Robust visual tracking for UAVs with dynamic feature weight selection

Learning Background-Suppressed Dual-Regression Correlation Filters for Visual Tracking

The discriminative correlation filter (DCF)-based tracking method has shown good accuracy and efficiency in visual tracking. However, the periodic assumption of sample space causes unwanted boundary effects, restricting the tracker's ability to distinguish between the target and background. Additionally, in the real tracking environment, interference factors such as occlusion, background clutter, and illumination changes cause response aberration and, thus, tracking failure. To address these issues, this work proposed a novel tracking method named the background-suppressed dual-regression correlation filter (BSDCF) for visual tracking. First, we utilize the background-suppressed function to crop out the target features from the global features. In the training step, while introducing the spatial regularity constraint and background response suppression regularization, we construct a dual regression structure to train the target and global filters separately. The aim is to exploit the difference between the output response maps for mutual constraint to highlight the target and suppress the background interference. Furthermore, in the detection step, the global response can be enhanced by a weighted fusion of the target response to further improve the tracking performance in complex scenes. Finally, extensive experiments are conducted on three public benchmarks (including OTB100, TC128, and UAVDT), and the experimental results indicate that the proposed BSDCF tracker achieves tracking performance comparable to many state-of-the-art (SOTA) trackers in a variety of complex situations.

Determination of Air Traffic Complexity Most Influential Parameters Based on Machine Learning Models

Today, aircraft demand is exceeding the capacity of the Air Traffic Control (ATC) system. As a result, airspace is becoming a very complex environment to control. The complexity of airspace is thus closely related to the workload of controllers and is a topic of great interest. The major concern is that variables that are related to complexity are currently recognised, but there is still a debate about how to define complexity. This paper attempts to define which variables determine airspace complexity. To do so, a novel methodology based on the use of machine learning models is used. In this way, it tries to overcome one of the main disadvantages of the current complexity models: the subjectivity of the models based on expert opinion. This study has determined that the main indicator that defines complexity is the number of aircraft in the sector, together with the occupancy of the traffic flows and the vertical distribution of aircraft. This research can help numerous studies on both air traffic complexity assessment and Air Traffic Controller (ATCO) workload studies. This model can also help to study the behaviour of air traffic and to verify that there is symmetry in structure and the origin of the complexity in the different ATC sectors. This would have a great benefit on ATM, as it would allow progress to be made in solving the existing capacity problem.

Tracking and Dynamic Tuning of a Wireless Powered Endoscopic Capsule

This work presents an inductive wireless power transfer system for powering an endoscopy capsule supplying energy to power electronic devices allocated inside a capsule of ≈26.1 mm × 9 mm. A receiver with three coils in quadrature with dimensions of ≈9 mm × 9 mm × 10 mm is located inside the capsule, moving freely inside a transmitter coil with 380 mm diameter through translations and revolutions. The proposed system tracks the variations of the equivalent magnetic coupling coefficient compensating misalignments between the transmitter and receiver coils. The power on the load is estimated and optimized from the transmitter, and the tracking control is performed by actuating on a capacitance in the matching network and on the voltage source frequency. The proposed system can prevent load overheating by limiting the power via adjusting of the magnitude of voltage source VS. Experimental results with uncertainties analysis reveal that, even at low magnetic coupling coefficients k ranging from (1.7 × 10-3, 3.5 × 10-3), the power on the load can be held within the range of 100-130 mW. These results are achieved with any position of the capsule in the space, limited by the diameter of the transmitter coil and height of 200 mm when adjusting the series capacitance of the transmitter in the range (17.4, 19.4) pF and the frequency of the power source in the range (802.1, 809.5) kHz.

