检索结果-内蒙古大学图书馆

Real-time video object segmentation in H.264 compressed domain

IET image processing 2009年第5期3卷 272-285页

作者： Mak, C. -M. Cham, W. -K. Chinese Univ Hong Kong Shatin Hong Kong Peoples R China

In this study the authors proposed a real-time video object segmentation algorithm that works in the H.264 compressed domain. The algorithm utilises the motion information from the H.264 compressed bit stream to identify background motion model and moving objects. In order to preserve spatial and temporal continuity of objects, Markov random field (MRF) is used to model the foreground field. Quantised transform coefficients of the residual frame are also used to improve segmentation result. Experimental results show that the proposed algorithm can effectively extract moving objects from different kinds of sequences. The computation time of the segmentation process is merely about 16 ms per frame for CIF size frame, allowing the algorithm to be applied in real-time applications.

关键词： residual frame background motion model motion information computer vision and image processing techniques real-time video object segmentation image and video coding Markov processes image coding moving objects Markov random field spatial continuity temporal continuity H.264 compressed bit stream quantised transform coefficients data compression H.264 compressed domain image segmentation

来源：评论

学校读者我要写书评

暂无评论

CSNet: Cascade stereo matching network using multi-information cost volume

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2021年第5期15卷 635-645页

作者： Shao, XiaoTao Zhang, Wen Guo, MingKun Guo, SiQi Qian, ManYi Beijing Jiaotong Univ Sch Elect & Informat Engn 3 Shangyuan Village Beijing Peoples R China

The disparity map produced by matching a pair of rectified stereo images provides estimated depth information and accurate distance calculations for autonomous driving. For most stereo matching networks, cost volume plays a crucial role in the accuracy of disparity maps. To increase the accuracy of disparity maps, an improved cost volume method called multi-information cost volume (MICV) is proposed, with the fusion of concatenation volume and improved correlation volume, which is calculated both in inner product space and Euclidean space, to measure the correlation similarity between features in the left and right images. The inclusion of a squeeze and excitation (SE) module further improves MICV by adjusting the contribution of the correlation volume. To refine the disparity map and enhance the semantics of small objects, a cascade stereo network called CSNet is proposed, with a dilation feature fusion unit (DFFU) to calculate and integrate disparity maps from three different scale branches. The smaller scale branches are gradually integrated into the larger scale branches to implement the transmission of semantic information. The proposed method was evaluated using several established benchmarks including the Sceneow, KITTI2012 and KITTI2015 datasets. Experimental results demonstrate that authors' method produces more accurate disparity maps compared with existing state-of-the-art methods.

关键词： image recognition computer vision and image processing techniques

来源：评论

学校读者我要写书评

暂无评论

A discriminative self-attention cycle GAN for face super-resolution and recognition

引用

IET image processing 2021年第11期15卷 2614-2628页

作者： Li, Xiaoguang Dong, Ning Huang, Jianglu Zhuo, Li Li, Jiafeng Beijing Univ Technol Fac Informat Technol Beijing Peoples R China

Face image captured via surveillance videos in an open environment is usually of low quality, which seriously affects the visual quality and recognition accuracy. Most image super-resolution methods adopt paired high-quality and its interpolated low-resolution version to train the super-resolution network. It is difficult to achieve contented visual quality and restoring discriminative features in real scenarios. A discriminative self-attention cycle generative adversarial network is proposed for real-world face image super-resolution. Based on the cycle GAN framework, unpaired samples are adopted to train a degradation network and a reconstruction network simultaneously. A self-attention mechanism is employed to capture the contextual information for details restoring. A Siamese face recognition network is introduced to provide a constraint on identify consistency. In addition, an asymmetric perceptual loss is introduced to handle the imbalance between the degradation model and the reconstruction model. Experimental results show that the observation model achieved more realistic low-quality face images, and the super-resolved face images have shown better subjective quality and higher face recognition performance.

