检索结果-内蒙古大学图书馆

Unsupervised motion detection with background update and shadow suppression

控制理论与应用（英文版） 2012年第4期10卷 517-522页

作者： Yepeng GUAN School of Communication and Information Engineering Shanghai University Key Laboratory of Advanced Displays and System Application Ministry of Education

An algorithm is developed to detect moving object and suppress shadow. According to motion variations caused by some moving objects in a scene, a background update approach is proposed. The developed update method ef- ficiently prevents undesired corruption of background and does not consider the adaptation coefficient or the learning rate used in some existing algorithms. A multi-scale wavelet transform methodology is used to segment foreground from a clut- ter background. The optimal selection of threshold value is automatically determined which does not require any complex supervised training or manual calibration. According to photometric invariant, a color ratio difference is proposed to sup- press shadow. Some complete foreground motion object regions are extracted by integrating moving object segmentation in the multi-scale wavelet with shadow suppression in the color ratio difference. The mentioned method is less affected by the presence of moving objects in a scene. Experimental results show that the proposed approach is efficient in detecting motion objects and suppressing shadows by comparisons.

关键词： Moving objects segmentation Shadow elimination Color ratio Multi-scale wavelet transformation

来源：评论

学校读者我要写书评

暂无评论

Frame-layer bit allocation for multi-view video coding based on frame complexity estimation

引用

Journal of Shanghai University(English Edition) 2010年第1期14卷 50-54页

作者：严涛安平沈礼权李振纲王贺张兆杨 School of Communication and Information Engineering Shanghai University Key Laboratory of Advanced Displays and System Application

Current multi-view video coding （MVC） reference model in joint video team （JVT） does not provide efficient rate control schemes. This paper presents a rate control algorithm for MVC by improving the quadratic rate-distortion （R-D） model. We reasonably allocate bit-rate among views based on the correlation analysisl The proposed algorithm consists of three levels to control the rate bits more accurately, of which the frame layer allocates bits according to the frame complexity and the temporal activity. Extensive experiments show that the proposed algorithm can control the bit rate efficiently.

关键词： multi-view video coding (MVC) rate control bit-allocation rate-distortion model correlation analysis frame complexity

来源：评论

学校读者我要写书评

暂无评论

Robust video foreground segmentation and face recognition

引用

Journal of Shanghai University(English Edition) 2009年第4期13卷 311-315页

作者：管业鹏 School of Communication and Information Engineering Shanghai University Key Laboratory of Advanced Displays and System Application Ministry of Education Shanghai University

Face recognition provides a natural visual interface for human computer interaction （HCI） applications. The process of face recognition, however, is inhibited by variations in the appearance of face images caused by changes in lighting, expression, viewpoint, aging and introduction of occlusion. Although various algorithms have been presented for face recognition, face recognition is still a very challenging topic. A novel approach of real time face recognition for HCI is proposed in the paper. In view of the limits of the popular approaches to foreground segmentation, wavelet multi-scale transform based background subtraction is developed to extract foreground objects. The optimal selection of the threshold is automatically determined, which does not require any complex supervised training or manual experimental calibration. A robust real time face recognition algorithm is presented, which combines the projection matrixes without iteration and kernel Fisher discriminant analysis （KFDA） to overcome some difficulties existing in the real face recognition. Superior performance of the proposed algorithm is demonstrated by comparing with other algorithms through experiments. The proposed algorithm can also be applied to the video image sequences of natural HCI.

关键词： face recognition human computer interaction (HCI) foreground segmentation face detection threshold

来源：评论

学校读者我要写书评

暂无评论

QUALITY ENHANCEMENT FOR INTRA FRAME CODING VIA CNNS: AN ADVERSARIAL APPROACH

QUALITY ENHANCEMENT FOR INTRA FRAME CODING VIA CNNS: AN ADVE...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Zhipeng Jin Ping An Chao Yang Liquan Shen Shanghai Institute for Advance Communication and Data Science Key Laboratory of Advance Displays and System Application Ministry of Education

ISBN: (纸本)9781538646595

Lossy compression is an indispensable technique in image/video processing, due to its highly desirable ability of reducing the huge data volume. However, lossy compression introduces complex compression artifacts. To reduce these artifacts, post-processing techniques have been extensively studied. In this paper, we propose a novel post-processing technique using multi-level progressive refinement network via an adversarial training approach, called MPRGAN, for artifacts reduction and coding efficiency improvement in intra frame coding. Furthermore, our network generates multi-level residues in one feed-forward pass through the progressive reconstruction. This coarse-to-fine work fashion, which makes our network have high flexibility, can make trade-off between enhanced quality and computational complexity. Thereby facilitates the resource-aware applications. Extensive evaluations on benchmark datasets verify the superiority of our proposed MPRGAN model over the latest state-of-the-art methods with fast deployment running speed.

