Search Results (2,416)

The integration of robotics in the garment industry remains relatively limited, primarily due to the challenges in the highly deformable nature of garments. The objective of this study is thus to explore a vision-based garment recognition and environment reconstruction model to facilitate the application of robots in garment processing. Object SLAM (Simultaneous Localization and Mapping) was employed as the core methodology for real-time mapping and tracking. To enable garment detection and reconstruction, two datasets were created: a 2D garment image dataset for instance segmentation model training and a synthetic 3D mesh garment dataset to enhance the DeepSDF (Signed Distance Function) model for generative garment reconstruction. In addition to garment detection, the SLAM system was extended to identify and reconstruct environmental planes, using the CAPE (Cylinder and Plane Extraction) model. The implementation was tested using an Intel Realsense^® camera, demonstrating the feasibility of simultaneous garment and plane detection and reconstruction. This study shows improved performance in garment recognition with the 2D instance segmentation models and an enhanced understanding of garment shapes and structures with the DeepSDF model. The integration of CAPE plane detection with SLAM allows for more robust environment reconstruction that is capable of handling multiple objects. The implementation and evaluation of the system highlight its potential for enhancing automation and efficiency in the garment processing industry. Full article

Addressing the challenges in online multi-object tracking algorithms under complex scenarios, where the independence among feature extraction, object detection, and data association modules leads to both error accumulation and the difficulty of maintaining visual consistency for occluded objects, we have proposed an end-to-end multi-object tracking method based on hypergraph matching (JDTHM). Initially, a feature extraction and object detection module is introduced to achieve preliminary localization and description of the objects. Subsequently, a deep feature aggregation module is designed to extract temporal information from historical tracklets, amalgamating features from object detection and feature extraction to enhance the consistency between the current frame features and the tracklet features, thus preventing identity swaps and tracklet breaks caused by object detection loss or distortion. Finally, a data association module based on hypergraph matching is constructed, integrating with object detection and feature extraction into a unified network, transforming the data association problem into a hypergraph matching problem between the tracklet hypergraph and the detection hypergraph, thereby achieving end-to-end model optimization. The experimental results demonstrate that this method has yielded favorable qualitative and quantitative analysis results on three multi-object tracking datasets, thereby validating its effectiveness in enhancing the robustness and accuracy of multi-object tracking tasks. Full article

This study presents a robust framework designed to address the limitations of passive infrared (PIR) sensors in home-based elderly monitoring, particularly focusing on false detections and sensor blind times, which compromise data accuracy. While PIR sensors are low-cost and privacy-preserving, their inherent inaccuracies hinder their use in reliable monitoring systems. To overcome these challenges, we propose a novel spatiotemporal data cleaning framework that integrates non-deterministic tracking (NDT) and late-binding adjustment (LBA). This framework enhances the quality and accuracy of sensor data by filtering out false positives and omissions through analysis of walking speed and sensor connectivity. Simulations demonstrated significant improvements in movement tracking accuracy, and real-world experiments involving three elderly participants further validated the framework’s practicality. The experiments confirmed that the proposed method can remove errors such as false positives and false negatives from PIR sensors. It can achieve 90% accuracy in tracking the movements of elderly people, highlighting the potential for this framework to be applied in the real world. The key scientific contribution of this research lies in the development of a scalable, non-wearable indoor tracking solution that reduces the need for dense sensor arrays, making it cost-effective and adaptable to existing infrastructure with minimal modifications. This framework contributes to advancing the field of indoor localization and offers a reliable solution for sensor-based monitoring systems, especially in elderly care, addressing the urgent needs of an aging global population. Full article

Accurate ship trajectory prediction is crucial for real-time vessel position tracking and maritime safety management. However, existing methods for ship trajectory prediction encounter significant challenges. They struggle to effectively extract long-term and complex spatial–temporal features hidden within the data. Moreover, they often overlook correlations among multivariate dynamic features such as longitude (LON), latitude (LAT), speed over ground (SOG), and course over ground (COG), which are essential for precise trajectory forecasting. To address these pressing issues and fulfill the need for more accurate and comprehensive ship trajectory prediction, we propose a novel and integrated approach. Firstly, a Trajectory Point Correlation Attention (TPCA) mechanism is devised to establish spatial connections between trajectory points, thereby uncovering the local trends of trajectory point changes. Subsequently, a Temporal Pattern Attention (TPA) mechanism is introduced to handle the associations between multiple variables across different time steps and capture the dynamic feature correlations among trajectory attributes. Finally, a Great Circle Route Loss Function (GCRLoss) is constructed, leveraging the perception of the Earth’s curvature to deepen the understanding of spatial relationships and geographic information. Experimental results demonstrate that our proposed method outperforms existing ship trajectory prediction techniques, showing enhanced reliability in multi-step predictions. Full article

