YOLOv5 Drone Detection Using Multimodal Data Registered by the Vicon System.

This work is focused on the preliminary stage of the 3D drone tracking challenge, namely the precise detection of drones on images obtained from a synchronized multi-camera system. The YOLOv5 deep network with different input resolutions is trained and tested on the basis of real, multimodal data containing synchronized video sequences and precise motion capture data as a ground truth reference. The bounding boxes are determined based on the 3D position and orientation of an asymmetric cross attached to the top of the tracked object with known translation to the object's center. The arms of the cross are identified by the markers registered by motion capture acquisition. Besides the classical mean average precision (mAP), a measure more adequate in the evaluation of detection performance in 3D tracking is proposed, namely the average distance between the centroids of matched references and detected drones, including false positive and false negative ratios. Moreover, the videos generated in the AirSim simulation platform were taken into account in both the training and testing stages.

Intelligent Video Analytics for Human Action Recognition: The State of Knowledge.

The paper presents a comprehensive overview of intelligent video analytics and human action recognition methods. The article provides an overview of the current state of knowledge in the field of human activity recognition, including various techniques such as pose-based, tracking-based, spatio-temporal, and deep learning-based approaches, including visual transformers. We also discuss the challenges and limitations of these techniques and the potential of modern edge AI architectures to enable real-time human action recognition in resource-constrained environments.

Correlation dimension and entropy in the assessment of sex differences based on human gait data.

Introduction: It is proved that there are differences between gait performed by females and males, which appear in movements of selected body parts. Despite numerous state-of-the-art studies related to the discriminative analysis of motion capture data, the question of whether measures of signal complexity and uncertainty can extract valuable features for the problem of sex distinction still remains open. It is the subject of the paper. Methods: Correlation dimension, as well as approximate and sample entropies, are selected to describe motion data. In the numerical experiments, the collected dataset with 884 samples of 25 females and 30 males was used. The measurements took place in the Human Motion Laboratory (HML), equipped with a highly precise motion capture system. Two variants of data representation were investigated-time series that contain joint rotations of taken skeleton model as well as positions of the markers attached to the human body. Finally, a comparative analysis between the populations of females and males using descriptive statistics, non-parametric estimation, and statistical hypotheses verification was carried out. Results: There are statistically significant sex differences extracted by the taken measures. In general, the movements of lower limbs result in greater values of correlation dimension and entropies for females, while selected upper body parts play a similar role for males. The dissimilarities are mainly observed in hip, ankle, shoulder, and head movements. Discussion: Correlation dimension and entropy measures provide robust and explainable features of motion capture data with a valuable description of the human locomotion system. Thus, beyond the importance of discovered differences between females and males, their interpretation and understanding are also known.

Recreating the Motion Trajectory of a System of Articulated Rigid Bodies on the Basis of Incomplete Measurement Information and Unsupervised Learning.

Re-creating the movement of an object consisting of articulated rigid bodies is an issue that concerns both mechanical and biomechanical systems. In the case of biomechanical systems, movement re-storation allows, among other things, introducing changes in training or rehabilitation exercises. Motion recording, both in the case of mechanical and biomechanical systems, can be carried out with the use of sensors recording motion parameters or vision systems and with hybrid solutions. This article presents a method of measuring motion parameters with IMU (Inertial Measurement Unit) sensors. The main assumption of the article is to present the method of data estimation from the IMU sensors for the given time moment on the basis of data from the previous time moment. The tested system was an industrial robot, because such a system allows identifying the measurement errors from IMU sensors and estimating errors basing on the reference measurements from encoders. The aim of the research is to be able to re-create the movement parameters of an object consisting of articulated rigid bodies on the basis of incomplete measurement information from sensors. The developed algorithms can be used in the diagnostics of mechanical systems as well as in sport or rehabilitation. Limiting sensors will allow, for example, athletes defining mistakes made during training only on the basis of measurements from one IMU sensor, e.g., installed in a smartphone. Both in the case of rehabilitation and sports, minimizing the number of sensors allows increasing the comfort of the person performing a given movement as part of the measurement.