关键词： image resolution low resolution version open environment image super resolution methods image reconstruction Siamese face recognition network image recognition computer vision and image processing techniques degradation network real-world face image super resolution self attention mechanism face images discriminative self-attention cycle generative adversarial network reconstruction network visual quality discriminative self-attention cycle GAN cycle GAN framework super resolved face images face super resolution video surveillance higher face recognition performance recognition accuracy feature extraction Video signal processing face recognition subjective quality super resolution network Television and video equipment, systems and applications restoring discriminative features

来源：评论

学校读者我要写书评

暂无评论

Multifocus image fusion using modified pulse coupled neural network for improved image quality

引用

IET image processing 2010年第6期4卷 443-451页

作者： Agrawal, D. Singhai, J. MANIT Dept Elect & Commun Engn Bhopal MP India

The present day camera systems have the limitation of acquiring the clearer image of a scene having objects at different distances. This limitation can be overcome by fusion of multiple images of the scene taken with different camera settings. The fusion of these images comes under the category of multifocus image fusion. In the existing method of image, fusion partitioned source image blocks are fused by pulse coupled neural network (PCNN) based on their clarity measure. PCNN plays an important role in the image fusion process in choosing the best-quality image block for fused image. Fusion method becomes tedious and time consuming because of the inherent complexity of PCNN. In this study, a modified approach of PCNN suitable for application in image fusion technique is proposed by reducing the processing time and computational complexity. The modifications proposed are in linking and feeding field of PCNN. This study presents a method for multifocus image fusion by using modified PCNN (MPCNN) with spatial frequency (SF) and energy of Laplacian (EOL) as clarity measures. The proposed method of image fusion using MPCNN results in better quality of fused image with reduced root mean square error (RMSE) and computational time requirements as compared to conventional PCNN.

关键词： Neural computing techniques pulse coupled neural network image quality scene image acquisition spatial frequency neural nets best-quality image block EOL image processing computer vision and image processing techniques image fusion Optical, image and video signal processing multifocus image fusion energy of Laplacian day camera system root mean square error method Interpolation and function approximation (numerical analysis) Computational complexity computational complexity mean square error methods cameras modified PCNN

来源：评论

学校读者我要写书评

暂无评论

image restoration by regularisation in uncorrelated transform domain

引用

IEE PROCEEDINGS-vision image AND SIGNAL processing 2000年第6期147卷 587-594页

作者： Choy, SO Chan, YH Siu, WC Hong Kong Polytech Univ Dept Elect & Informat Engn Ctr Multimedia Signal Proc Hong Kong Hong Kong Peoples R China

Conventional spatially adaptive regularised image restoration schemes weight the amount of regularisation according to the spatial content of an image. The authors first separately decorrelate the signals under analysis into uncorrelated components and then weight the amount of regularisation performed to these components accordingly. The proposed approach works better than conventional schemes, especially in edge regions.

关键词： decorrelation discrete cosine transforms edge regions regularisation uncorrelated transform domain Integral transforms in numerical analysis spatial content uncorrelated components image restoration Optical, image and video signal processing Karhunen-Loeve transforms discrete Fourier transforms DFT computer vision and image processing techniques DCT KLT spatially adaptive weighting

来源：评论

学校读者我要写书评

暂无评论

Optimized deep learning model for mango grading: Hybridizing lion plus firefly algorithm

引用

IET image processing 2021年第9期15卷 1940-1956页

作者： Tripathi, Mukesh Kumar Maktedar, Dhananjay D. Guru Nanak Dev Engn Coll Comp Sci & Engn Bidar India Visvesvaraya Technol Univ Belagavi India

