检索结果-内蒙古大学图书馆

2019 IEEE International Conference on Signal, information and Data processing, ICSIDP 2019

作者： Qin, Feiyu Cao, Lumeng Chen, Xuejin CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (纸本)9781728123455

Semantic segmentation is a fundamental task in indoor scene understanding. Most previous supervised approaches rely on densely annotated image data sets. Due to the limited amount of images with segmentation labels, the performance of existing networks is greatly limited. In this paper, we exploit temporal correlation in video frames to improve the performance and robustness of segmentation networks. Two effective learning strategies are proposed to propagate the information from a few labeled frames to their immediate neighbor frames. First, we scale up training dataset for supervised semantic segmentation networks by generating pseudo ground-truth for neighboring frames from a labeled frame using filtered homography transformation. Furthermore, we introduce a self-supervised loss function to ensure temporal consistency between the segmentation results of adjacent frames. The experimental results demonstrate that our proposed method outperforms state-of-the-art techniques for semantic segmentation on NYU-Depth V2 dataset. © 2019 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

The Research on the Space-Time Variation of Phase Imbalance for GF-3 Azimuth Multichannel Mode 6

The Research on the Space-Time Variation of Phase Imbalance ...

引用

6th Asia-Pacific Conference on Synthetic Aperture Radar, APSAR 2019

作者： Shang, Mingyang Qiu, Xiaolan Han, Bing Zhong, Lihua DIng, Chibiao Yang, Junying Key Laboratory of Technology in Geo-Spatial Information Processing and Application Systems Institute of Electronics Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781728129129

Azimuth multichannel (AMC) synthetic aperture radar (SAR) is an advanced technique which can prevent the minimum antenna area constraint and provide high-resolution and wide-swath (HRWS) SAR images. Channel imbalance calibration is an important topic in AMC SAR signal processing, since it has a great impact on the image quality. The phase imbalance of AMC SAR is not only related to the radar system, but also to the satellite attitude. This paper first models the relationship between phase imbalance and satellite attitude, and analyzes the influence of satellite attitude on the phase imbalance. In the presence of the satellite attitude deviation, the phase imbalance is time-variation in azimuth, and spatial-variation in range. Then, the real data acquired by Gaofen-3 (GF-3) in the ultra-fine strip-map (UFS) mode is used to verify the relationship model both in theoretical calculations and estimation. The result shows that the model proposed in this paper can describe the space-time variation of phase imbalance very accurately. Finally, some discussions and conclusions are drawn and the future research perspectives are proposed. © 2019 IEEE.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Human Machine Joint Decision Making in Distorted Surveillance Scenario 2

Human Machine Joint Decision Making in Distorted Surveillanc...

引用

2nd China Symposium on Cognitive Computing and Hybrid Intelligence, CCHI 2019

作者： Liu, Sen Zhao, Shuxin Pang, Yingxue Chen, Zhibo CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (纸本)9781728140919

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 should give a rejection option when having a high risk or uncertainty score so that the input can be passed to human to make the decision. This is an interesting algorithmic model of human-machine collaboration, but implicitly assumes that humans are more trustworthy than machines. Such an assumption ignores the bias and inconsistency of human, especially in scenarios where machines have superior recognition ability than humans. In this work, we investigate the human-machine joint decision-making problem in distorted surveillance videos, where machines experimentally prove to be comparable to human beings in tolerance to distortion, sometimes even stronger. We propose a new human-machine joint decision-making framework by considering both the confidences of machine and human. To obtain the confidence of human, we build a real-life human decision-making database and propose a deep neural network to estimate human's confidence. Then, confidence alignment method and decision rule are proposed to further output the final decision. Experiments demonstrate that the proposed framework can make less human intervention and more accurate decisions in several human-machine joint decision-making scenarios. © 2019 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Hybrid transform for HEVC-based lossless coding

Hybrid transform for HEVC-based lossless coding

引用

2014 IEEE International Symposium on Circuits and Systems, ISCAS 2014

作者： Chen, Fangdong Zhang, Jinlei Li, Houqiang CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (纸本)9781479934324

The High Efficiency Video Coding (HEVC) with the transform bypass mode is simple but inefficient for lossless coding. For this reason, we propose a novel transform to further eliminate the redundancy between residues of different blocks in intra prediction. Dependent on intra prediction modes, the proposed transform is adaptable to exploit correlations of residues formed by different modes. In order to accurately obtain parameters of the transform matrix, an approach similar to the Wiener filtering method is adopted. Experimental results show that on top of the lossless coding mode in HEVC, our method offers the performance with a 7.4% bit-rate reduction on average for All Intra Main configuration. Compared with other representative algorithms, our proposal still shows an improvement in the compression ratio, without substantial increases of computational complexity in the encoder or decoder. © 2014 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Robust sketch-based image retrieval by saliency detection 22nd

Robust sketch-based image retrieval by saliency detection

引用

22nd International Conference on MultiMedia Modeling, MMM 2016

作者： Zhang, Xiao Chen, Xuejin CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (纸本)9783319276700

Sketch-based image retrieval (SBIR) has been extensively studied for decades because sketch is one of the most intuitive ways to describe ideas. However, the large expressional gap between hand-drawn sketches and natural images with small-scale complex structures is the fundamental challenge for SBIR systems. We present a novel framework to efficiently retrieve images with a query sketch based on saliency detection. In order to extract primary contours of the scene and depress textures, a hierarchical saliency map is computed for each image. Object contours are extracted from the saliency map instead of the original natural image. Histograms of oriented gradients (HOG) are extracted at multiple scales on a dense gradient field. Using a bag-of-visual-words representation and an inverted index structure, our system efficiently retrieves images by sketches. The experimental results conducted on a dataset of 15 k photographs demonstrate that our method performs well for a wide range of natural scenes. © Springer International Publishing Switzerland 2016.