Adaptive Beamforming Approaches to Improve Passive Radar Performance in Sea and Wind Farms' Clutter

This article presents the problem of passive radar vessel detection in a real coastal scenario in the presence of sea and wind farms' clutter, which are characterised by high spatial and time variability due to the influence of weather conditions. Deterministic and adaptive beamforming techniques are proposed and evaluated using real data. Key points such as interference localisation and characterisation are tackled in the passive bistatic scenario with omnidirectional illuminators that critically increase the area of potential clutter sources to areas far from the surveillance area. Adaptive beamforming approaches provide significant Signal-to-Interference improvements and important radar coverage improvements. In the presented case study, an aerial target is detected 28 km far from the passive radar receiver, fulfilling highly demanding performance requirements.

Qualitative Classification of Lubricating Oil Wear Particle Morphology Based on Coaxial Capacitive Sensing Network and SVM

In addition to lubricating and cooling, aero-engine lubricating oil is also a transport medium for wear particles generated by mechanical wear. Online identification of the number and shape of wear particles is an important means to directly determine the wear state of rotating parts, but most of the existing research focuses on the identification and counting of wear particles. In this paper, a qualitative classification method of wear particle morphology based on support vector machine is proposed by using the wear particle capacitance signal obtained by the coaxial capacitive sensing network. Firstly, the coaxial capacitive sensing network simulation model is used to obtain the capacitance signals of different shapes of wear particles entering the detection space of different electrode plates. In addition, a variety of intelligent optimization algorithms are used to optimize the relevant parameters of the support vector machine (SVM) model in order to improve the classification accuracy. By using the processed data and optimized parameters, a SVM-based qualitative classification model for wear particles is established. Finally, the validity of the classification model is verified by real wear particles of different sizes. The simulation and experimental results show that the qualitative classification of different wear particle morphologies can be achieved by using the coaxial capacitive sensing network signal and the SVM model.

UAV-Based Hyperspectral Monitoring Using Push-Broom and Snapshot Sensors: A Multisite Assessment for Precision Viticulture Applications

Hyperspectral aerial imagery is becoming increasingly available due to both technology evolution and a somewhat affordable price tag. However, selecting a proper UAV + hyperspectral sensor combo to use in specific contexts is still challenging and lacks proper documental support. While selecting an UAV is more straightforward as it mostly relates with sensor compatibility, autonomy, reliability and cost, a hyperspectral sensor has much more to be considered. This note provides an assessment of two hyperspectral sensors (push-broom and snapshot) regarding practicality and suitability, within a precision viticulture context. The aim is to provide researchers, agronomists, winegrowers and UAV pilots with dependable data collection protocols and methods, enabling them to achieve faster processing techniques and helping to integrate multiple data sources. Furthermore, both the benefits and drawbacks of using each technology within a precision viticulture context are also highlighted. Hyperspectral sensors, UAVs, flight operations, and the processing methodology for each imaging type' datasets are presented through a qualitative and quantitative analysis. For this purpose, four vineyards in two countries were selected as case studies. This supports the extrapolation of both advantages and issues related with the two types of hyperspectral sensors used, in different contexts. Sensors' performance was compared through the evaluation of field operations complexity, processing time and qualitative accuracy of the results, namely the quality of the generated hyperspectral mosaics. The results shown an overall excellent geometrical quality, with no distortions or overlapping faults for both technologies, using the proposed mosaicking process and reconstruction. By resorting to the multi-site assessment, the qualitative and quantitative exchange of information throughout the UAV hyperspectral community is facilitated. In addition, all the major benefits and drawbacks of each hyperspectral sensor regarding its operation and data features are identified. Lastly, the operational complexity in the context of precision agriculture is also presented.

Three-Dimensional Quantitative Evaluation of the Scapular Skin Marker Movements in the Upright Posture

Motion capture systems using skin markers are widely used to evaluate scapular kinematics. However, soft-tissue artifact (STA) is a major limitation, and there is insufficient knowledge of the marker movements from the original locations. This study explores a scapular STA, including marker movements with shoulder elevation using upright computed tomography (CT). Ten healthy males (twenty shoulders in total) had markers attached to scapular bony landmarks and underwent upright CT in the reference and elevated positions. Marker movements were calculated and compared between markers. The bone-based and marker-based scapulothoracic rotation angles were also compared in both positions. The median marker movement distances were 30.4 mm for the acromial angle, 53.1 mm for the root of the scapular spine, and 70.0 mm for the inferior angle. Marker movements were significantly smaller on the superolateral aspect of the scapula, and superior movement was largest in the directional movement. Scapulothoracic rotation angles were significantly smaller in the marker-based rotation angles than in the bone-based rotation angles of the elevated position. We noted that the markers especially did not track the inferior movement of the scapular motion with shoulder elevation, resulting in an underestimation of the marker-based rotation angles.