This paper intends to present an automated mango grading system under four stages (1) pre-processing, (2) feature extraction, (3) optimal feature selection and (4) classification. Initially, the input image is subjected to the pre-processing phase, where the reading, sizing, noise removal and segmentation process happens. Subsequently, the features are extracted from the pre-processed image. To make the system more effective, from the extracted features, the optimal features are selected using a new hybrid optimization algorithm termed the lion assisted firefly algorithm (LA-FF), which is the combination of LA and FF, respectively. Then, the optimal features are given for the classification process, where the optimized deep convolutional neural network (CNN) is deployed. As a major contribution, the configuration of CNN is fine-tuned via selecting the optimal count of convolutional layers. This obviously enhances the classification accuracy in grading system. For fine-tuning the convolutional layers in the deep CNN, the LA-FF algorithm is used so that the classifier is optimized. The grading is evaluated on the basis of healthydiseased, ripeunripe and bigmediumvery big cases with respect to type I and type II measures and the performance of the proposed grading model is compared over the other state-of-the-art models.

关键词： Optical, image and video signal processing Optimisation techniques computer vision and image processing techniques Data handling techniques Optimisation techniques Neural nets

来源：评论

学校读者我要写书评

暂无评论

Residual dense U-Net for abnormal exposure restoration from single images

引用

IET image processing 2021年第1期15卷 115-126页

作者： Que, Yue Lee, Hyo Jong Jeonbuk Natl Univ Div Comp Sci & Engn Jeonju 54896 South Korea Jeonbuk Natl Univ Ctr Adv Image & Informat Technol Jeonju South Korea

Digital imaging devices sometimes capture images with abnormal exposure because of the complex lighting conditions and limited dynamic range of luminance. In this work, a new residual dense U-Net is proposed to predict the information that has been lost in saturated image areas, to enable abnormal exposure restoration from a single image. Full advantage of the multi-level features is taken from all the convolution layers in the restoration process. Specifically, the densely connected convolutional layers are used in a contracting encoder net to extract abundant local features. The transition layer and local residual learning after each dense block is then applied to adaptively learn more effectively from prior with present local features. Further, an expanding decoder net with dense layers is used and added with skip connections to preserve low-level information and existing details. Finally, multiple global residual learning is used to adaptively extract hierarchical features and help train the network. It is shown that such a network can be trained end-to-end from abnormal exposure images and outperform the prior best method on image enhancement. Experimental results show that the proposed model can greatly enhance the dynamic range of an abnormal exposure image.

关键词： residual dense U-Net dense block saturated image areas multiple global residual learning multilevel features image enhancement image capture abundant local features extraction densely connected convolutional layers abnormal exposure image computer vision and image processing techniques local residual learning convolutional neural nets hierarchical features extraction Optical, image and video signal processing single image low-level information complex lighting conditions feature extraction decoder net transition layer image sensors encoder net learning (artificial intelligence) image sensors abnormal exposure restoration

来源：评论

学校读者我要写书评

暂无评论

Mean shift tracking through scale and occlusion

引用

IET SIGNAL processing 2012年第5期6卷 534-540页

作者： Dulai, A. Stathaki, T. Univ London Imperial Coll Sci Technol & Med Dept Elect & Elect Engn London SW7 2AZ England

This study describes a method for tracking objects through scale and occlusion. The technique presented is based on the mean shift algorithm, which provides an efficient way to track objects based on their colour characteristics. A novel and efficient method is derived for tracking through changes in the target scale, where an object of interest moves away or towards the camera and therefore appears to change size in the image plane. The method works by interleaving spatial mean shift iterations with scale iterations. It is shown that this method is considerably more efficient than other methods and possesses other advantages too. It is also demonstrated that the Bhattacharyya coefficient, a histogram similarity metric that is used in the mean shift framework, can be used to reliably detect when target occlusion occurs. In such situations, the motion of an object can be extrapolated to give an accurate estimate of its position. This is used as the basis of a technique for tracking through occlusion. Experimental results are presented on data from various scenarios.