Light-Stable Methylammonium-Free Inverted Flexible Perovskite Solar Modules on PET Exceeding 10.5% on a 15.7 cm2 Active Area.

Perovskite solar modules (PSMs) have been attracting the photovoltaic market, owing to low manufacturing costs and process versatility. The employment of flexible substrates gives the chance to explore new applications and further increase the fabrication throughput. However, the present state-of-the-art of flexible perovskite solar modules (FPSMs) does not show any data on light-soaking stability, revealing that the scientific community is still far from the potential marketing of the product. During this work, we demonstrate, for the first time, an outstanding light stability of FPSMs over 1000 h considering the recovering time (T80 = 730 h), exhibiting a power conversion efficiency (PCE) of 10.51% over a 15.7 cm2 active area obtained with scalable processes by exploiting blade deposition of a transporting layer and a stable double-cation perovskite (cesium and formamidinium, CsFA) absorber.

Designing New Indene-Fullerene Derivatives as Electron-Transporting Materials for Flexible Perovskite Solar Cells.

The synthesis and characterization of a family of indene-C60 adducts obtained via Diels-Alder cycloaddition [4 + 2] are reported. The new C60 derivatives include indenes with a variety of functional groups. These adducts show lowest unoccupied molecular orbital energy levels to be at the right position to consider these compounds as electron-transporting materials for planar heterojunction perovskite solar cells. Selected derivatives were applied into inverted (p-i-n configuration) perovskite device architectures, fabricated on flexible polymer substrates, with large active areas (1 cm2). The highest power conversion efficiency, reaching 13.61%, was obtained for the 6'-acetamido-1',4'-dihydro-naphtho[2',3':1,2][5,6]fullerene-C60 (NHAc-ICMA). Spectroscopic characterization was applied to visualize possible passivation effects of the perovskite's surface induced by these adducts.

Application of Crowd Simulations in the Evaluation of Tracking Algorithms.

Tracking and action-recognition algorithms are currently widely used in video surveillance, monitoring urban activities and in many other areas. Their development highly relies on benchmarking scenarios, which enable reliable evaluations/improvements of their efficiencies. Presently, benchmarking methods for tracking and action-recognition algorithms rely on manual annotation of video databases, prone to human errors, limited in size and time-consuming. Here, using gained experiences, an alternative benchmarking solution is presented, which employs methods and tools obtained from the computer-game domain to create simulated video data with automatic annotations. Presented approach highly outperforms existing solutions in the size of the data and variety of annotations possible to create. With proposed system, a potential user can generate a sequence of random images involving different times of day, weather conditions, and scenes for use in tracking evaluation. In the design of the proposed tool, the concept of crowd simulation is used and developed. The system is validated by comparisons to existing methods.

Assessment of Local Dynamic Stability in Gait Based on Univariate and Multivariate Time Series.

The ability of the locomotor system to maintain continuous walking despite very small external or internal disturbances is called local dynamic stability (LDS). The importance of the LDS requires constantly working on different aspects of its assessment method which is based on the short-term largest Lyapunov exponent (LLE). A state space structure is a vital aspect of the LDS assessment because the algorithm of the LLE computation for experimental data requires a reconstruction of a state space trajectory. The gait kinematic data are usually one- or three-dimensional, which enables to construct a state space based on a uni- or multivariate time series. Furthermore, two variants of the short-term LLE are present in the literature which differ in length of a time span, over which the short-term LLE is computed. Both a state space structure and the consistency of the observations based on values of both short-term LLE variants were analyzed using time series representing the joint angles at ankle, knee, and hip joints. The short-term LLE was computed for individual joints in three state spaces constructed on the basis of either univariate or multivariate time series. Each state space revealed walkers' locally unstable behavior as well as its attenuation in the current stride. The corresponding conclusions made on the basis of both short-term LLE variants were consistent in ca. 59% of cases determined by a joint and a state space. Moreover, the authors present an algorithm for estimation of the embedding dimension in the case of a multivariate gait time series.

