通讯机构:
[Lu, H.] K;Kyushu Institute of Technology, Japan
关键词:
Point cloud compression;Three-dimensional displays;Robustness;Feature extraction;Deep learning;Training;Space exploration;Registration;point cloud data processing;PointNet;branch-and-bound
摘要:
Registration performs an individual and deciding role in multiple intelligent transport systems. The advancement of deep-learning-based methods enhances the robustness and effectiveness of the preliminary registration stage, although the algorithm will effortlessly fall into local optima when improving the ultimate exactitude. Similarly, traditional method based on optimization has a more reliable performance in terms of precision. However, its performance still counts on the quality of initialization. In order to solve the above problems, we propose a PBNet that combines a point cloud network with a global optimization method. This framework uses the feature information of objects to perform high-precision rough registration and then searches the entire 3D motion space to implement branch-and-bound and iterative nearest point methods. The evaluation results show that PBNet significantly reduce the influence of initial values on registration and has good robustness against noise and outliers.
期刊:
Fourth International Conference on Computer Science and Educational Informatization (CSEI 2022),2022年2022:65-70
作者机构:
[K. Li; Y. Deng; Q. Li; L. Miao; G. Zheng] College of Computer Science and Technology, Hengyang Normal University, Hengyang, China
摘要:
With the continuous development of China's economy, the demand for high-quality technical and skilled talent is increasing. As a base for cultivating high-skilled talent, secondary vocational education plays an irreplaceable role in China's economic development. Therefore, secondary vocational schools must adopt more effective education and teaching methods to cultivate students' practical skills and improve their teaching quality. This paper analyzes the teaching effect and explores the teaching reform of secondary vocational schools by carrying out PBL (project-based learning) teaching in the graphic design course of computer specialty in secondary vocational schools.
摘要:
In recent years, chaotic image encryption algorithms with key and plaintext association have been developed, which are essentially similar to a one-time pad at a time because each encryption requires the transmission of the key. However, some existing schemes cannot uniquely map the seed key to the initial value of the chaotic system, which leads to the reduction of the key space of the encryption system. In addition, some schemes use the same key to encrypt the same image, which does not conform to the one-time pad strategy. This paper solves these problems from two aspects. On the one hand, random pixels are inserted into a plain image and then a hash value is generated using SHA-256. Different seed keys can be obtained even if the same image is encrypted. On the other hand, the Sequential Expansion Algorithm (SEA) and Feedback Iterative Piece-Wise Linear Chaotic Mapping (FI-PWLCM) are proposed to realize the one-to-one correspondence between the seed key and the encrypted key stream. SEA can quickly generate seed key sensitive and random sequences. FI-PWLCM achieves one-to-one correspondence with the seed key through feedback iteration with more control parameters. The mapping not only has the rapidity of PWLCM, but also can produce more complex chaotic sequences. Besides, this paper proposes a Segmented Coordinate Descent (SCD) method for histogram statistical optimization of images to improve the ability of cryptosystems against statistical attacks. Experiments and security analysis show that the algorithm can resist chosen-plaintext (chosen-ciphertext) attacks, brute force attacks, statistical attacks and so on. Compared with most current algorithms, it achieves the best performance in the statistical properties of histogram and entropy.
期刊:
Journal of Electronic Imaging,2022年31(5) ISSN:1017-9909
通讯作者:
Ge Jiao
作者机构:
[Li, Chen; Jiao, Ge] Hengyang Normal Univ, Coll Comp Sci & Technol, Hengyang, Peoples R China.;[Jiao, Ge] Hunan Prov Key Lab Intelligent Informat Proc & A, Hengyang, Peoples R China.
