期刊：
Computer Vision and Image Understanding,2016年150:109-125 ISSN：1077-3142
通讯作者：
Peng, Xiaojiang
作者机构：
[Peng, Xiaojiang] Hengyang Normal Univ, Coll Comp Sci & Technol, Hengyang, Peoples R China.;[Wang, Limin] Swiss Fed Inst Technol, Comp Vis Lab, Zurich, Switzerland.;[Wang, Xingxing; Qiao, Yu; Wang, Limin; Peng, Xiaojiang] Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen, Peoples R China.;[Peng, Xiaojiang] INRIA, LEAR Team, Grenoble, France.
通讯机构：
[Peng, Xiaojiang] H;[Peng, Xiaojiang] C;[Peng, Xiaojiang] I;Hengyang Normal Univ, Coll Comp Sci & Technol, Hengyang, Peoples R China.;Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen, Peoples R China.
关键词：
Action recognition;Bag of visual words;Feature encoding;Fusion methods
摘要：
A Comprehensive study on the BoVW pipeline for action recognition task.An evaluation and a generic analysis on 13 encoding methods.Intra-normalization for supervector based encoding methods.An evaluation on three fusion methods.Several good practices of the BoVW pipeline for action recognition task. Video based action recognition is one of the important and challenging problems in computer vision research. Bag of visual words model (BoVW) with local features has been very popular for a long time and obtained the state-of-the-art performance on several realistic datasets, such as the HMDB51, UCF50, and UCF101. BoVW is a general pipeline to construct a global representation from local features, which is mainly composed of five steps; (i) feature extraction, (ii) feature pre-processing, (iii) codebook generation, (iv) feature encoding, and (v) pooling and normalization. Although many efforts have been made in each step independently in different scenarios, their effects on action recognition are still unknown. Meanwhile, video data exhibits different views of visual patterns , such as static appearance and motion dynamics. Multiple descriptors are usually extracted to represent these different views. Fusing these descriptors is crucial for boosting the final performance of an action recognition system. This paper aims to provide a comprehensive study of all steps in BoVW and different fusion methods, and uncover some good practices to produce a state-of-the-art action recognition system. Specifically, we explore two kinds of local features, ten kinds of encoding methods, eight kinds of pooling and normalization strategies, and three kinds of fusion methods. We conclude that every step is crucial for contributing to the final recognition rate and improper choice in one of the steps may counteract the performance improvement of other steps. Furthermore, based on our comprehensive study, we propose a simple yet effective representation, called hybrid supervector, by exploring the complementarity of different BoVW frameworks with improved dense trajectories. Using this representation, we obtain impressive results on the three challenging datasets; HMDB51 (61.9%), UCF50 (92.3%), and UCF101 (87.9%).
摘要：
Glass bottles are widely used as containers in the food and beverage industry, especially for beer and carbonated beverages. As the key part of a glass bottle, the bottle bottom and its quality are closely related to product safety. Therefore, the bottle bottom must be inspected before the bottle is used for packaging. In this paper, an apparatus based on machine vision is designed for real-time bottle bottom inspection, and a framework for the defect detection mainly using saliency detection and template matching is presented. Following a brief description of the apparatus, our emphasis is on the image analysis. First, we locate the bottom by combining Hough circle detection with the size prior, and we divide the region of interest into three measurement regions: central panel region, annular panel region, and annular texture region. Then, a saliency detection method is proposed for finding defective areas inside the central panel region. A multiscale filtering method is adopted to search for defects in the annular panel region. For the annular texture region, we combine template matching with multiscale filtering to detect defects. Finally, the defect detection results of the three measurement regions are fused to distinguish the quality of the tested bottle bottom. The proposed defect detection framework is evaluated on bottle bottom images acquired by our designed apparatus. The experimental results demonstrate that the proposed methods achieve the best performance in comparison with many conventional methods.
作者机构：
[Wang, Dong] South China Agr Univ, Coll Math & Informat, Guangzhou, Guangdong, Peoples R China.;[Zou, Changqing] Hengyang Normal Univ, Coll Comp Sci & Technol, Hengyang, Peoples R China.;[Tan, Ping; Zou, Changqing] Simon Fraser Univ, Sch Comp Sci, Burnaby, BC, Canada.;[Li, Guiqing] South China Univ Technol, Sch Comp Sci & Engn, Guangzhou, Guangdong, Peoples R China.;[Su, Zhuo; Gao, Chengying] Sun Yat Sen Univ, Natl Engn Res Ctr Digital Life, Sch Data & Comp Sci, Guangzhou, Guangdong, Peoples R China.