Motivation: Chest X-ray (CXR) is a routine diagnostic X-ray examination for checking and screening various diseases. Automatically localizing and classifying diseases from CXR as a detection task is of much significance for subsequent diagnosis and treatment. Due to the fact that samples of some diseases are difficult to acquire, CXR detection datasets often present a long-tail distribution over different diseases. Objective: The detection performance of tail classes is very poor due to the limited number and diversity of samples in the training dataset and should be improved. Method: In this paper, motivated by a correspondence-based tracking system, we build a pipeline named RaTrack, leveraging a diffusion model to alleviate the tail class degradation problem by aligning the generation process of the tail to the head class. Then, the samples of rare classes are generated to extend the number and diversity of rare samples. In addition, we propose a filtering strategy to control the quality of the generated samples. Results: Extensive experiments on public datasets, Vindr-CXR and RSNA, demonstrate the effectiveness of the proposed method, especially for rare diseases. Full article

Background: This study examined electrical bioimpedance as a biomarker for intracochlear tissue changes after cochlear implant surgery, comparing monopolar, three-point, and four-point impedance measurements over time and evaluating different measurement systems and approaches. Methods: Impedance measurements were obtained from 21 participants during surgery and at four postoperative stages. Monopolar impedances were recorded using the Bionic Ear Data Collection System (BEDCS) and the Active Insertion Monitoring (AIM) system. Three- and four-point impedances were recorded directly using BEDCS, and indirect three-point impedances were additionally derived from Electrical Field Imaging matrices recorded using BEDCS or AIM. Results: There was an 11% relative error between monopolar measurements from BEDCS and AIM and a 25% discrepancy between direct and indirect three-point measurements. Despite this, direct and indirect measurements from both systems were useful for tracking postoperative impedance shifts. Three- and four-point measurements showed a strong relationship both during and after surgery. Our results suggest that three- and four-point measurements are more specific than monopolar impedances in capturing localized tissue changes. Conclusions: Three- and four-point impedance measurements are potential markers of intracochlear tissue changes over time. While direct three-point impedance measurements offer higher accuracy, indirect measurements provide a feasible alternative for monitoring intracochlear changes in clinical settings lacking the option of direct measurements. Full article

Currently, the process of tracking moving objects and determining their indoor location is considered to be one of the most attractive applications that have begun to see widespread use, especially after the adoption of this technology in some smartphone applications. The great developments in electronics and communications systems have provided the basis for tracking and location systems inside buildings, so-called indoor positioning systems (IPSs). The ultra-wideband (UWB) technology is one of the important emerging solutions for IPSs. This radio communications technology provides important characteristics that distinguish it from other solutions, such as secure and robust communications, wide bandwidth, high data rate, and low transmission power. In this paper, we review the implementation of the most important real-time indoor positioning and tracking systems that use ultra-wideband technology for tracking and localizing moving objects. This paper reviews the newest in-market UWB modules and solutions, discussing several types of algorithms that are used by the real-time UWB-based systems to determine the location with high accuracy, along with a detailed comparison that saves the reader a lot of time and effort in choosing the appropriate UWB-module/method/algorithm for real-time implementation. Full article

Non-contact heart monitoring is crucial in advancing telemedicine, fitness tracking, and mass screening. Remote photoplethysmography (rPPG) is a non-contact technique to obtain information about heart pulse by analyzing the changes in the light intensity reflected or absorbed by the skin during the blood circulation cycle. However, this technique is sensitive to environmental lightning and different skin pigmentation, resulting in unreliable results. This research presents a multimodal approach to non-contact heart rate estimation by combining facial video and physical attributes, including age, gender, weight, height, and body mass index (BMI). For this purpose, we collected local datasets from 60 individuals containing a 1 min facial video and physical attributes such as age, gender, weight, and height, and we derived the BMI variable from the weight and height. We compare the performance of two machine learning models, support vector regression (SVR) and random forest regression on the multimodal dataset. The experimental results demonstrate that incorporating a multimodal approach enhances model performance, with the random forest model achieving superior results, yielding a mean absolute error (MAE) of 3.057 bpm, a root mean squared error (RMSE) of 10.532 bpm, and a mean absolute percentage error (MAPE) of 4.2% that outperforms the state-of-the-art rPPG methods. These findings highlight the potential for interpretable, non-contact, real-time heart rate measurement systems to contribute effectively to applications in telemedicine and mass screening. Full article