关键词： computer vision and image processing techniques extrapolation position estimate image motion analysis colour characteristics Optical, image and video signal processing object motion occlusion spatial mean shift iteration Bhattacharyya coefficient scale iteration mean shift algorithm histogram similarity metric image colour analysis mean shift tracking Interpolation and function approximation (numerical analysis) image plane object tracking cameras camera

来源：评论

学校读者我要写书评

暂无评论

MFNet-LE: Multilevel fusion network with, Laplacian embedding for face presentation attacks detection

引用

IET image processing 2021年第14期15卷 3608-3622页

作者： Niu, Sijie Qu, Xiaofeng Chen, Junting Gao, Xizhan Wang, Tingwei Dong, Jiwen Jinan Univ Sch Informat Sci & Engn Shandong Prov Key Lab Network Based Intelligent C Jinan Peoples R China Shandong Normal Univ Sch Informat Sci & Engn Jinan Peoples R China

Face detection is playing a pivotal role for crowd counting and abnormal events detection. However, it is vulnerable to face presentation attacks by printed photos, videos, and 3D masks of real human faces. Although numerous detection techniques based on deep learning have been employed to address the problem of face presentation attacks, there are still several weaknesses in these approaches, such as high algorithm complexity and a lack of detection ability. To overcome these weaknesses, a method based on a multilevel fusion network with Laplacian embedding (MFNet-LE) for the detection of face presentation attacks is proposed. First, a shallow network that contains just three layers was developed, which makes the model faster. Then, an optimised multilevel fusion strategy was developed to combine the input with the output of all previous layers to improve the detection ability of the method. Finally, a Laplacian embedding algorithm is introduced to maintain the inter-class discrimination and penalise the intra-class distance. Under the joint supervision of Laplacian loss and softmax loss, the proposed approach can obtain more discriminative features, which enhance the accuracy of attack detection. Experiments were conducted with three public databases for face presentation attacks: CASIA FASD, Idiap Replay Attack database and MSU USSA. The results demonstrate that the MFNet-LE model can outperform the state-of-the-art methods.

关键词： Algebra Integral transforms Optical, image and video signal processing image recognition image sensors Integral transforms computer vision and image processing techniques Video signal processing Data handling techniques Spatial and pictorial databases

来源：评论

学校读者我要写书评

暂无评论

Deep spectral unmixing framework via 3D denoising convolutional autoencoder

引用

IET image processing 2021年第7期15卷 1399-1409页

作者： Jia, Peiyuan Zhang, Miao Shen, Yi Harbin Inst Technol Dept Control Sci & Engn Harbin Peoples R China

Hyperspectral unmixing is an important technique which attempts to acquire pure spectra of distinct substances (endmembers) and estimate fractional abundances from highly mixed pixels. This paper proposed a novel deep network-based framework for unmixing problem. It contains two parts: a three-dimensional convolutional autoencoder for hyperspectral denoising (denoising 3D CAE) which aims to recover data from highly noised input imagery through an unsupervised manner, and a restrictive non-negative sparse autoencoder which extracts endmembers and abundances from the scene simultaneously. The proposed denoising 3D CAE network integrates 3D operations in each layer, which allows manipulating volumetric representation of the image data directly and facilitates hierarchical exploration for latent information. Being trained with corrupted hyperspectral image data, the denoising 3D CAE network has strong capacity of capturing the principle and robust local features in spatial and spectral domains efficiently, and it shows superior performance for image recovery with high noise disturbance. Moreover, a part-based non-negative autoencoder is concatenated, and the l2,1-norm penalty is imposed for sparsity enhancement of the solution. Comparative experiments are conducted both on synthetic and real-world hyperspectral data, which demonstrate the applicability and effectiveness of the proposed unmixing framework.

关键词： Data and information acquisition, processing, storage and dissemination in geophysics Instrumentation and techniques for geophysical, hydrospheric and lower atmosphere research image and video coding image recognition Geophysical techniques and equipment computer vision and image processing techniques Geography and cartography computing Machine learning (artificial intelligence)

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：