会议名称：
25th Pacific Conference on Computer Graphics and Applications (Pacific Graphics)
会议时间：
OCT 16-19, 2017
会议地点：
Taipei, TAIWAN
会议主办单位：
[Wang, Dong] South China Agr Univ, Coll Math & Informat, Guangzhou, Guangdong, Peoples R China.^[Zou, Changqing] Hengyang Normal Univ, Coll Comp Sci & Technol, Hengyang, Peoples R China.^[Zou, Changqing;Tan, Ping] Simon Fraser Univ, Sch Comp Sci, Burnaby, BC, Canada.^[Li, Guiqing] South China Univ Technol, Sch Comp Sci & Engn, Guangzhou, Guangdong, Peoples R China.^[Gao, Chengying;Su, Zhuo] Sun Yat Sen Univ, Natl Engn Res Ctr Digital Life, Sch Data & Comp Sci, Guangzhou, Guangdong, Peoples R China.
摘要：
This paper presents a new two-step color transfer method which includes color mapping and detail preservation. To map source colors to target colors, which are from an image or palette, the proposed similarity-preserving color mapping algorithm uses the similarities between pixel color and dominant colors as existing algorithms and emphasizes the similarities between source image pixel colors. Detail preservation is performed by an L0 gradient-preserving algorithm. It relaxes the large gradients of the sparse pixels along color region boundaries and preserves the small gradients of pixels within color regions. The proposed method preserves source image color similarity and image details well. Extensive experiments demonstrate that the proposed approach has achieved a state-of-art visual performance.
摘要：
This paper presents a multi-modal feature fusion based framework to improve the geographic image annotation. To achieve effective representations of geographic images, the method leverages a low-to-high learning flow for both the deep and shallow modality features. It first extracts low-level features for each input image pixel, such as shallow modality features (SIFT, Color, and LBP) and deep modality features (CNNs). It then constructs mid-level features for each superpixel from low-level features. Finally it harvests high-level features from mid-level features by using deep belief networks (DBN). It uses a restricted Boltzmann machine (RBM) to mine deep correlations between high-level features from both shallow and deep modalities to achieve a final representation for geographic images. Comprehensive experiments show that this feature fusion based method achieves much better performances compared to traditional methods. (C) 2017 Published by Elsevier Ltd.
摘要：
We propose a new ultra-lightweight block cipher, QTL. The 64 bits block cipher QTL supports 64 and 128 bits keys. To solve the slow diffusion of the traditional Feistel-type structures we have used a new variant of generalized Feistel network structure in design of the QTL. Traditional Feistel-type structures change only half of block messages in an iterative round, but our structure overcomes this disadvantage and changes all block messages. Thus, our structure has the fast diffusion of the Substitution Permutation Networks (SPNs) structures, which improves the security of lightweight block cipher in Feistel-type structures. Moreover, QTL algorithm has the same encryption and decryption processes, so it will occupy less area in resource-constrained applications. Furthermore, to reduce the cost of energy consumption in hardware implementation of the cipher while maintaining security, we decide not to use a key schedule. We show that QTL offers an adequate security level against classic analyses. Our hardware implementation for the 64 and the 128 bits keys modes only require 1025.52 and 1206.52 gate equivalents, respectively. QTL achieves high security and compact implementation in hardware. QTL is one of the most competitive ultra-lightweight block ciphers, which is suitable for extremely constrained devices. (C) 2016 Elsevier B.V. All rights reserved.
摘要：
During past few years, some lightweight block ciphers have been proposed. These lightweight block ciphers take single encryption method that either uses Substitution-Permutation (SP) network structure or Feistel network structure to encrypt. In this paper, we have designed a different encryption method that takes both SP network structure and Feistel network structure to encrypt. Current SP network has a limitation that the encryption and decryption processes are dissimilar. To solve this problem, we have employed involution related properties of the nonlinear and linear components to modify SP network structure. The modified one enables the encryption and decryption program or circuit to work as the Feistel network structure. Additionally, we have implemented a MixRows in SP network structure. Then we instantiate these three novel ideas into the lightweight block cipher called SFN. We have carried out the security evaluation and the hardware and software experiments to it. The result shows that compared to other lightweight block ciphers, SFN has more advantages in terms of being immune to attacks. Also, SFN is not only compact in hardware environment but also efficient in software platforms.
