International Journal of Pattern Recognition and Artificial Intelligence

Simultaneous extraction of spectral and spatial features and their fusion is currently a popular solution in hyperspectral image (HSI) classification. It has achieved satisfactory results in some research. Because the scales of objects are often different in HSI, it is necessary to extract multi-scale features. However, this aspect was not taken into account in many spectral-spatial feature fusion methods. This causes the model to be unable to get sufficient features on scales with a large difference range. The model (MCMN: Multi-Content Merging Network) proposed in this paper designs a multi-branch fusion structure to extract multi-scale spatial features by using multiple dilated convolution kernels. Considering the interference of the surrounding heterogeneous objects, the useful information from different directions is also fused together to realize the merging of multiple regional features. MCMN introduces a convolution block attention mechanism, which fully extracts attention features in both spatial and spectral directions, so that the network can focus on more useful parts, which can effectively improve the performance of the model. In addition, since the number of objects in each class is often discrepant, it will have some impact on the training process. We apply the focal loss function to eliminate the negative factor. The experimental results of MCMN on three data sets have a breakthrough compared with the other comparison models, which highlights the role of MCMN structure.

As an important identification certificate for citizens, ID card plays a significant role in daily life and its information has found its way into almost every aspect. However, traditional ways tend to adopt manual input, which is not only time-consuming and labor-intensive, but also expensive as well as inaccuracy. In this paper, we proposed a novel algorithm to locate and recognize ID card information, in which several fresh strategies are presented to rectify image, detect boundary, and locate information, respectively. To solve the problem of image rotating, the image is rectified by searching the best rotating angle that can lead to the maximum corner point projection peak. Meanwhile, the boundary of ID card is detected by finding the best lines in the predicted boundary area based on the deviation between the predicted boundary and the detected boundary, and the position of information is located by incorporating the prior information and the location relation between the key information. Experimental results show that the proposed algorithm can achieve a state-of-the-art effect for recognizing ID card’s information.

Traditional machine learning requires users to have a strong ability to control features and distance calculation formulas, especially in the use of support vector machine SVM and nearest neighbor KNN. Traditional machine learning uses PCA in feature extraction will actually lead to Information is lost. In order to solve the problem of low optical film damage detection rate of traditional methods, a new method is proposed in this paper based on a convolutional neural network instead of traditional machine learning to classify CCD images with different damage degrees of SiO₂ film and K9 glass. First, film images are collected by online CCD, and the proposed algorithm is designed to extract the image characteristic parameters of the film microscopic images, filter denoising, and run binarization to analyze film images. Second, gray values of images are extracted and classified by unsupervised learning. Finally, the film microscopic images under the microscope are analyzed. The experimental results show that the defect positions on the images can be detected after the images are detected and processed by a convolution neural network, binarization, and connected domains. The defective parts can be intercepted from the images, and the data related is saved for damage type determination. The average classification rate is over 99%, which is better than the traditional method by 9.1%. Therefore, it has a high application value.

Considering that the extended targets tracking problem of the measurement is a glint noise with an unknown inverse covariance, a new algorithm from a multi-extended target tracking based on the Variational Bayesian Expectation Maximization (VBEM) is proposed. To improve the variational Bayesian technique, a modeled Student’s t distribution is proposed based on multiple Gaussian mixture terms in order to replace the probability hypothesis density (PHD) intensity. The extended target was modeled with a Student’s t distribution with the glint noise, using Gauss-Gamma distribution combining the variational Bayesian technique to obtain an approximate distribution and applying the expectation-maximization algorithm for iterative estimation. The two experiments are compared and analyzed with the VBEM-CPHD algorithm and the traditional extended target tracking algorithm. Experiment 1 estimated the trajectory of the target, compared algorithms of VBEM-CPHD and GM-CPHD with OSPA distance, varied glint noise with the three different measurement noise standard deviations. Experiment 2 completed the examination of the tracking performance and stability of the proposed method and performed to compare the VBEM-CPHD algorithm proposed with the VB-based GM-CPHD (GM-VBCPHD) algorithm under an unknown measurement noise covariance. The experimental results indicate that the algorithm of VBEM-CPHD has high tracking accuracy, good adaptability, and a strong antijamming ability for multiple extended targets under glint noise conditions.