关键词： Convolutional neural network (CNN) compression artifacts reduction compression post-processing image enhancement High Efficiency Video Coding (HEVC) image enhancement lossy compression Artifacts FRAMES artifact reduction COMPRESSION ARTIFACTS

来源：评论

学校读者我要写书评

暂无评论

Texture and space-time based moving objects segmentation and shadow removing

Texture and space-time based moving objects segmentation and...

引用

3rd International Conference on Swarm Intelligence, ICSI 2012

作者： Guan, Ye-Peng School of Communication and Information Engineering Shanghai University China Key Laboratory of Advanced Displays and System Application Ministry of Education China

ISBN: (纸本)9783642310195

A novel algorithm is developed to detect moving objects and remove cast shadows by exploiting textural and spatial-temporal features. Multi-scale wavelet transformation is used to segment moving objects based on spatial property. Textural and spectral features color ratio differences between two adjacent pixels in four different directions are used to remove cast shadows. RGB color space is selected instead of introducing complex color models to segment moving objects and eliminate shadows. The proposal requires much less efforts compared with currently available methods. It does not require any complex supervised training phase, and does not require manual calibration or makes any hypothesis. Experiments have highlighted that the proposal is robust and efficient to segment moving objects and suppress shadow by comparisons. © 2012 Springer-Verlag.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

A novel depth coding scheme for multiview video plus depth compression

A novel depth coding scheme for multiview video plus depth c...

引用

2010 International Conference on Audio, Language and Image Processing, ICALIP 2010

作者： Zhang, Qiuwen An, Ping Zuo, Yifan Zhang, Zhaoyang School of Communication and Information Engineering Shanghai University Shanghai China Key Laboratory of Advanced Displays and System Application Ministry of Education China

ISBN: (纸本)9781424458653

Efficient compression of multi-view images and videos is an open and interesting research issue that has been attracting the attention of both academic and industrial world during the past several years. Multiview video plus depth (MVD) is a new 3D video format that would support 3D television (3DTV) and free viewpoint television (FTV). Depth-images are a 2D representation of the 3D scene surface and for 3DTV and FTV applications the depth information of MVD data is used for rendering virtual intermediate views of the scene. In this paper, we propose a novel coding scheme that is adapted to the special characteristics of depth-images, individual coding for color and depth data: the conventional multiview coding approach (MVC) is used for color videos and multidimensional multiscale parser (MMP) algorithm for depth maps coding. Experimental results show that the presented scheme achieves significant coding gains at high rate while compared with the joint multiview video model and Platelet depth coding. ©2010 IEEE.

关键词： Video signal processing

来源：评论

学校读者我要写书评

暂无评论

Solution for hybrid bandwidth variation in wireless video environments

Solution for hybrid bandwidth variation in wireless video en...

引用

2005 Second IEEE International Workshop on Mobile Commerce and Services, WMCS'05

作者： Li, Zhi-Gang Zhang, Zhao-Yang Wu, Biao Zhang, Ying School of Communication and Information Engineering Shanghai University Shanghai 200072 China Key Laboratory of Advanced Displays and System Application Ministry of Education

ISBN: (纸本)0769523919

With the development of broadband wireless networks, high efficiency of wireless video transmission has been received increasingly greater attentions than before. One should settle the problems of high-compression efficiency and that of adaptation to the random variation of transmission bandwidth, as well as a network friendly design, in wireless environments. SP(Synchronization- Predictive) frame, which enables high efficiency of switching between two or more bitstreams with different qualities, is supported by H.264/AVC Extended Profile suitable for mobile services. On the other hand, FGS(Fine-Granular- Scalability), which can always adapt to the network bandwidth varying but with some sacrifice of coding efficiency, is supported by MPEG-4. This paper proposes a solution for combination these two tools with each other so as to accommodate high bandwidth variations of wireless networks and low bandwidth variations flexibly for transmitted streams. Moreover, it also improves the efficiency of video streaming. Experimental results show that our proposed system outperforms FGS by 0.76dB and the H.264/AVC-based video stream switching approach by 0.51 dB on average under 3GPP /3GPP2 wireless common test conditions. © 2005 IEEE.

