息
Data scarcity is a major obstacle for high-resolution mapping of permafrost on the Tibetan Plateau(TP).This study produces a new permafrost stability distribution map for the 2010 s(2005–2015)derived from the predict...
详细信息
Data scarcity is a major obstacle for high-resolution mapping of permafrost on the Tibetan Plateau(TP).This study produces a new permafrost stability distribution map for the 2010 s(2005–2015)derived from the predicted mean annual ground temperature(MAGT)at a depth of zero annual amplitude(10–25 m)by integrating remotely sensed freezing degree-days and thawing degree-days,snow cover days,leaf area index,soil bulk density,high-accuracy soil moisture data,and in situ MAGT measurements from 237 boreholes on the TP by using an ensemble learning method that employs a support vector regression model based on distance-blocked resampled training data with 200 *** of the new permafrost map indicates that it is probably the most accurate of all currently available *** map shows that the total area of permafrost on the TP,excluding glaciers and lakes,is approximately 115.02(105.47–129.59)×10^4 km^*** areas corresponding to the very stable,stable,semi-stable,transitional,and unstable types are 0.86×10^4,9.62×10^4,38.45×10^4,42.29×10^4,and 23.80×10^4 km^2,*** new map is of fundamental importance for engineering planning and design,ecosystem management,and evaluation of the permafrost change in the future on the TP as a baseline.
Deep convolutional neural networks (DCNNs) have been used to achieve state-of-the-art performance on land cover classification thanks to their outstanding nonlinear feature extraction abil-ity. DCNNs are usually desig...
详细信息
In this paper, we focus on a special class of symmetric tensors, which can be orthogonally diagonalizable, and investigate their Z-eigenpairs problem. We show that the eigenpairs can be uniformly expressed using sever...
详细信息
Single image super-resolution (SISR) aims to recover the high-resolution (HR) image from its low-resolution (LR) input image. With the development of deep learning, SISR has achieved great progress. However, It is sti...
详细信息
暂无评论