期刊：
Image and Vision Computing,2014年32(9):616-628 ISSN：0262-8856
通讯作者：
Qiao, Yu
作者机构：
[Peng, Qiang; Peng, Xiaojiang] Southwest Jiaotong Univ, Chengdu, Peoples R China.;[Peng, Xiaojiang] Hengyang Normal Univ, Dept Comp Sci, Hengyang, Peoples R China.;[Qiao, Yu; Peng, Xiaojiang] Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen Key Lab CVPR, Shenzhen, Peoples R China.;[Qiao, Yu] Chinese Univ Hong Kong, Hong Kong, Hong Kong, Peoples R China.;[Qiao, Yu] 1068 Xueyuan Ave, Shenzhen, Peoples R China.
通讯机构：
[Qiao, Yu] 1;1068 Xueyuan Ave, Shenzhen, Peoples R China.
关键词：
Dense trajectory;Action recognition;3D co-occurrence descriptors;Motion boundary;Bag of Features
摘要：
Recent studies witness the success of Bag-of-Features (BoF) frameworks for video based human action recognition. The detection and description of local interest regions are two fundamental problems in BoF framework. In this paper, we propose a motion boundary based sampling strategy and spatial-temporal (3D) co-occurrence descriptors for action video representation and recognition. Our sampling strategy is partly inspired by the recent success of dense trajectory (DT) based features [Wang et al., 20131 for action recognition. Compared with DT, we densely sample spatial-temporal cuboids along a motion boundary which can greatly reduce the number of valid trajectories and preserve the discriminative power. Moreover, we develop a set of 3D co-occurrence descriptors which take account of the spatial-temporal context within local cuboids and deliver rich information for recognition. Furthermore, we decompose each 3D co-occurrence descriptor at pixel level and bin level and integrate the decomposed components with a multi-channel framework, which can improve the performance significantly. To evaluate the proposed methods, we conduct extensive experiments on three benchmarks including KTH, YouTube and HMDB51. The results show that our sampling strategy significantly reduces the computational cost of point tracking without degrading performance. Meanwhile, we achieve superior performance than the state-of-the-art methods. We report 95.6% on KTH, 87.6% on YouTube and 51.8% on HMDB51. (C) 2014 Elsevier B.V. All rights reserved.
摘要：
A chaotic model for generating multi-directional multi-scroll attractors via hyperbolic tangent function series is proposed in this paper. The dynamical mechanisms of this chaotic model are further investigated, including M-scroll, MxN-grid scroll, MxNxL-grid scroll chaotic attractors. Moreover, the dynamical behaviors of this system are theoretically analyzed and numerically simulated, such as equilibria and their stability,.Lyapunov exponents and bifurcation diagrams. This system can be widely used in data encryption and secure communication. (C) 2016 Elsevier GmbH. All rights reserved.
作者：
Zhang, Feng;Zhao, Huihuang;Ying, Wang;Liu, Qingyun;Raj, Alex Noel Joseph;...
期刊：
Intelligent Automation and Soft Computing,2020年26(6):1391-1401 ISSN：1079-8587
作者机构：
[Zhao, Huihuang; Liu, Qingyun; Ying, Wang; Zhang, Feng] Hengyang Normal Univ, Coll Comp Sci & Technol, Hengyang 421002, Peoples R China.;[Zhao, Huihuang; Liu, Qingyun; Ying, Wang] Hunan Prov Key Lab Intelligent Informat Proc & Ap, Hengyang 421002, Peoples R China.;[Raj, Alex Noel Joseph] Key Lab Digital Signal & Image Proc Guangdong, Shantou 515063, Peoples R China.;[Fu, Bin] Univ Texas Rio Grande Valley, Dept Comp Sci, Edinburg, TX USA.