关键词： Image retrieval

来源：评论

学校读者我要写书评

暂无评论

SAR data processing for GF3 12

SAR data processing for GF3

引用

12th European Conference on Synthetic Aperture Radar, EUSAR 2018

作者： Bing, Han Lihua, Zhong Jiayin, Liu Xiaolan, Qiu Yuxin, Hu Bin, Lei Key Laboratory of Technology in Geo-spatial Information Processing and Application Systems In-stituteof Electronics Chinese Academyof Sciences Beijing China

ISBN: (纸本)9783800746361

The Gaofen-3 (GF3) data processor was developed as a workstation-based GF3 synthetic aperture radar (SAR) data processing system. The processor consists of two subsystems of the GF3 ground segment, which are referred to as the data ingesting subsystem (DDS) and the product generation subsystem (PGS). The primary purpose of the DDS is to record and catalogue GF3 raw data with transferring format, and the PGS is to produce slant range or geocoded imagery from the signal data. This paper provides an overview of the GF3 data processor, including descriptions of the system architecture, the imagery generating procedures for different imaging modes and the output format. Some processing results will also be given here. © VDE VERLAG GMBH • Berlin • Offenbach.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Edge-Guided Panoramic Video Stitching with Limited Overlap

Edge-Guided Panoramic Video Stitching with Limited Overlap

引用

2019 IEEE International Conference on Signal, information and Data processing, ICSIDP 2019

作者： Xie, Chaoyu Chen, Xuejin CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (纸本)9781728123455

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 steps: (1) spherical projection of the input video frames based on camera calibration, (2) edge detection and edge-guided feature matching for video registration, and (3) seam optimization to eliminate distortions and ghosts in the composited panoramic videos. The experimental results and user studies demonstrate that our method is robust to videos that have small overlapped regions and produces more visually pleasing panoramic videos than state-of-the-art techniques. © 2019 IEEE.

关键词： Edge detection

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

2011 International Symposium on Image and Data Fusion, ISIDF 2011

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

ISBN: (纸本)9781457709692

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 highresolution 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. © 2011 IEEE.

关键词： Wetlands

来源：评论

学校读者我要写书评

暂无评论

IMPROVED CALIBRATION METHOD FOR AIRBORNE ATI-SAR BASELINE

引用

Journal of Electronics(China) 2012年第5期29卷 368-374页

作者： Wang Xin Hong Jun Institute of Electronics Chinese Academy of Sciences Key Laboratory of Geo-spatial Information Processing and Application System Technology Graduate University of Chinese Academy of Sciences

Airborne Along-Track Interferometric Synthetic Aperture Radar (ATI-SAR) baseline error is a main error resource affecting the precision of velocity measurement of moving objects and therefore should be calibrated externally. The Jet Propulsion laboratory (JPL) has proposed a calibration scheme for tasks of PacRim98 and PacRim2000 based on several static objects on the ground. In this paper, the influence of phase center uncertainty on baseline determination by using PacRim method proposed by JPL is analyzed. According to the analysis, the phase center uncertainty can cause a constant part of error to the result of baseline calibration. In order to deal with this problem, an improved calibration method on the basis of sensitivity equations and some ground moving targets, whose velocities are already known, is proposed in this paper. The simulation results show that our proposed calibration method has improved the accuracy of baseline calibration and has obviously prohibited the effect of antennas' phase center uncertainty.

关键词： Airborne Along-Track Interferometric Synthetic Aperture Radar (ATI-SAR) Baseline error Baseline calibration Sensitivity equation

来源：评论

学校读者我要写书评

暂无评论

An invariant generalized Hough transform based method of inshore ships detection

An invariant generalized Hough transform based method of ins...

引用

2011 International Symposium on Image and Data Fusion, ISIDF 2011

作者： Xu, Jian Fu, Kun Sun, Xian Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute of Electronics Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781457709692

Automatic inshore ship detection from remote sensing imagery has many important applications, such as ship change detection and harbor dynamic surveillance. Stable performance of inshore ship detection is vital to the analysis of ship change and then determines the harbor surveillance effect. However, it is hard to detect inshore ships utilizing the traditional area-based method because the grayscale and texture character of inshore ships are similar to that of the shore. In this paper, a new method based on invariant generalized Hough transform is introduced to extract ship shape using the evidence-gathering procedure. In contrast with other shape extraction methods used in inshore ships detection, our method is specially tolerant to noise and occlusion, and also invariant to translation, scale and rotation transformation. Moreover, our method can be used to separate ships moored together that can benefit to ship recognition. Experiment results are demonstrated on the optical remote sensing imagery from Google Earth. © 2011 IEEE.

关键词： Ships

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：