In this paper, we propose a multi-modal sparse tracking by jointing timing and modal consistency to locate the target location with the similarity of multiple local appearances. First, we propose an alignable patching strategy for red-green-blue (RGB) color mode and thermal infrared mode to adapt to the local changes of the target. Second, we propose a consistency expression of the corresponding aligned patches between the modes and the correlation of the gaussian mapping within mode to reconstruct the target judgment likelihood function. Finally, we propose an updating scenario based on timing correlation and mode sparsity to fit with the target changes. According to the experimental results, significant improvement in terms of tracking accuracy can be achieved on average compared with the state-of-the-art algorithms. The source code of our algorithm is available on https://github.com/Liincq/tracker.

“Road detection is said to be a major research area in remote sensing analysis and it is usually complex due to the data complexities as it gets varied in appearance with minor inter-class and huge intra-class variations that often cause errors and gaps in the extraction of the road”. Moreover, the majority of supervised learning techniques endure from the high price of manual annotation or inadequate training data. Thereby, this paper intends to introduce a new model for road detection. This work exploits a siamesed fully convolutional network (named as “s-FCN-loc”) based on VGG-net architecture that considers semantic contour, RGB channel and location prior for segmenting road regions precisely. As a major contribution, super pixel segmentation was carried out, where the RGB images are given as input to the FCN network and the road regions of images are set as a target. Further, the segmented outputs are fused using AND operation to attain the final segmented output that detects the road regions accurately. To make the detection more accurate, the convolutional layers of FCN are optimally chosen by a new improved model termed as distance oriented sea lion algorithm (DSLnO) model. The presented DSLnO + FCN model has achieved a minimal value of negative measures and accuracy is 8.2% higher than traditional methods. Finally, the presented method is evaluated on the KITTI road detection dataset, and achieves a better result. The analysis was done with respect to positive measures and negative measures.

Aiming at the defects of pronunciation errors and limited collection of pronunciation data resources in traditional artificial neural networks, an English pronunciation judgment and detection model based on deep learning neural networks data stream fusion is proposed. Taking Chinese English pronunciation as the research object, three groups of phonetic data were selected as experimental auxiliary data, based on the convolutional neural network, through the preset reset of the pronunciation detection system of the model, the sampling and recognition extraction of the speech system, the wrong speech detection and the feature analysis of the multi-level data stream tandem, the experiments are carried out with CU-CHLOE language learning database, WSJ1 database and 863 Mandarin database. The experimental results show that the recognition accuracy of this model is higher than that of the traditional neural network model, the accuracy of error type diagnosis is significantly improved, and its noise robustness is the best.

Edge detection is one of the most fundamental fields in computer vision. With the rapid development of the combination of Convolutional Neural Network and Multi-Scale Representation of image, significant progress has been made in this field. However, most of them have a huge size, which makes it hard to apply in reality, and a huge number of parameters may lead to waste of computing resources. In this paper, we focus on qualitative analysis of the role of each part in the network, and propose a modified light-weight architecture based on our result and the study of former works. Our new architecture is composed of residual-blocks, max-pooling layers and batch normalization layers. Compared with the previous models, the new architecture performs better in memory, convergence and computation efficiency with similar model size. Moreover, the new architecture can achieve better accuracy with smaller model size. When evaluating our model on the well-known BSDS500 benchmark, we achieve ODS F-measure of 0.769 with parameters less than 0.3M, which shows a better property than the state-of-the-art result 0.766 at this level.

The application of deep learning in time-series prediction has developed gradually. In this paper, we propose a deep generative network model for feature extraction of multivariate time series, namely, mutual information variational autoencoders (MI-VAE). In the architecture of the proposed model, we use the latent space of VAE for feature learning, which can extract the essential features of multivariate time-series data effectively. The latent space employed directly as a feature extractor can avoid poor interpretability of model. In addition, we introduce a mutual information term into the loss function, which improves the expression capability and accuracy of model. The proposed model, combining the merits of VAE and mutual information, extracts features for multivariate time-series data from a new perspective. The Lorenz system and Beijing air quality time series are used to test performance of the proposed model and comparative models. Results show that the proposed model is superior to other similar models in terms of accuracy and expression capability of latent space.