通讯机构:
[Ge Jiao] H;Hengyang Normal Univ.<&wdkj&>Provincial Key Lab. of Intelligent Information Processing and Application
关键词:
Transformers;Performance modeling;Data modeling;Visual process modeling;Computer programming;Camouflage;Convolution;Feature extraction;Visualization;Transmission electron microscopy
摘要:
Camouflaged object detection (COD) is a new computer vision challenge for locating and identifying camouflaged objects in complex situations. Camouflaged objects are more similar to their surroundings than conventional objects, and their appearance in terms of size and shape is also considerably different, making accurate identification of the COD tasks difficult. As a result, we propose an enhanced identification network (EINet) to strengthen the COD task's identification capabilities. First, the pyramid vision transformer is used as an encoder for extracting more robust multiscale features. Second, the multiple texture refinement modules are exploited to refine the multiscale features. Third, an improved neighbor and hop connection decoder is designed to produce a coarse estimation map for guiding the detailed identification of camouflaged objects backward. Finally, numerous new reverse criss-cross block attention modules that gradually recognize fine-grained features at various scales is designed to allow for the accurate recognition of camouflaged objects. Extensive experiments have been conducted on four benchmarked datasets of camouflaged objects. The results of the experiments reveal that our EINet is a powerful COD model that outperforms current state-of-the-art models. (c) 2022 SPIE and IS&T
通讯机构:
[Li, L ] H;Hengyang Normal Univ, Coll Comp Sci & Technol, Hengyang 421002, Peoples R China.;Hengyang Normal Univ, Hunan Prov Key Lab Intelligent Informat Proc & Ap, Hengyang 421002, Peoples R China.
关键词:
Differential power analysis;Hamming weight;Ghost peaks;AES
摘要:
Differential power analysis (DPA) is disturbed by ghost peaks. There is a phenomenon that the mean absolute difference (MAD) value of the wrong key is higher than the correct key. We propose a compressed key guessing space (CKGS) scheme to solve this problem and analyze the AES algorithm. The DPA based on this scheme is named CKGS-DPA. Unlike traditional DPA, the CKGS-DPA uses two power leakage points for a combined attack. The first power leakage point is used to determine the key candidate interval, and the second is used for the final attack. First, we study the law of MAD values distribution when the attack point is AddRoundKey and explain why this point is not suitable for DPA. According to this law, we modify the selection function to change the distribution of MAD values. Then a key-related value screening algorithm is proposed to obtain key information. Finally, we construct two key candidate intervals of size 16 and reduce the key guessing space of the SubBytes attack from 256 to 32. Simulation experimental results show that CKGS-DPA reduces the power traces demand by 25% compared with DPA. Experiments performed on the ASCAD dataset show that CKGS-DPA reduces the power traces demand by at least 41% compared with DPA.
通讯机构:
[Xiaoman Liang] C;College of Computer Science and Technology, Hengyang Normal University, Hengyang 421002, China<&wdkj&>Hunan Provincial Key Laboratory of Intelligent Information Processing and Application, Hengyang 421002, China
关键词:
Face key point detection;Facial segmentation;Peking Opera;Style transfer
通讯机构:
[Yaqi Sun] C;College of Computer Science and Technology, Hengyang Normal University, Hengyang, 421002, China<&wdkj&>Hunan Provincial Key Laboratory of Intelligent Information Processing and Application, Hengyang, 421002, China
通讯机构:
[Lang Li] C;College of Computer Science and Technology, Hengyang Normal University, Hengyang, 421002, China<&wdkj&>Hunan Provincial Key Laboratory of Intelligent Information Processing and Application, Hengyang Normal University, Hengyang, 421002, China
作者机构:
[Chen, Wenhui] Hengyang Normal Univ, Coll Comp Sci & Technol, Hengyang 421002, Peoples R China.;[Wu, Guanchen] Guizhou Commun Polytech, Dept Informat Engn, Guiyang 551400, Peoples R China.;[Jung, Hoekyung] Paichai Univ, Dept Comp Sci & Engn, 155-40 Baejae Ro, Daejeon 35345, South Korea.
通讯机构:
[Hoekyung Jung] D;Department of Computer Science and Engineering, Paichai University, 155-40 Baejae-ro, Daejeon 35345, Korea<&wdkj&>Author to whom correspondence should be addressed.