Evidence of Nitrogen Contribution to the Electronic Structure of the CH3 NH3 PbI3 Perovskite.

Despite fast development of hybrid perovskite solar cells, there are many fundamental questions related to the perovskite film which remain open. For example, there are contradicting theoretical reports on the role of the organic methylammonium cation (CH3 NH3+ ) in the methylammonium lead triiodide (CH3 NH3 PbI3 ) perovskite film. From one side it is reported that the organic cation does not contribute to electronic structure of the CH3 NH3 PbI3 film. From the other side, valence band maximum fluctuations, dependent on the CH3 NH3+ rotation, have been theoretically predicted. The resonant X-ray photoelectron spectroscopy results reported here show experimental evidence of nitrogen contribution to the CH3 NH3 PbI3 electronic structure. Moreover, the observed strong resonances of nitrogen with the I 5s and the Pb 5d-6s levels indicate that the CH3 NH3 PbI3 valence band is extended up to ≈18 eV below the Fermi energy, and therefore one should also consider these shallow core levels while modeling its electronic structure.

Analysis of facial expressions in patients with schziophrenia, in comparison with a healthy control - case study.

INTRODUCTION: Deficits in area of communication, crucial for maintaining proper social bonds, may have a prominent adverse impact on quality of life in patients with schizophrenia. Social exclusion, lack of employment and deterioration of family life, may be consequences of aggravated social competencies, caused by inability to properly exhibit and interpret facial expressions. Although this phenomenon is known since first clinical descriptions of schizophrenia, lack of proper methodology limited our knowledge in this area. Aim of our study was to compare facial expressivity of the patient with schizophrenia, and the healthy individual. METHODS: 47-years old patient suffering from schizophrenia, and 36-years old healthy individual were invited to participate in our study. They underwent the examination in Human Facial Modelling Lab in Polish-Japanese Institute of Information Technology in Bytom (Silesia, Katowice). Both participants were presented with two video materials, first one contained different facial expressions, which they had to imitate. Second one a part of comedy show, during which spontaneous reactions were recorded. Acquisition of facial expressions was conducted with marker-based technology of modelling. Obtained data was analyzed using Microsoft Excel. RESULTS AND CONCLUSIONS: An overall facial expression intensity, expressed as an average value of distances traveled by markers during shifts from neutral position was higher in case of a healthy participant during both part of the study. The difference was especially visible in case of an upper half of the face. Utilization of marker-based methods in analysis of human facial expressions seem to be reliable and remarkably accurate.

Inertial Motion Capture Costume Design Study.

The paper describes a scalable, wearable multi-sensor system for motion capture based on inertial measurement units (IMUs). Such a unit is composed of accelerometer, gyroscope and magnetometer. The final quality of an obtained motion arises from all the individual parts of the described system. The proposed system is a sequence of the following stages: sensor data acquisition, sensor orientation estimation, system calibration, pose estimation and data visualisation. The construction of the system's architecture with the dataflow programming paradigm makes it easy to add, remove and replace the data processing steps. The modular architecture of the system allows an effortless introduction of a new sensor orientation estimation algorithms. The original contribution of the paper is the design study of the individual components used in the motion capture system. The two key steps of the system design are explored in this paper: the evaluation of sensors and algorithms for the orientation estimation. The three chosen algorithms have been implemented and investigated as part of the experiment. Due to the fact that the selection of the sensor has a significant impact on the final result, the sensor evaluation process is also explained and tested. The experimental results confirmed that the choice of sensor and orientation estimation algorithm affect the quality of the final results.

REmote SUpervision to Decrease HospitaLization RaTe. Unified and integrated platform for data collected from devices manufactured by different companies: Design and rationale of the RESULT study.

