Scale Adaptive Target Tracking Based on Kernel Correlation Filter and Residual Network

Data-driven rolling-bearing fault diagnosis methods are mostly based on deep-learning models, and their multilayer nonlinear mapping capability can improve the accuracy of intelligent fault diagnosis. However, problems such as gradient disappearance occur as the number of network layers increases. Moreover, directly taking the raw vibration signals of rolling bearings as the network input results in incomplete feature extraction. In order to efficiently represent the state characteristics of vibration signals in image form and improve the feature learning capability of the network, this paper proposes fault diagnosis model MTF-ResNet based on a Markov transition field and deep residual network. First, the data of raw vibration signals are augmented by using a sliding window. Then, vibration signal samples are converted into two-dimensional images by MTF, which retains the time dependence and frequency structure of time-series signals, and a deep residual neural network is established to perform feature extraction, and identify the severity and location of the bearing faults through image classification. Lastly, experiments were conducted on a bearing dataset to verify the effectiveness and superiority of the MTF-ResNet model. Features learned by the model are visualized by t-SNE, and experimental results indicate that MTF-ResNet showed better average accuracy compared with several widely used diagnostic methods.

MSST-ResNet: Deep multi-scale spatiotemporal features for robust visual object tracking

The target tracking technology in the UAV autonomous landing process is studied. Based on the analysis of the occlusion, background change, and variable scale problems in the target tracking process, a scale adaptive method for UAV target tracking based on KCF (Kernelized Correlation Filter) algorithm is proposed. The original KCF target tracking framework is adopted to achieve the target position prediction function. Secondly, to address the variable scale problem of moving targets and the target loss problem caused by scale changes, the scale filter of the DSST target tracking algorithm is used. The algorithm is for estimating the scale of moving targets and generating a small-scale filter estimate to improve the tracking efficiency of the UAV for moving targets and reduce the target loss rate. The final test on the OTB dataset showed a 4% improvement in variable scale accuracy and a 2.9% improvement in variable scale success rate. A Gazebo 3D environment scene was set up under the Linux system, and UAV autonomous landing simulation experiments were conducted to verify the improved algorithm’s real-time effectiveness in the UAV autonomous landing application. The simulation results show that the improved KCF target tracking algorithm has real-time performance in the UAV autonomous landing trajectory tracking process.

Robust scale estimation and occlusion handling are two challenging problems in visual target tracking. Most existing methods do not perform well with complex image sequences, especially those with scale changes and partial occlusion. In this paper, a real-time RGB-D object tracker is proposed to deal with occlusion and scale changes in various scenes. Our approach is more accurate than most existing algorithms, while the computational complexity does not increase greatly. We build our approach based on the kernelized correlation filter (KCF), which utilizes the property of a circulant matrix and kernel to achieve fast target tracking. Our approach makes use of the spatial continuity of the depth information to achieve accurate scale estimation, and it performs better than an exhaustive search. In addition, we propose a method for model updating that combines the different parts of the target to deal with occlusion. We evaluate our method using the Princeton Data, which is a public RGB-D dataset for object tracking. Experiments show that the proposed approach significantly improves the performance compared with the baseline. Finally, we provide both quantitative and qualitative comparisons between our tracker and current state-of-the-art trackers. The proposed approach is shown to be superior to most trackers, while operating at a high frame rate.

Aiming at the problem that the difference in fault data distribution caused by the variation of gear and bearing conditions during the operation of rotating machinery affects the accuracy of fault diagnosis, a multi-condition fault diagnosis approach based on whale optimization algorithm (WOA), variational mode decomposition (VMD), and deep residual shrinkage network (DRSN) is proposed. Firstly, WOA is employed to optimize the parameters of the decomposition level and the penalty factor value in VMD, enhancing its noise resistance. Subsequently, VMD processing yields several modal components, each characterized by a permutation entropy feature vector, ensuring optimal feature extraction. DRSN is then utilized, employing an attention mechanism to adaptively set soft threshold functions, thereby improving gear fault diagnosis accuracy under multiple operating conditions. Finally, the proposed method’s performance was validated through the collection of gear running signals under various conditions, and the fault diagnosis accuracy was used as the model evaluation index to conduct comparative experiments and ablation experiments. The experimental results indicate that the WOA-VMD feature extraction and DRSN fault diagnosis techniques outperform traditional methods in multi-condition gear fault diagnosis. This study provides a new effective approach for multi-condition diagnosis of rotating machinery.