关键词:
deep learning;you only look once (YOLO);number of people detection;distributed probability-adjusted confidence (DPAC)
摘要:
Compared to traditional detection methods, image-based flow statistics that determine the number of people in a space are contactless, non-perceptual, and high-speed statistical methods that have broad application prospects and potential economic value in business, education, transportation, and other fields. In this paper, we propose that the distributed probability-adjusted confidence (DPAC) function can optimize the reliability of model prediction according to the actual situation. That is, the reliability can be adjusted using the distribution characteristics of the target in the field of view, and a target can be determined with a confidence level that is greater than 0.5 and more accurately. DPAC can assign different target occurrence probability weights to different regions according to target distribution. Adding the DPAC function to a YOLOv4 network model on the basis of having the target confidence of the YOLOv4 network can reduce or improve confidence according to the target distribution and can then output the final confidence level. Using YOLOv4 + DPAC on the brainwash dataset can improve precision by 0.05% compared to the YOLOv4 model when the target confidence threshold is equal to 0.5; it can improve the recall of the model by 0.12% and the AP of the model by 0.12%. This paper also proposes that the distribution in the DPAC function be obtained based on unsupervised learning and verifies its effectiveness.
作者机构:
[Wu, Guanchen] Dept Informat Engn, Guizhou Commun Polytech, Guiyang 551400, Peoples R China.;[Chen, Wenhui] Hengyang Normal Univ, Coll Comp Sci & Technol, Hengyang 421002, Peoples R China.;[Jung, Hoekyung] Paichai Univ, Dept Comp Sci & Engn, 155-40 Baejae Ro, Daejeon 35345, Peoples R China.
通讯机构:
[Hoekyung Jung] D;Department of Computer Science and Engineering, Paichai University, 155-40 Baejae-ro, Daejeon 35345, Korea<&wdkj&>Author to whom correspondence should be addressed.
关键词:
deep learning;recurrent neural network;spatiotemporal prediction;precipitation nowcasting
摘要:
Precipitation nowcasting predicts the future rainfall intensity in local areas in a brief time that impacts directly on human life. In this paper, we express the precipitation nowcasting as a spatiotemporal sequence prediction problem. Predictive learning for a spatiotemporal sequence aims to construct a model of natural spatiotemporal processes to predict the future frames based on historical frames. The spatiotemporal process is an abstraction of some of the spatial things in nature that change with time, and they usually do not change very dramatically. To simplify the model and facilitate the training, we considered that the spatiotemporal process satisfies the generalized Markov properties. The natural spatiotemporal processes are nonlinear and non-stationary in many aspects. The processes are not satisfied with the first-order Markov properties when making predictions, such as the nonlinear movement, expansion, dissipation, and intensity enhancement of echoes. To describe such complex spatiotemporal variations, higher-order Markov models need to be used for the modeling. However, many of the previous models for spatiotemporal prediction constructed were based on first-order Markov properties, losing information on the higher-order variations. Thus, we propose a recurrent neural network which satisfies the multi-order Markov properties to create more accurate spatiotemporal predictions. In this network, the core component is the memory cell structure of the gated attention mechanism, which combines the current input information, extracts the historical state that best matches the existing input from the historical multi-period memory information, and then predicts the future. Through this principle of the gated attention, we could extract the historical state information that is richer and deeper to predict the future and more accurately describe the changing characteristics of motion. The experiments show that our GARNN network captures the spatiotemporal characteristics better and obtains excellent results in the precipitation forecasting with radar echoes.
通讯机构:
[Lang Li] C;College of Computer Science and Technology, Hengyang Normal University, Hengyang, China<&wdkj&>Hunan Provincial Key Laboratory of Intelligent Information Processing and Application, Hengyang Normal University, Hengyang, China
关键词:
Side channel analysis;Deep learning;Signal processing;Random convolution kernel
摘要:
Many researches transform the traditional side channel analysis (SCA) into a classification problem. However, there are some inconsistencies in the evaluation metrics and excessive training overhead. A regression model theory is proposed from power traces to intermediate values in this work. It leads us to design a random convolution model that can closely fit the timing features of power consumption and transform them directly to intermediate values. In training phase, the raw power traces on ASCAD is processed to the dataset with six subsets, which is similar to the form of UCR sets. The determination coefficient (
$$R^2$$
), time and correlation coefficient are used in training and evaluation. The experiments show that the model has a faster training speed and better attack effect. Our model can address two problems in combining deep learning with SCA. Further, the model can quickly adapt to new cryptographic algorithms by greatly reducing the training time.