关键词： Wireless telecommunication systems

来源：评论

学校读者我要写书评

暂无评论

Efficient Wavelet Channel Attention Module with a Fusion Network for Image Super-Resolution 18th

Efficient Wavelet Channel Attention Module with a Fusion N...

引用

18th International Forum of Digital Multimedia Communication, IFTC 2021

作者： Han, Xiyu Ma, Jian Xu, Guoming An, Ping Ma, Ran School of Internet Anhui University Hefei230039 China School of Computer Science Fudan University Shanghai200433 China Key Laboratory of Advance Displays and System Application Ministry of Education Shanghai University Shanghai200444 China

ISBN: (纸本)9789811922657

In recent years, deep convolutional neural networks (CNNs) have been generally used in image Super-Resolution (SR) and has made great progress. Nevertheless, the existing CNNs based SR method cannot fully search the background information in the step of feature extraction. Moreover, the later network pursues too much deeper and heavier, thus ignoring the desired performance of SR. To solve the problem, we project a learning wavelets and channel attention network (LWCAN) for image SR. The network mainly comprises three branches. The first part extracts the low-level feature from the input image through two convolution layers and the Efficient Channel Attention (ECA) block. The second part is calculating the second level low frequency wavelet coefficient. The third part is used for forecasting the residual frequency bands of wavelet coefficient. Finally, the reverse wavelet transform is used to reconstruct the SR image from these coefficients. Experiments on the common used dataset prove the effectiveness of our projected LWCAN in the light of visual effects and quantitative metrics. © 2022, Springer Nature Singapore Pte Ltd.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

A deep learning framework for face verification without alignment

A deep learning framework for face verification without alig...

引用

作者： Fan, Zhongkui Guan, Ye-peng School of Communication and Information Engineering Shanghai University Shanghai China Key Laboratory of Advanced Displays and System Application Ministry of Education Shanghai China

Most of the CNN (convolutional neural networks) methods require alignment, which will affect the efficiency of verification. This paper proposes a deep face verification framework without alignment. First and foremost, the framework consists of two training stages and one testing stage. In the first training stage, the CNN is fully trained on the large face dataset. In the second training stage, embedding triplet is adopted to fine-tune the models. Furthermore, in the testing stage, SIFT (scale invariant feature transform) descriptors are extracted from intermediate pooling results for cascading verification, which effectively improves the accuracy of face verification without alignment. Last but not least, two CNN architectures are designed for different scenarios. The CNN1 (convolutional neural networks 1), with fewer layers and parameters, requires a small amount of memory and computation in training and testing, so it is suitable for real-time system. The CNN2 (convolutional neural networks 2), with more layers and parameters, has excellent face verification. Through the long-term training on WEB-face dataset and experiments on the LFW (labled faces in the wild), YTB (YouTube) datasets, the results show that the proposed method has superior performance compared with some state-of-the-art methods. © 2020, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Extended application of scalable video coding methods

引用

2nd International Conference on Image Analysis and Recognition, ICIAR 2005

ISBN: (纸本)3540290699

SP(Synchronization-Predictive) frame coding, which enables high efficiency of switching between two video bitstreams with different qualities, is supported by H.264/AVC. And FGS(Finc-Granular-Scalability) coding is supported by MPEG-4 video standard. This paper proposes a solution for combination these two tools with each other so as to adapt to high bandwidth variations of Internet or wireless networks and to low bandwidth variations flexibly for transmitted video streams. Experimental results show that our proposed system outperforms FGS coding by 0.47dB and the H.264/AVC-based video stream switching approach by 0.23dB on average. © Springer-Verlag Berlin Heidelberg 2005.

关键词： Image analysis

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：