Recognition of High Difference Features in Urban Planning Images Based on Morphological FilteringRead the full article
Advances in Mathematical Physics publishes papers that seek to understand mathematical basis of physical phenomena, and solve problems in physics via mathematical approaches.
Chief Editor, Prof Di Matteo (Department of Mathematics, King’s College London), engages in world-leading multidisciplinary and data-driven research focussed on the analysis of complex data from the perspective of a statistical physicist.
Latest ArticlesMore articles
Lie Symmetry Analysis, Exact Solutions, and Conservation Laws of Variable-Coefficients Boiti-Leon-Pempinelli Equation
In this article, we study the generalized ()-dimensional variable-coefficients Boiti-Leon-Pempinelli (vcBLP) equation. Using Lie’s invariance infinitesimal criterion, equivalence transformations and differential invariants are derived. Applying differential invariants to construct an explicit transformation that makes vcBLP transform to the constant coefficient form, then transform to the well-known Burgers equation. The infinitesimal generators of vcBLP are obtained using the Lie group method; then, the optimal system of one-dimensional subalgebras is determined. According to the optimal system, the ()-dimensional reduced partial differential equations (PDEs) are obtained by similarity reductions. Through -expansion method leads to exact solutions of vcBLP and plots the corresponding 3-dimensional figures. Subsequently, the conservation laws of vcBLP are determined using the multiplier method.
A Poisson Equation-Based Method for 3D Reconstruction of Animated Images
3D reconstruction techniques for animated images and animation techniques for faces are important research in computer graphics-related fields. Traditional 3D reconstruction techniques for animated images mainly rely on expensive 3D scanning equipment and a lot of time-consuming postprocessing manually and require the scanned animated subject to remain in a fixed pose for a considerable period. In recent years, the development of large-scale computing power of computer-related hardware, especially distributed computing, has made it possible to come up with a real-time and efficient solution. In this paper, we propose a 3D reconstruction method for multivisual animated images based on Poisson’s equation theory. The calibration theory is used to calibrate the multivisual animated images, obtain the internal and external parameters of the camera calibration module, extract the feature points from the animated images of each viewpoint by using the corner point detection operator, then match and correct the extracted feature points by using the least square median method, and complete the 3D reconstruction of the multivisual animated images. The experimental results show that the proposed method can obtain the 3D reconstruction results of multivisual animation images quickly and accurately and has certain real-time and reliability.
Commodity Price Recognition and Simulation of Image Recognition Technology Based on the Nonlinear Dimensionality Reduction Method
Dimensionality reduction of images with high-dimensional nonlinear structure is the key to improving the recognition rate. Although some traditional algorithms have achieved some results in the process of dimensionality reduction, they also expose their respective defects. In order to achieve the ideal effect of high-dimensional nonlinear image recognition, based on the analysis of the traditional dimensionality reduction algorithm and refining its advantages, an image recognition technology based on the nonlinear dimensionality reduction method is proposed. As an effective nonlinear feature extraction method, the nonlinear dimensionality reduction method can find the nonlinear structure of datasets and maintain the intrinsic structure of data. Applying the nonlinear dimensionality reduction method to image recognition is to divide the input image into blocks, take it as a dataset in high-dimensional space, reduce the dimension of its structure, and obtain the low-dimensional expression vector of its eigenstructure so that the problem of image recognition can be carried out in a lower dimension. Thus, the computational complexity can be reduced, the recognition accuracy can be improved, and it is convenient for further processing such as image recognition and search. The defects of traditional algorithms are solved, and the commodity price recognition and simulation experiments are carried out, which verifies the feasibility of image recognition technology based on the nonlinear dimensionality reduction method in commodity price recognition.
A Massive Image Recognition Algorithm Based on Attribute Modelling and Knowledge Acquisition
In this paper, an in-depth study and analysis of attribute modelling and knowledge acquisition of massive images are conducted using image recognition. For the complexity of association relationships between attributes of incomplete data, a single-output subnetwork modelling method for incomplete data is proposed to build a neural network model with each missing attribute as output alone and other attributes as input in turn, and the network structure can deeply portray the association relationships between each attribute and other attributes. To address the problem of incomplete model inputs due to the presence of missing values, we propose to treat and describe the missing values as system-level variables and realize the alternate update of network parameters and dynamic filling of missing values through iterative learning among subnets. The method can effectively utilize the information of all the present attribute values in incomplete data, and the obtained subnetwork population model is a fit to the attribute association relationships implied by all the present attribute values in incomplete data. The strengths and weaknesses of existing image semantic modelling algorithms are analysed. To reduce the workload of manually labelling data, this paper proposes the use of a streaming learning algorithm to automatically pass image-level semantic labels to pixel regions of an image, where the algorithm does not need to rely on external detectors and a priori knowledge of the dataset. Then, an efficient deep neural network mapping algorithm is designed and implemented for the microprocessing architecture and software programming framework of this edge processor, and a layout scheme is proposed to place the input feature maps outside the kernel DDR and the reordered convolutional kernel matrices inside the kernel storage body and to design corresponding efficient vectorization algorithms for the multidimensional matrix convolution computation, multidimensional pooling computation, local linear normalization, etc., which exist in the deep convolutional neural network model. The efficient vectorized mapping scheme is designed for the multidimensional matrix convolution computation, multidimensional pooling computation, local linear normalization, etc. in the deep convolutional neural network model so that the utilization of MAC components in the core loop can reach 100%.
Multiperson Target Dynamic Tracking Method for Athlete Training Based on Wireless Body Area Network
Aiming at the problems of large tracking error and long tracking time in traditional multiperson target dynamic tracking methods, a new method based on wireless body area network for athlete training multiperson target dynamic tracking is proposed. First, the microinertial sensor in the wireless body area network is used to collect the multiperson image data of the athlete training, and the sparse representation is performed after processing, which improves the reliability of the data and reduces the tracking error. Secondly, the multiperson target dynamic tracking method based on the adaptive search box is used, combined with target isolation and occlusion detection, to judge the athlete’s training target. Finally, the nearest neighbor algorithm is used to construct an adaptive search box to achieve dynamic tracking of multiple targets. Experimental results show that this method can accurately measure the similarity of target features, with small tracking error and short tracking time. The minimum tracking error is only 0.11 frame.
Noise Data Removal and Image Restoration Based on Partial Differential Equation in Sports Image Recognition Technology
With the rapid development of image processing technology, the application range of image recognition technology is becoming more and more extensive. Processing, analyzing, and repairing graphics and images through computer and big data technology are the main methods to obtain image data and repair image data in complex environment. Facing the low quality of image information in the process of sports, this paper proposes to remove the noise data and repair the image based on the partial differential equation system in image recognition technology. Firstly, image recognition technology is used to track and obtain the image information in the process of sports, and the fourth-order partial differential equation is used to optimize and process the image. Finally, aiming at the problem of low image quality and blur in the transmission process, denoising is carried out, and image restoration is studied by using the adaptive diffusion function in partial differential equation. The results show that the research content of this paper greatly improves the problems of blurred image and poor quality in the process of sports and realizes the function of automatically tracking the target of sports image. In the image restoration link, it can achieve the standard repair effect and reduce the repair time. The research content of this paper is effective and applicable to image processing and restoration.