检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Chen, Zhibo He, Tianyu Jin, Xin Wu, Feng CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

One key challenge to learning-based video compression is that motion predictive coding, a very effective tool for video compression, can hardly be trained into a neural network. In this paper we propose the concept of PixelMotionCNN (PMCNN) which includes motion extension and hybrid prediction networks. PMCNN can model spatiotemporal coherence to effectively perform predictive coding inside the learning network. On the basis of PMCNN, we further explore a learning-based framework for video compression with additional components of iterative analysis/synthesis, binarization, etc. Experimental results demonstrate the effectiveness of the proposed scheme. Although entropy coding and complex configurations are not employed in this paper, we still demonstrate superior performance compared with MPEG-2 and achieve comparable results with H.264 codec. The proposed learning-based scheme provides a possible new direction to further improve compression efficiency and functionalities of future video coding. Copyright © 2018, The Authors. All rights reserved.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Hierarchical co-segmentation of 3D point clouds for indoor scene

Hierarchical co-segmentation of 3D point clouds for indoor s...

引用

International Conference on systems, Signals and Image processing, IWSSIP

作者： Yanting Lin CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei City China

ISBN: (纸本)9781509063451

Segmentation of point clouds has been studied under a variety of scenarios. However, the segmentation of scanned point clouds for a clustered indoor scene remains significantly challenging due to noisy and incomplete data, as well as scene complexity. Based on the observation that objects in an indoor scene vary largely in scale but are typically supported by planes, we propose a co-segmentation approach. This technique utilizes the mutual agency between the point clouds captured at different times after the objects' poses change due to human actions. Hence, we hierarchically segment scenes from different times into patches and generate tree structures to store their relations. By iteratively clustering patches and co-analyzing them based on the relations between patches, we modify the tree structures and generate our results. To test the robustness of our method, we evaluate it on imperfectly scanned point clouds from a childroom, a bedroom, and two offices scenes.

关键词： Three-dimensional displays Image color analysis geometry Mathematical model Principal component analysis Silicon

来源：评论

学校读者我要写书评

暂无评论

VNVC: A Versatile Neural Video Coding Framework for Efficient Human-Machine Vision

arXiv

引用

arXiv 2023年

作者： Sheng, Xihua Li, Li Liu, Dong Li, Houqiang The CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Almost all digital videos are coded into compact representations before being transmitted. Such compact representations need to be decoded back to pixels before being displayed to humans and – as usual – before being enhanced/analyzed by machine vision algorithms. Intuitively, it is more efficient to enhance/analyze the coded representations directly without decoding them into pixels. Therefore, we propose a versatile neural video coding (VNVC) framework, which targets learning compact representations to support both reconstruction and direct enhancement/analysis, thereby being versatile for both human and machine vision. Our VNVC framework has a feature-based compression loop. In the loop, one frame is encoded into compact representations and decoded to an intermediate feature that is obtained before performing reconstruction. The intermediate feature can be used as reference in motion compensation and motion estimation through feature-based temporal context mining and cross-domain motion encoder-decoder to compress the following frames. The intermediate feature is directly fed into video reconstruction, video enhancement, and video analysis networks to evaluate its effectiveness. The evaluation shows that our framework with the intermediate feature achieves high compression efficiency for video reconstruction and satisfactory task performances with lower complexities. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Improving Wetland Mapping by Using Multi-Source Data Sets

Improving Wetland Mapping by Using Multi-Source Data Sets

引用

International Symposium on Image and Data Fusion (ISIDF)

作者： Luyan Ji Kang Jiang Xiurui Geng Hairong Tang Kai Yu Yongchao Zhao Key Laboratory of Technology in Geo-spatial information Processing and Application System Institute of Electronics Chinese Academy of Science Beijing China