Machine Learning and Lexicon Approach to Texts Processing in the Detection of Degrees of Toxicity in Online Discussions

This article focuses on the problem of detecting toxicity in online discussions. Toxicity is currently a serious problem when people are largely influenced by opinions on social networks. We offer a solution based on classification models using machine learning methods to classify short texts on social networks into multiple degrees of toxicity. The classification models used both classic methods of machine learning, such as naïve Bayes and SVM (support vector machine) as well ensemble methods, such as bagging and RF (random forest). The models were created using text data, which we extracted from social networks in the Slovak language. The labelling of our dataset of short texts into multiple classes-the degrees of toxicity-was provided automatically by our method based on the lexicon approach to texts processing. This lexicon method required creating a dictionary of toxic words in the Slovak language, which is another contribution of the work. Finally, an application was created based on the learned machine learning models, which can be used to detect the degree of toxicity of new social network comments as well as for experimentation with various machine learning methods. We achieved the best results using an SVM-average value of accuracy = 0.89 and F1 = 0.79. This model also outperformed the ensemble learning by the RF and Bagging methods; however, the ensemble learning methods achieved better results than the naïve Bayes method.

Transformer with progressive sampling for medical cellular image segmentation

The convolutional neural network, as the backbone network for medical image segmentation, has shown good performance in the past years. However, its drawbacks cannot be ignored, namely, convolutional neural networks focus on local regions and are difficult to model global contextual information. For this reason, transformer, which is used for text processing, was introduced into the field of medical segmentation, and thanks to its expertise in modelling global relationships, the accuracy of medical segmentation was further improved. However, the transformer-based network structure requires a certain training set size to achieve satisfactory segmentation results, and most medical segmentation datasets are small in size. Therefore, in this paper we introduce a gated position-sensitive axial attention mechanism in the self-attention module, so that the transformer-based network structure can also be adapted to the case of small datasets. The common operation of the visual transformer introduced to visual processing when dealing with segmentation tasks is to divide the input image into equal patches of the same size and then perform visual processing on each patch, but this simple division may lead to the destruction of the structure of the original image, and there may be large unimportant regions in the divided grid, causing attention to stay on the uninteresting regions, affecting the segmentation performance. Therefore, in this paper, we add iterative sampling to update the sampling positions, so that the attention stays on the region to be segmented, reducing the interference of irrelevant regions and further improving the segmentation performance. In addition, we introduce the strip convolution module (SCM) and pyramid pooling module (PPM) to capture the global contextual information. The proposed network is evaluated on several datasets and shows some improvement in segmentation accuracy compared to networks of recent years.

Hyper-Parameter Optimization of Stacked Asymmetric Auto-Encoders for Automatic Personality Traits Perception

In this work, a method for automatic hyper-parameter tuning of the stacked asymmetric auto-encoder is proposed. In previous work, the deep learning ability to extract personality perception from speech was shown, but hyper-parameter tuning was attained by trial-and-error, which is time-consuming and requires machine learning knowledge. Therefore, obtaining hyper-parameter values is challenging and places limits on deep learning usage. To address this challenge, researchers have applied optimization methods. Although there were successes, the search space is very large due to the large number of deep learning hyper-parameters, which increases the probability of getting stuck in local optima. Researchers have also focused on improving global optimization methods. In this regard, we suggest a novel global optimization method based on the cultural algorithm, multi-island and the concept of parallelism to search this large space smartly. At first, we evaluated our method on three well-known optimization benchmarks and compared the results with recently published papers. Results indicate that the convergence of the proposed method speeds up due to the ability to escape from local optima, and the precision of the results improves dramatically. Afterward, we applied our method to optimize five hyper-parameters of an asymmetric auto-encoder for automatic personality perception. Since inappropriate hyper-parameters lead the network to over-fitting and under-fitting, we used a novel cost function to prevent over-fitting and under-fitting. As observed, the unweighted average recall (accuracy) was improved by 6.52% (9.54%) compared to our previous work and had remarkable outcomes compared to other published personality perception works.