Various microfossils from the early Cambrian provide crucial clues for understanding the Cambrian explosion and the origin of animal phyla. However, specimens with important anatomical structures are extremely rare and the efficiency of retrieving such fossils by traditional manual selection under a microscope is quite low. Such a contradiction has hindered breakthroughs in micropaleontology for a long time. Here, we propose a solution for identifying specific taxa of Cambrian microfossils using only a few available specimens by transferring a model pre-trained on natural image datasets to the field of paleontological artificial intelligence. The method employs a 34-layer deep residual neural network as the underlying framework, migrates the ImageNet pre-trained model, freezes the low-layer network parameters and retrains the high-layer parameters to build a microfossil image recognition model. We built training sets with randomly selected images of varied number for each taxon. Our experiments show that the average recognition accuracy for specific taxa of Cambrian microfossils (50 images for each taxon) is higher than 0.97 and it can reach 0.85 with only three training samples per taxon. Comparative analyses indicate that our results are much better than those of various prevalent methods, such as the transpose convolutional neural network (TCNN). This demonstrates the feasibility of using natural images (ImageNet) for the training of microfossil recognition models and provides a promising tool for the discovery of rare fossils.

Gait Recognition using Deep Residual Networks and Conditional Generative Adversarial Networks

Aiming at the problem that the traditional correlation filter tracking algorithm is prone to tracking failure under the target’s scale change and occlusion environment, we propose a scale-adaptive Kernel Correlation Filter (KCF) target tracking algorithm combined with the learning rate adjustment. Firstly, we use the KCF to obtain the initial position of the target, and then adopt a low-complexity scale estimation scheme to get the target's scale, which improves the ability of the proposed algorithm to adapt to the change of the target's scale, and the tracking speed is also ensured. Finally, we use the average difference between two adjacent images to analyze the change of the image, and adjust the learning rate of the target model in segments according to the average difference to solve the tracking failure problem when the target is severely obstructed. Compared the proposed algorithm with other five classic target tracking algorithms, the experimental results show that the proposed algorithm is well adapted to the complex environment such as target’s scale change, severe occlusion and background interference. At the same time, it has a real-time tracking speed of 231 frame/s.

The secondary surveillance radar system is the main surveillance method for national defense and domestic civil aviation. It will be interfered by noise during the transmission process, affecting the clarity of signal transmission, and also leading to a reduction in the stability and reliability of radio transmission. Although the traditional denoising method is effective, there is still a lot of noise remaining, which affects the signal detection. This paper proposes a secondary radar signal processing method based on the two-channel deep residual neural network (2CD-NET), which can effectively extract the deep features of the secondary radar signal and predict the response timing signal. It is verified by experiments that under the normal working noise environment of the secondary radar, the two-channel deep residual neural network has strong noise suppression performance. When the signal-to-noise ratio is 10dB, the signal-to-noise ratio of the test set can reach 99.9S%. When the signal-to-noise ratio is 5dB, the test set accuracy rate can reach 94.71%.

The estimation of state of charge (SOC) is a critical issue in the energy management of electric vehicle (EV) power batteries. However, the current accuracy of SOC estimation methods does not meet the requirements of practical applications. Therefore, this study proposes an improved lithium-ion battery SOC estimation method that combines deep residual shrinkage network (DRSN) and bidirectional gated recurrent unit (BiGRU) to enhance the SOC estimation accuracy. First, we insert the bidirectional gated recurrent unit neural network between the global average pooling layer and the output fully connected layer of the deep residual shrinkage network. This improvement enhances the model’s expressiveness, robustness, and data learning effect. Second, we develop a new activation function called “∂_swish” to replace the original ReLU activation function in the deep residual shrinkage network. The ∂_swish activation function improves the accuracy of the deep network model and reduces the risk of overfitting by utilizing its regularization effect. Finally, we conduct experimental tests at three different temperatures using the FUDS driving cycle dataset and the DST-US06-FUDS continuous driving cycle dataset. The algorithm model’s convergence speed is verified by comparing it with other models. The results show that compared to other models, the proposed method significantly improves SOC estimation accuracy at three different temperatures. In addition, the method demonstrates a high convergence speed.

Deep residual networks (ResNets) can learn deep feature representation from hyperspectral images (HSIs), and therefore have been widely used for HSI classification. Despite their high accuracies, there still exist a lot of challenging cases, such as open world recognition, limited-sample learning and visualization of learned classification features, which cannot be well addressed. Most of the challenges in HSI classification can be attributed to the dependence on softmax based loss function and classifiers, which cause the lack of robustness for deep learning models and the hardness to visualize the learned classification features. To improve the robustness and achieve the visualization of learned classification features, we propose a novel learning framework called Residual Prototype Learning Network, a combination of residual network and prototypes learning mechanism. Under the framework, a prototype learning based loss function is proposed to enhance intra-class compactness and the inter-class separation of these feature representations; in addition, a prototype learning based classifier is simultaneously proposed to achieve the 2D or 3D visualization of the classification features. The effectiveness of our proposed learning framework is evaluated on several publicly available HSI benchmarks, and the experimental results show that our approach achieve better results than traditional softmax based ResNets.