To conserve and manage wetland resources, it is important to map wetlands and monitor their changes. However, wetland mapping is difficult because of spectral confusion with other landcover classes and spectral variability among different types of wetlands. This paper demonstrated a multi-source based approach for improving the accuracy of wetland mapping. According to the formation of wetland, variables derived from multi-source image date, and other ancillary GIS layers were first integrated to create the possible region for wetland (PRW). And then classification was conducted within the PRW to map wetlands. PRW could greatly reduce the amount of other land cover classes that participated in the classification, therefore reducing both the difficulty of wetland mapping and the commission error rate. In this study, we chose the test area in Dongzhai Harbor, Hainan Island, China, where the main wetland type is mangrove. The mapping was based on LANDSAT TM/ETM+ imagery combined with DEM data, and the ancillary GIS data included available water, soil and vegetation layers. The thematic accuracy of the mapping was assessed using high-resolution images from Google Earth and local wetlands databases. Classification of the 2001 Landsat ETM+ scene alone resulted in consumer's accuracy of 65% and Kappa coefficients of 0.69, whereas the multi-source based approach with the same training samples resulted in an accuracy of 86% and 0.80. The developed method is portable, relatively easy to implement, and should be applicable in other landcover classes and over larger extents.

关键词： Remote sensing Accuracy Satellites Earth Training Monitoring Databases

来源：评论

学校读者我要写书评

暂无评论

A Bayesian adaptive weighted total generalized variation model for image restoration

A Bayesian adaptive weighted total generalized variation mod...

引用

IEEE International Conference on Image processing

作者： Zhenbo Lu Houqiang Li Weiping Li CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Heifei Anhui China

In recent years, the Total Generalized Variation (TGV) model has received lots of attention in image processing community. Though this model can restore image with natural intensity transitions, its spatial identical parameter setting limits its performance. In this paper, we propose a novel Adaptive Weighted Total Generalized Variation model for image restoration. We analyze the TGV model from Bayesian Probability view and derive a novel adaptive parameter calculation scheme for it, exploiting the image's self-similarity. Experiment results on image deblurring and reconstruction show that by adapting the parameters in TGV model to image contents, the proposed model can restore image's edges and details well and achieve significant improvement over state of the art variational based models.

关键词： Adaptation models Image restoration Mathematical model Approximation methods Bayes methods TV Minimization

来源：评论

学校读者我要写书评

暂无评论

Efficient structure-preserving superpixel segmentation based on minimum spanning tree

Efficient structure-preserving superpixel segmentation based...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yu Bai Xuejin Chen CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei Anhui China

ISBN: (纸本)9781467372596

We propose a novel superpixel algorithm based on Minimum Spanning Tree (MST), to generate superpixels efficiently while strictly adhere to object boundaries. The MST, which built by gradually removing strong edges of the image graph extracted from the image, is more sensitive to image local structures. Therefore, an efficient hierarchical clustering strategy is basically employed in our algorithm to segment the input image into superpixels based on the tree distance. To gradually merge the image pixels and remove texture noises, a multi-layer scheme with different resolutions of superpixels is proposed. In each layer, the graph is constructed from the lower layer and segmented into superpixels in a linear complexity with the node number in the graph. Because the node number in each layer is exponentially reduced, the computational time of our method mainly concentrates on the first few layers, which is linear with the number of image pixels. The experimental results conducted on the Berkeley Segmentation Dataset demonstrate that our method outperforms state-of-the-art methods both in terms of structure preservation and computational efficiency.

关键词： Image segmentation Image color analysis Image edge detection Clustering algorithms Partitioning algorithms Joining processes Colored noise

来源：评论

学校读者我要写书评

暂无评论

ON THE USE OF CNN FOR AUTOMATED QUALITY ASSESSMENT OF GF-3 POLARIMETRIC DATA

ON THE USE OF CNN FOR AUTOMATED QUALITY ASSESSMENT OF GF-3 P...

引用

IEEE International geoscience and Remote Sensing Symposium

作者： Songtao Shangguan Xiaolan Qiu Bin Lei The Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute of Electronics Chinese Academy of Sciences Beijing China

With the needs of quality assessment for massive GF-3 polarimetric data, a method based on common distribution targets has been proposed by Sha Jiang. However, it needs manually selection of those woodlands, and cannot be performed automatically. In this paper, an automated GF-3 full-polarization SAR data quality assessment method is conducted using a classic Convolution Neural Network (VGG-16). The network is pre-trained by Radarsat-2 PolSAR data and then trained by selected typical GF-3 scenes. It is supposed to learn the features of the targets, which satisfies the azimuthal symmetry and backscatter reciprocity and fulfills the quality assessment work. Several typical GF-3 strips data are used to test the method. Experiments show that the network can predict the plots of targets from a new scene under the interference of polarimetric distortion and noise. And, the quality assessment results by the network are consistent with the manual assessment results, which shows the effectiveness of the method.