关键词：
Human face sketch;generative adversarial networks;RGB image;edge optimization
摘要：
Generating an RGB image from a sketch is a challenging and interesting topic. This paper proposes a method to transform a face sketch into a color image based on generation confrontation network and edge optimization. A neural network model based on Generative Adversarial Networks for transferring sketch to RGB image is designed. The face sketch and its RGB image is taken as the training data set. The human face sketch is transformed into an RGB image by the training method of generative adversarial networks confrontation. Aiming to generate a better result especially in edge, an improved loss function based on edge optimization is proposed. The experimental results show that the clarity of the output image, the maintenance of facial features, and the color processing of the image are enhanced best by the image translation model based on the generative adversarial network. Finally, the results are compared with other existing methods. Analyzing the experimental results shows that the color face image generated by our method is closer to the target image, and has achieved a better performance in term of Structural Similarity (SSIM).
作者机构：
[Zhao, Hui-Huang] Hengyang Normal Univ, Coll Comp Sci & Technol, Hengyang, Peoples R China.;[Lai, Yu-Kun; Rosin, Paul L.] Cardiff Univ, Sch Comp Sci & Informat, Cardiff, Wales.;[Wang, Yao-Nan] Hunan Univ, Coll Elect & Informat Engn, Changsha, Peoples R China.
通讯机构：
[Zhao, Hui-Huang] H;Hengyang Normal Univ, Coll Comp Sci & Technol, Hengyang, Peoples R China.
关键词：
Deep neural networks;Style transfer;Soft mask;Semantic segmentation
摘要：
This paper presents an automatic image synthesis method to transfer the style of an example image to a content image. When standard neural style transfer approaches are used, the textures and colours in different semantic regions of the style image are often applied inappropriately to the content image, ignoring its semantic layout and ruining the transfer result. In order to reduce or avoid such effects, we propose a novel method based on automatically segmenting the objects and extracting their soft semantic masks from the style and content images, in order to preserve the structure of the content image while having the style transferred. Each soft mask of the style image represents a specific part of the style image, corresponding to the soft mask of the content image with the same semantics. Both the soft masks and source images are provided as multichannel input to an augmented deep CNN framework for style transfer which incorporates a generative Markov random field model. The results on various images show that our method outperforms the most recent techniques.
关键词：
PIλ controller;fractional order interval plant;robust stability region;value set approach;zero exclusion principle
摘要：
In this article, by using the fractional order PIλ controller, we propose a simple and effective method to compute the robust stability region for the fractional order linear time-invariant plant with interval type uncertainties in both fractional orders and relevant coefficients. The presented method is based on decomposing the fractional order interval plant into several vertex plants using the lower and upper bounds of the fractional orders and relevant coefficients and then constructing the characteristic quasi-polynomial of each vertex plant, in which the value set of vertex characteristic quasi-polynomial in the complex plane is a polygon. The D-decomposition method is used to characterise the stability boundaries of each vertex characteristic quasi-polynomial in the space of controller parameters, which can obtain the stability region by varying λ orders in the range (0, 2). These regions of each vertex plant are computed by using three stability boundaries: real root boundary (RRB), complex root boundary (CRB) and infinite root boundary (IRB). The method gives the explicit formulae corresponding to these boundaries in terms of fractional order PIλ controller parameters. Thus, the robust stability region for fractional order interval plant can be obtained by intersecting stability region of each vertex plant. The robustness of stability region is tested by the value set approach and zero exclusion principle. Our presented technique does not require sweeping over the parameters and also does not need linear programming to solve a set of inequalities. It also offers several advantages over existing results obtained in this direction. The method in this article is useful for analysing and designing the fractional order PIλ controller for the fractional order interval plant. An example is given to illustrate this method.
摘要：
As a next-generation power system, the smart grid can implement fine-grained smart metering data collection to optimize energy utilization. Smart meters face serious security challenges, such as a trusted third party or a trusted authority being attacked, which leads to the disclosure of user privacy. Blockchain provides a viable solution that can use its key technologies to solve this problem. Blockchain is a new type of decentralized protocol that does not require a trusted third party or a central authority. Therefore, this paper proposes a decentralized privacy-preserving data aggregation (DPPDA) scheme for smart grid based on blockchain. In this scheme, the leader election algorithm is used to select a smart meter in the residential area as a mining node to build a block. The node adopts Paillier cryptosystem algorithm to aggregate the user's power consumption data. Boneh-Lynn-Shacham short signature and SHA-256 function are applied to ensure the confidentiality and integrity of user data, which is convenient for billing and power regulation. The scheme protects user privacy data while achieving decentralization, without relying on TTP or CA. Security analysis shows that our scheme meets the security and privacy requirements of smart grid data aggregation. The experimental results show that this scheme is more efficient than existing competing schemes in terms of computation and communication overhead.