Finding the best configuration of a neural network’s hyper-parameters may take too long to be feasible using an exhaustive search, especially when the cardinality of the search space has a big combinatorial number of possible solutions with various hyper-parameters. This problem is aggravated when we also need to optimize the parameters of the neural network, such as the weight of the hidden neurons and biases. Extreme learning machines (ELMs) are part of the random weights neural network family, in which parameters are randomly initialized, and the solution, unlike gradient-descent-based algorithms, can be found analytically. This ability is especially useful for metaheuristic analysis due to its reduced training times allowing a faster optimization process, but the problem of finding the best hyper-parameter configuration is still remaining. In this paper, we propose a modification of the artificial bee colony (ABC) metaheuristic to act as parameterizers for a regularized ELM, incorporating three methods: an adaptive mechanism for ABC to balance exploration (global search) and exploitation (local search), an adaptation of the opposition-based learning technique called opposition local-based learning (OLBL) to strengthen exploitation, and a record of access to the search space called forbidden redundant indexes (FRI) that allow us to avoid redundant calculations and track the explored percentage of the search space. We set ten parameterizations applying different combinations of the proposed methods, limiting them to explore up to approximately 10% of the search space, with results over 98% compared to the maximum performance obtained in the exhaustive search in binary and multiclass datasets. The results demonstrate a promising use of these parameterizations to optimize the hyper-parameters of the R-ELM in datasets with different characteristics in cases where computational efficiency is required, with the possibility of extending its use to other problems with similar characteristics with minor modifications, such as the parameterization of support vector machines, digital image filters, and other neural networks, among others. Full article

In this paper, an energy management strategy is developed in a renewable energy-based microgrid composed of a wind farm, a battery energy storage system, and an electolyzer unit. The main objective of energy management in the studied microgrid is to guarantee a stable supply of electrical energy to local consumers. In addition, it encompasses hydrogen gas production by using part of the available excess energy in the system, which has some economic benefits. Also, energy management can protect the battery bank from damage by preventing the possibility of it being overcharged. These objectives should be achieved by developing a robust and effective control technique for DC-DC converters that are connected to energy storage devices. For this purpose, an advanced control technique based on Model Predictive Control, which is recognized as a popular control technique for industrial and process applications, is developed. This technique has a fast dynamic response and good tracking features and is simple to implement. The simulation results prove the effectiveness of the proposed control strategy and control technique for energy management in the studied renewable energy-based microgrid. Full article

The application of wool as mulch in strawberry cultivation was analysed to find a solution for the rational use of wool from mountain sheep. In the plantation, the experimental plots mulched with wool, straw, and bark were appointed. The plots were monitored during the experiment, while the soil temperature and moisture content were measured. The data collected in two-hour intervals were analysed, taking into account air temperature and falls registered in the local meteorological station. Additionally, the progress of mulch biodegradation was tracked. The changes in the wool morphology that occurred by biodegradation were observed during microscopic examinations using the Scanning Electron Microscope (SEM). It was stated that wool mulch plays an essential role in thermoregulation of the soil surface, prevents the overheating of the soil during the summer heat, and protects soil against excessive cooling during cold nights. The wool mulch minimizes the fluctuations between the soil’s day and night temperature. The fluctuations do not exceed 2–3 degrees on hot summer days, which are five times smaller than for the control plot. The wool retains large amounts of rainwater several times its weight. The water is then slowly released, providing the growing plants with a moist environment during a longer rainless period. Moreover, wool is difficult to biodegrade and maintains its properties for a long time, lasting longer than one vegetation season. Compared to straw and bark, the temperature fluctuations recorded for wool are two times smaller, and its effectiveness in water management is considerably better. The beneficial impact of the wool mulch ensuring favourable conditions for strawberry growth was explained by the specific wool structure and its unique properties. Full article

To achieve efficient and accurate thick plate welding, as well as to precisely extract and plan the paths of complex three-dimensional weld seams in large steel structures, this study introduces a novel vision-guided approach for robotic welding systems utilizing a constant-focus laser sensor. This methodology specifically targets and mitigates several critical shortcomings inherent in conventional vision-guided welding techniques, including limited detection ranges, diminished precision in both detection and tracking, and suboptimal real-time performance. For preprocessed weld images, an improved grayscale extreme centroid method was developed to extract the center of the light stripe. Furthermore, a sophisticated feature point extraction algorithm, which integrates a maximum distance search strategy with a least-squares fitting procedure, was developed to facilitate the precise and timely identification of weld seam characteristic points. To further optimize the outcomes, a cylindrical filtering mechanism was employed to eliminate substantial discrepancies, whereas local Non-Uniform Rational B-Spline (NURBS) curve interpolation was utilized for the generation of smooth and accurate trajectory plans. A spatial vector-based pose adjustment strategy was then implemented to provide robust guidance for the welding robot, ensuring the successful execution of the welding operations. The experimental results indicated that the proposed algorithm achieved a tracking error of 0.3197 mm for welding workpieces with a thickness of 60 mm, demonstrating the method’s substantial potential in the manufacturing sector, especially in the domain of automated welding. Full article