关键词： Quality assessment Distortion Data integrity Strips Manuals Forestry Radar polarimetry

来源：评论

学校读者我要写书评

暂无评论

A novel proposal of Gaofen-3 satellite constellation for multi-applications

A novel proposal of Gaofen-3 satellite constellation for mul...

引用

ISPRS geospatial Week 2017

作者： Qiu, Xiaolan Ding, Chibiao Lei, Bin Han, Bing Li, Fangfang Key Laboratory of Geo-Spatial Information Processing and Application System Chinese Academy of Sciences Beijing China Institute of Electronics Chinese Academy of Sciences Suzhou Research Center Suzhou China Institute of Electronics Chinese Academy of Sciences Beijing China

Gaofen-3 is the first C-band fully polarimetric SAR satellite in China, which is widely used in various fields such as ocean monitoring, disaster reduction and so on. In this paper, a new satellite constellation is proposed based on the orbit of Gaofen-3 satellite. The constellation includes Gaofen-3 and other two duplicates. It is able to do repeat-pass interferometry, repeat-pass differential interferometry, along-track interferometry and stereo measurement. With these abilities, it can generate the earth DEM without ground control points and have better performance in moving target identification and monitoring. The performance and the system requirements are analysed, which provides a good reference for the design of spaceborne SAR constellation.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Advancing Few-Shot Instance Segmentation of Military Aircraft in Remote Sensing Imagery with Large Vision Models

Advancing Few-Shot Instance Segmentation of Military Aircraf...

引用

IEEE International Symposium on geoscience and Remote Sensing (IGARSS)

作者： Xiyu Qi Yifan Wu Wenhui Zhang Zhan Chen Yidan Zhang Lei Wang Aerospace Information Research Institute Chinese Academy of Sciences Key Laboratory of Target Cognition and Application Technology (TCAT) Key Laboratory of Network Information System Technology (NIST) Key Laboratory of Technology in Geo-Spatial Information Processing and Application System

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

This study introduces a novel few-shot instance segmentation framework MAR FSIS for identifying and segmenting aircraft in high-resolution remote sensing imagery under stringent few-shot conditions. Utilizing large vision models in conjunction with a sophisticated detector and a novel object prompter, MAR FSIS demonstrates superior performance in discerning intricate details of aircraft with minimal training examples. The effectiveness of this approach is confirmed through experimental evaluations on the proposed MAR20IS dataset, achieving remarkable precision in both detection and segmentation tasks.

关键词： Instance segmentation Training Atmospheric modeling Detectors Military aircraft Data models Proposals

来源：评论

学校读者我要写书评

暂无评论

No-reference light field image quality assessment based on spatial-angular measurement

arXiv

引用

arXiv 2019年

作者： Shi, Likun Zhou, Wei Chen, Zhibo CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Light field image quality assessment (LFI-QA) is a significant and challenging research problem. It helps to better guide light field acquisition, processing and applications. However, only a few objective models have been proposed and none of them completely consider intrinsic factors affecting the LFI quality. In this paper, we propose a No-Reference Light Field image Quality Assessment (NR-LFQA) scheme, where the main idea is to quantify the LFI quality degradation through evaluating the spatial quality and angular consistency. We first measure the spatial quality deterioration by capturing the naturalness distribution of the light field cyclopean image array, which is formed when human observes the LFI. Then, as a transformed representation of LFI, the Epipolar Plane Image (EPI) contains the slopes of lines and involves the angular information. Therefore, EPI is utilized to extract the global and local features from LFI to measure angular consistency degradation. Specifically, the distribution of gradient direction map of EPI is proposed to measure the global angular consistency distortion in the LFI. We further propose the weighted local binary pattern to capture the characteristics of local angular consistency degradation. Extensive experimental results on four publicly available LFI quality datasets demonstrate that the proposed method outperforms state-of-the-art 2D, 3D, multi-view, and LFI quality assessment algorithms. Copyright © 2019, The Authors. All rights reserved.

关键词： Deterioration

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：