Regional land-use change is the leading cause of ecosystem carbon stock change; it is essential to investigate the response of LUCC to carbon stock to achieve the strategic goal of “double carbon” in a region. This paper proposes a residual network algorithm, the Residual Multi-module Fusion Network (R-MFNet), to address the problems of blurred feature boundary information, low classification accuracy, and high noise, which are often encountered in traditional classification methods. The network algorithm uses an R-ASPP module to expand the receptive field of the feature map to extract sufficient and multi-scale target features; it uses the attention mechanism to assign weights to the multi-scale information of each channel and space. It can fully preserve the remote sensing image features extracted by the convolutional layer through the residual connection. Using this classification network method, the classification of three Landsat-TM/OLI images of Zhengzhou City (the capital of Henan Province) from 2001 to 2020 was realized (the years that the three images were taken are 2001, 2009, and 2020). Compared with SVM, 2D-CNN, and deep residual networks (ResNet), the overall accuracy of the test dataset is increased by 10.07%, 3.96%, and 1.33%, respectively. The classification achieved using this method is closer to the real land surface, and its accuracy is higher than that of the finished product data obtained using the traditional classification method, providing high-precision land-use classification data for the subsequent carbon storage estimation research. Based on the land-use classification data and the carbon density data corrected by meteorological data (temperature and precipitation data), the InVEST model is used to analyze the land-use change and its impact on carbon storage in the region. The results showed that, from 2001 to 2020, the carbon stock in the study area showed a downward trend, with a total decrease of 1.48 × 107 t. Over the course of this 19-year period, the farmland area in Zhengzhou decreased by 1101.72 km2, and the built land area increased sharply by 936.16 km2. The area of land transfer accounted for 29.26% of the total area of Zhengzhou City from 2001 to 2009, and 31.20% from 2009 to 2020. The conversion of farmland to built land is the primary type of land transfer and the most important reason for decreasing carbon stock. The research results can provide support, in the form of scientific data, for land-use management decisions and carbon storage function protections in Zhengzhou and other cities around the world undergoing rapid urbanization.

As one of the representative algorithms of convolutional neural networks, deep residual network has achieved very good results in computer vision, classification and other fields. Deep residual networks redefine the way networks learn, allowing networks to directly learn the difference between input and output information. This paper takes the deep residual network as the main research object, introduces the innovation of the deep residual network, and uses the deep residual network and other neural network models to train on different datasets. It is found that the highest accuracy of the test set of the deep residual network on the MNIST dataset is 0.555% higher than that of LeNet. 0.225% higher than AlexNet; The maximum accuracy of the test set on the CIFAR-10 dataset is 23.13% higher than LeNet and 2.46% higher than AlexNet.

Currently, the research on the health state of rotating machinery under time-varying operating conditions mainly focuses on using a combination of several constant operating conditions or uniformly changing speed and load. This article studied the health status recognition of rotating machinery under nonlinear and continuous changes in speed and load. A health status recognition method of rotating machinery was proposed based on the gram angle field and deep residual contraction network. Considering the influence of working conditions on signal characteristics, the speed, load, and multidimensional time-domain features are fused to form feature vectors. The feature vectors were transformed into images by gram coding. The color contrast relationship mapped from the overall difference distribution of sample feature indexes to the image was not changed while the feature timing was retained, which weakened the influence of working condition information on the sample state, improved the deep residual shrinkage network (DRSN) structure, and introduced the Gaussian error linear unit (GELU) activation function. The experimental verification is completed on the reducer experimental platform and the Xi’an Jiaotong University (XJTU)-Changxing Sumyoung Technology Company Ltd. (XJTU-SY) dataset. The results show that the method can effectively identify the health state of rotating machinery under time-varying working conditions.

Event recognition in surveillance video has gained extensive attention from the computer vision community. This process still faces enormous challenges due to the tiny inter-class variations that are caused by various facets, such as severe occlusion, cluttered backgrounds, and so forth. To address these issues, we propose a spatio-temporal deep residual network with hierarchical attentions (STDRN-HA) for video event recognition. In the first attention layer, the ResNet fully connected feature guides the Faster R-CNN feature to generate object-based attention (O-attention) for target objects. In the second attention layer, the O-attention further guides the ResNet convolutional feature to yield the holistic attention (H-attention) in order to perceive more details of the occluded objects and the global background. In the third attention layer, the attention maps use the deep features to obtain the attention-enhanced features. Then, the attention-enhanced features are input into a deep residual recurrent network, which is used to mine more event clues from videos. Furthermore, an optimized loss function named softmax-RC is designed, which embeds the residual block regularization and center loss to solve the vanishing gradient in a deep network and enlarge the distance between inter-classes. We also build a temporal branch to exploit the long- and short-term motion information. The final results are obtained by fusing the outputs of the spatial and temporal streams. Experiments on the four realistic video datasets, CCV, VIRAT 1.0, VIRAT 2.0, and HMDB51, demonstrate that the proposed method has good performance and achieves state-of-the-art results.