期刊：
International Journal of Distributed Sensor Networks,2015年2015(10):437678:1-437678:13 ISSN：1550-1477
通讯作者：
Liu, Fangju
作者机构：
[Liu, Fangju] Univ South China, Sch Comp Sci & Technol, Hengyang 421001, Hunan, Peoples R China.;[Ma, Xingpo] Xinyang Normal Univ, Sch Comp & Informat Technol, Xinyang 464000, Henan, Peoples R China.;[Liang, Junbin] Guangxi Univ, Sch Comp & Elect Informat, Nanning 530004, Guangxi, Peoples R China.;[Lin, Mugang] Hengyang Normal Univ, Dept Comp Sci, Hengyang 421008, Hunan, Peoples R China.
通讯机构：
[Liu, Fangju] U;Univ South China, Sch Comp Sci & Technol, Hengyang 421001, Hunan, Peoples R China.
摘要：
Verifiable top-k query processing in tiered sensor networks, which refers to verifying the authenticity and the completeness of top-k query results received by the network owner in tiered sensor networks, has received attention in very recent years. However, the existing solutions of this problem are only fit for static sensor network. In this paper, we try to solve the problem in a tiered mobile sensor network model, where not only static sensor nodes but also mobile sensor nodes existed. Based on the tiered mobile sensor network model, we propose a novel verifiable scheme named VTMSN for fine-grained top-k queries. The main idea of VTMSN is as follows: it maps each of the positions where sensor nodes are in a static state to a virtual node and then establishes relationships among data items of each virtual node with their score orders, which are encrypted along with the scores of the data items and the time epochs using the distinct symmetric keys kept by each sensor node and the network owner. Both theory analysis and simulation results show the efficiency and the security of VTMSN.
作者机构：
[Wen, Guilin; Zhou, Huaan; Chen, Zhong] Hunan Univ, State Key Lab Adv Design & Mfg Vehicle Body, Changsha 410082, Hunan, Peoples R China.;[Chen, Zhong] Hengyang Normal Univ, Coll Comp Sci & Technol, Hengyang 421002, Peoples R China.;[Wen, Guilin; Zhou, Huaan; Chen, Zhong] Hunan Univ, Key Lab Adv Design & Simulat Tech Special Equipme, Minist Educ, Changsha 410082, Hunan, Peoples R China.;[Chen, Junyao] Hengyang Normal Univ, Dept Phys & Elect Informat Sci, Hengyang 421002, Peoples R China.;[Chen, Junyao] Ajou Univ, Coll Informat Technol, Suwon 16499, South Korea.
通讯机构：
[Chen, Zhong] H;Hunan Univ, State Key Lab Adv Design & Mfg Vehicle Body, Changsha 410082, Hunan, Peoples R China.
关键词：
Rucklidge system;Multi-scroll attractor;Arctangent function series
摘要：
A new method for generating M × N-grid double-scroll Rucklidge chaotic attractors is presented. By designing arctangent function series to construct a nonlinear function, which replace the state variables x, y of the Rucklidge system, a new M × N-grid double-scroll chaotic system is created. The formation mechanism of this M × N-grid double-scroll chaotic model is further investigated. Moreover, some basic properties are theoretically analyzed and numerically simulated, including equilibria and their stability, Lyapunov exponents and bifurcation diagram. This system can be widely utilized in secure communication and data encryption.