Video object tracking has taken advantage of pre-trained weights on large-scale datasets. However, most trackers fully fine-tune all the backbone’s parameters for adjusting to tracking-specific representations, where the utilization rate of parameter adjustment is inefficient. In this paper, we aim to explore whether a better balance can be achieved between parameter efficiency and tracking performance, and fully utilize the weight advantage of training on large-scale datasets. There are two main differences from a normal tracking paradigm: (i) We freeze the pre-trained weights of the backbone and add a dynamic adapter structure for every transformer block for tuning. (ii) We migrate the pre-trained decoder blocks to the tracking head for better generalization and localization. Extensive experiments are conducted on both mainstream challenging datasets and datasets for special scenarios or targets such as night-time and transparent objects. With the full utilization of pre-training knowledge, we found through experiments that a few tuned parameters can compensate for the gap between the pre-trained representation and the tracking-specific representation, especially for large backbones. Even better performance and generalization can be achieved. For instance, our AdaDe-B256 tracker achieves 49.5 AUC on the LaSOT${}_{\mathrm{ext}}$ which contains 150 sequences. Full article

The rapid expansion of BeiDou satellite navigation applications has led to a growing demand for real-time high-precision positioning services. Currently, high-precision positioning services face challenges such as a long initialization time and heavy reliance on reference station networks, thereby failing to fulfill the requirements for real-time, wide-area, and centimeter-level positioning. In this study, we consider the multi-frequency signals that are broadcast by a satellite to share a common reference clock and possess identical RF channels and propagation paths with strict temporal, spectral, and spatial coupling between signal components, resulting in strongly coherent propagation delays. Firstly, we accurately establish a multi-frequency signal model that fully exploits those coherent characteristics among the multi-frequency BDS signals. Subsequently, we propose a rapid high-precision ranging technique using the code and carrier phases of multi-frequency signals. The proposed method unitizes multi-frequency signals via a coherent joint processing unit consisting of a joint tracking state estimator and a coherent signal generator. The joint tracking state estimator simultaneously estimates the biased pseudorange and its change rate, ionospheric delay and its change rate, and ambiguities. The coherent signal generator updates the numerically controlled oscillator (NCO) to adjust the local reference signal’s code and carrier replicas of different frequencies, changing them according to the state estimated by the joint tracking state estimator. Finally, the simulation results indicate that the proposed method efficiently diminishes the estimated biased pseudorange and ionospheric delay errors to below 0.1 m. Furthermore, this method reduces the carrier phase errors by more than 60% compared with conventional single-frequency-independent tracking methods. Consequently, the proposed method can achieve rapid centimeter-level results ranging for up to 1 min without using precise atmosphere corrections and provide enhanced tracking sensitivity and robustness. Full article

In modern circuit design, the short-circuit problem is one of the key factors affecting routability. With the continuous reduction in feature sizes, the short-circuit problem grows significantly in detailed routing. Track assignment, as a crucial intermediary phase between global routing and detailed routing, plays a vital role in preprocessing the short-circuit problem. However, existing track assignment algorithms face the challenge of easily falling into local optimality. As a typical swarm intelligence technique, particle swarm optimization (PSO) is a powerful tool with excellent optimization ability to solve large-scale problems. To address the above issue, we propose an effective track assignment algorithm based on social learning discrete particle swarm optimization (SLDPSO-TA). First, an effective wire model that considers the local nets is proposed. By considering the pin distribution of local nets, this model extracts and allocates more segments to fully leverage the role of track assignment. Second, an integer encoding strategy is employed to ensure that particles within the encoding space range correspond one-to-one with the assignment scheme, effectively expanding the search space. Third, a social learning mode based on the example pool is introduced to PSO, which is composed of other particles that are superior to the current particle. By learning from various objects in the example pool, the diversity of the population is improved. Fourth, a negotiation-based refining strategy is utilized to further reduce overlap. This strategy intelligently transfers and redistributes wire segments in congested areas to reduce congestion across the entire routing panel. Experimental results on multiple benchmarks demonstrate that the proposed SLDPSO-TA can achieve the best overlap cost optimization among all the existing methods, effectively reducing congestion in critical routing areas. Full article