Combined Feature Extraction and Random Forest for Laser Self-Mixing Vibration Measurement without Determining Feedback Intensity

To measure the vibration of a target by laser self-mixing interference (SMI), we propose a method that combines feature extraction and random forest (RF) without determining the feedback strength (C). First, the temporal, spectral, and statistical features of the SMI signal are extracted to characterize the original SMI signal. Secondly, these interpretable features are fed into the pretrained RF model to directly predict the amplitude and frequency (A and f) of the vibrating target, recovering the periodic vibration of the target. The results show that the combination of RF and feature extraction yields a fit of more than 0.94 for simple and quick measurement of A and f of unsmooth planar vibrations, regardless of the feedback intensity and the misalignment of the retromirror. Without a complex optical stage, this method can quickly recover arbitrary periodic vibrations from SMI signals without C, which provides a novel method for quickly implementing vibration measurements.

An Improved Robust Fractal Image Compression Based on M-Estimator

In this paper, a robust fractal image compression method based on M-estimator is presented. The proposed method applies the M-estimator to the parameter estimation in the fractal encoding procedure using Huber and Tukey’s robust statistics. The M-estimation reduces the influence of the outliers and makes the fractal encoding algorithm robust to the noisy image. Meanwhile, the quadtree partitioning approach has been used in the proposed methods to improve the efficiency of the encoding algorithm, and some unnecessary computations are eliminated in the parameter estimation procedures. The experimental results demonstrate that the proposed method is insensitive to the outliers in the noisy corrupted image. The comparative data shows that the proposed method is superior in both the encoding time and the quality of retrieved images over other robust fractal compression algorithms. The proposed algorithm is useful for multimedia and image archiving, low-cost consumption applications and progressive image transmission of live images, and in reducing computing time for fractal image compression.

Scheduling uniform machines with restricted assignment

The problem of minimizing makespan (maximum completion time) on uniform machines with restricted assignment is considered. The machines differ in their speeds and functionalities. Each job has a set of machines to which it can be assigned, called its processing set. The goal is to finish the jobs as soon as possible. There exist 4/3-approximation algorithms for the cases of inclusive and tree-hierarchical assignment restrictions, under an assumption that machines with higher capabilities also run at higher speeds. We eliminate the assumption and present algorithms with approximation ratios 2 and 4/3 for both cases.

A Multi-Strategy Adaptive Comprehensive Learning PSO Algorithm and Its Application

In this paper, a multi-strategy adaptive comprehensive learning particle swarm optimization algorithm is proposed by introducing the comprehensive learning, multi-population parallel, and parameter adaptation. In the proposed algorithm, a multi-population parallel strategy is designed to improve population diversity and accelerate convergence. The population particle exchange and mutation are realized to ensure information sharing among the particles. Then, the global optimal value is added to velocity update to design a new velocity update strategy for improving the local search ability. The comprehensive learning strategy is employed to construct learning samples, so as to effectively promote the information exchange and avoid falling into local extrema. By linearly changing the learning factors, a new factor adjustment strategy is developed to enhance the global search ability, and a new adaptive inertia weight-adjustment strategy based on an S-shaped decreasing function is developed to balance the search ability. Finally, some benchmark functions and the parameter optimization of photovoltaics are selected. The proposed algorithm obtains the best performance on 6 out of 10 functions. The results show that the proposed algorithm has greatly improved diversity, solution accuracy, and search ability compared with some variants of particle swarm optimization and other algorithms. It provides a more effective parameter combination for the complex engineering problem of photovoltaics, so as to improve the energy conversion efficiency.