摘要：
Traditional image object classification and detection algorithms and strategies cannot meet the problem of video image acquisition and processing. Deep learning deliberately simulates the hierarchical structure of human brain, and establishes the mapping from low-level signals to high-level semantics, so as to achieve hierarchical feature representation of data. Deep learning technology has powerful visual information processing ability, which has become the forefront technology and domestic and international research hotspots to deal with this challenge. In order to solve the problem of target space location in video surveillance system, time-consuming and other problems, in this paper, we propose the algorithm based on RNN-LSTM deep learning. At the same time, according to the principle of OpenGL perspective imaging and photogrammetry consistency, we use 3D scene simulation imaging technology, relying on the corresponding relationship between video images and simulation images we locate the target object. In the 3D virtual scene, we set up the virtual camera to simulate the imaging processing of the actual camera, and the pixel coordinates in the video image of the surveillance target are substituted into the simulation image, next, the spatial coordinates of the target are inverted by the inverse process of the virtual imaging. The experimental results show that the detection of target objects has high accuracy, which has an important reference value for outdoor target localization through video surveillance images.
摘要：
We propose a mesh saliency detection approach using absorbing Markov chain. Unlike most of the existing methods based on some center-surround operator, our method employs feature variance to obtain insignificant regions and considers both background and foreground cues. Firstly, we partition an input mesh into a set of segments using Ncuts algorithm and then each segment is over segmented into patches based on Zernike coefficients. Afterwards, some background patches are selected by computing feature variance within the segments. Secondly, the absorbed time of each node is calculated via absorbing Markov chain with the background patches as absorbing nodes, which gives a preliminary saliency measure. Thirdly, a refined saliency result is generated in a similar way but with foreground nodes extracted from the preliminary saliency map as absorbing nodes, which inhibits the background and efficiently enhances salient foreground regions. Finally, a Laplacian-based smoothing procedure is utilized to spread the patch saliency to each vertex. Experimental results demonstrate that our scheme performs competitively against the state-of-the-art approaches.
通讯机构：
[Li, Lang] H;Hengyang Normal Univ, Hunan Prov Key Lab Intelligent Informat Proc & Ap, Hengyang 421002, Peoples R China.;Hengyang Normal Univ, Coll Comp Sci & Technol, Hengyang 421002, Peoples R China.
关键词：
Block cipher;SPN structure;involution;lightweight cryptography;Internet of Things
摘要：
In past few years, as security ciphers in the Internet of Things (IoT), the research of lightweight block cipher has attracted tremendous attention in cryptography. The SPN structure has been widely used in the design of block cipher. However, the encryption and decryption processes of ciphers based on the SPN structure are different. We design a new SPN structure, which is perfect for lightweight block cipher. The new SPN structure makes that the encryption process is the same as decryption. Moreover, input and output data directions are the same for encryption and decryption processes. Thus, the same process can absolutely be shared in decryption and encryption both for software and hardware implementation. Further, we propose a family of involutional lightweight block cipher, called Loong, based on the proposed SPN structure and components. Rigorous analysis indicates that Loong is of high security against cryptanalysis, especially the differential attack and linear attack. As shown by our experiments and comparisons, Loong is compact in hardware environment and is suitable for the IoT.
摘要：
Information security has become increasingly important with the rapid development of mobile devices and internet. An efficient encryption system is a key to this end. In this paper, we propose an image encryption method based on the cross diffusion of two chaotic maps. We use two chaotic sequences, namely the Logistic map and the Chebyshev map, for key generation which has larger security key space than single one. Moreover, we use these two sequences for further image encryption diffusion which decreases the correlation of neighboring pixels significantly. We conduct extensive experiments on several well-known images like Lena, Baboon, Koala, etc. Experimental results show that our algorithm has the characteristics of large key space, fast, robust to statistic attack, etc.
关键词：
Time Series;Similarity/Dissimilarity Analysis;Principal Component Analysis;Fast Fourier Transformation;Protein Sequence
摘要：
In this paper, a novel method to analyze the similarity/dissimilarity of protein sequences based on Principal Component Analysis-Fast Fourier Transformation (PCA-FFT) is proposed, in which, the PCA is utilized to transform protein sequences into time series and the FFT is utilized to analyze the time series while considering them as signals. To test the effectiveness of our newly proposed method, it is applied to analyze the similarity/dissimilarity of 16 different ND5 protein sequences and 29 different spike protein sequences, respectively. Furthermore, the correlation analysis is presented for comparing with others methods, and the simulation results show that it has better performances in the aspects of computation complexity and recognition degree than some existing methods.