Aiming at the problem of large location errors of traditional ranging-free algorithms in Wireless Sensor Network (WSN), a novel node location algorithm based on proximity-distance mapping (PDM) and Jaya optimization was proposed. In this algorithm, proximity and Euclidean distance are extracted from the relationship of anchor nodes to construct a mapping matrix by using the idea of PDM. It is calculated by using the mapping matrix that the estimated distance from the unknown node to the anchor node can be used for the subsequent calculations. After the estimated distance is obtained, the Jaya optimization algorithm is imported to calculate the location of the unknown one. To accelerate the convergence and enhance the accuracy of the algorithm, the idea of a boundary box is used to limit the initial feasible region of unknown nodes. The experiment results show that the PDM–Jaya algorithm has better positioning accuracy than the original PDM in the same condition.

Traditional GPS positioning technology cannot be used in indoor space. With the development of the new positioning technology and the Internet of things, the indoor mobile object positioning and navigation model have been the focus of the relevant research institutions at home and abroad. Based on this, indoor positioning technology was studied starting from Wi-Fi, RFID, and iBeacon technology in this paper. However, the accuracy of indoor positioning and navigation needs to be further improved. This paper presents a semantic space model based on artificial intelligence technology, through semantic pattern matching, semantic concept extension, semantic reasoning and semantic mapping, and interior semantic localization is realized. The indoor semantic network and indoor grid navigation model are constructed, and the indoor semantic path is modeled from time, location, user, and congestion. At the same time, the improved Term Frequency-Inverse Document Frequency is combined with the Hidden Markov Model to improve the accuracy of matching the stay area with the most likely location to visit and improve the accuracy of semantic annotation. It was found that the research on the indoor positioning and navigation model based on the semantic grid can realize the uniform expression of the complex spatial semantics of the theme, geometry, connectivity, and distance, which can promote the development of indoor positioning and navigation.

Visual retrieval has been a significant technology in the computer vision task. Visual feature descriptors are the key to the visual retrieval. The famous local feature descriptor is called the Scale Invariant Feature Transform (SIFT), which can keep invariant mapping for the scale, rotate and simulate images. To utilize effectively the SIFT feature descriptor for visual matching on different hardware platforms, this paper proposes an accelerated SIFT algorithm based on the SIFT feature computing principle of the general multi-core platform. First, our multi-core task allocation method introduces the WFM theory into task assignment for each core to improve the core computing resource utilization for high-efficient parallel computing. Then, to improve the efficiency of picture matching, we introduce global geometric constraints condition to optimal picture matching for the multi-core parallelization approach. Experimental results show that the proposed approach can save on average 87.31% on the Intel X86 platform, compared to the single-core time. Also, our approach can save on average 33.79% on the Raspberry Pi platform, compared to the single-core time.

Peking opera is one of the national cultural heritages in China. However, it is difficult for people to learn the gestures in Peking opera performance, which limits the spread of this traditional culture. To address this issue, we propose a Peking opera gesture training system using infrared sensors. Specifically, we build a character avatar for demonstrating the gestures in Peking opera in the proposed system. Based on the data collected by infrared sensors, a method for calculating gesture similarity is proposed and is applied for the training of Peking opera gestures, which allows natural interactions and provides interactive feedback for user gestures. We conducted multiple experiments to verify the feasibility and effectiveness of the training system. The experimental results showed that the proposed system can overcome the difficulties in the traditional learning process of Peking opera gestures, which helps users to achieve the goal of learning standard Peking opera gestures. The proposed training system greatly eases the learning of Peking opera gestures, adding vitality into the culture of traditional Peking opera.

While UAV ad hoc networks have made significant progress, implementing it in most of real-application scenarios is challenging due to data explosion. Instead of only ad hoc mode, this work simultaneously considers non-orthogonal multiple access technique (NOMA) and ad hoc mode to handle the problem. We further propose an effective framework to seamlessly integrate these two techniques, namely Multi-UAV heterogeneous networks. Specifically, we formulate the framework as a mixed integer nonlinear programming, in which original problem can be decomposed into two sub-problems, e.g., access mode selection for UAV to UAV mode (U2U) and UAV to Ground Base mode (U2G), and transmission rate optimization. For the access mode selection, to reduce the computational complexity at each UAV, a candidate set is constructed based on the connection time and link quality. After that, the component in candidate set that maximizes the objective function is selected as the access point. Due to the different communication techniques in U2U mode and U2G mode, we can obtain the optimal rate for each UAV by using the NOMA technique in U2G mode and channel prediction method with local information in U2U mode, respectively. For the transmission rate optimization, an effective algorithm is proposed for U2G mode and U2U mode, which considers the effects of the network connectivity and link quality on the optimization performance. Simulation results show that our method can reduce the outage rate and improve the network throughput effectively.