The number of patients with heart failure implantable cardiac electronic devices (CIEDs) is growing. Hospitalization rate in this group is very high and generates enormous costs. To avoid the need for hospital treatment, optimized monitoring and follow-up is crucial. Remote monitoring (RM) has been widely put into practice in the management of CIEDs but it may be difficult due to the presence of differences in systems provided by device manufacturers and loss of gathered data in case of device reimplantation. Additionally, conclusions derived from studies about usefulness of RM in clinical practice apply to devices coming only from a single company. An integrated monitoring platform allows for more comprehensive data analysis and interpretation. Therefore, the primary objective of Remote Supervision to Decrease Hospitalization Rate (RESULT) study is to evaluate the impact of RM on the clinical status of patients with ICDs or CRT-Ds using an integrated platform. Six hundred consecutive patients with ICDs or CRT-Ds implanted will be prospectively randomized to either a traditional or RM-based follow-up model. The primary clinical endpoint will be a composite of all-cause mortality or hospitalization for cardiovascular reasons within 12 months after randomization. The primary technical endpoint will be to construct and evaluate a unified and integrated platform for the data collected from RM devices manufactured by different companies. This manuscript describes the design and methodology of the prospective, randomized trial designed to determine whether remote monitoring using an integrated platform for different companies is safe, feasible, and efficacious (ClinicalTrials.gov Identifier: NCT02409225).

Efficient and Air-Stable Mixed-Cation Lead Mixed-Halide Perovskite Solar Cells with n-Doped Organic Electron Extraction Layers.

Air-stable doping of the n-type fullerene layer in an n-i-p planar heterojunction perovskite device is capable of enhancing device efficiency and improving device stability. Employing a (HC(NH2 )2 )0.83 Cs0.17 Pb(I0.6 Br0.4 )3 perovskite as the photoactive layer, glass-glass laminated devices are reported, which sustain 80% of their "post burn-in" efficiency over 3400 h under full sun illumination in ambient conditions.

Room-Temperature Atomic Layer Deposition of Al2 O3 : Impact on Efficiency, Stability and Surface Properties in Perovskite Solar Cells.

In this work, solar cells with a freshly made CH3 NH3 PbI3 perovskite film showed a power conversion efficiency (PCE) of 15.4 % whereas the one with 50 days aged perovskite film only 6.1 %. However, when the aged perovskite was covered with a layer of Al2 O3 deposited by atomic layer deposition (ALD) at room temperature (RT), the PCE value was clearly enhanced. X-ray photoelectron spectroscopy study showed that the ALD precursors are chemically active only at the perovskite surface and passivate it. Moreover, the RT-ALD-Al2 O3 -covered perovskite films showed enhanced ambient air stability.

C60 as an Efficient n-Type Compact Layer in Perovskite Solar Cells.

Organic-inorganic halide perovskite solar cells have rapidly evolved over the last 3 years. There are still a number of issues and open questions related to the perovskite material, such as the phenomenon of anomalous hysteresis in current-voltage characteristics and long-term stability of the devices. In this work, we focus on the electron selective contact in the perovskite solar cells and physical processes occurring at that heterojunction. We developed efficient devices by replacing the commonly employed TiO2 compact layer with fullerene C60 in a regular n-i-p architecture. Detailed spectroscopic characterization allows us to present further insight into the nature of photocurrent hysteresis and charge extraction limitations arising at the n-type contact in a standard device. Furthermore, we show preliminary stability data of perovskite solar cells under working conditions, suggesting that an n-type organic charge collection layer can increase the long-term performance.

Employing PEDOT as the p-Type Charge Collection Layer in Regular Organic-Inorganic Perovskite Solar Cells.

Organic-inorganic halide perovskite solar cells have recently emerged as high-performance photovoltaic devices with low cost, promising for affordable large-scale energy production, with laboratory cells already exceeding 20% power conversion efficiency (PCE). To date, a relatively expensive organic hole-conducting molecule with low conductivity, namely spiro-OMeTAD (2,2',7,7'-tetrakis(N,N-di-p-methoxyphenyl-amine) 9,9'- spirobifluorene), is employed widely to achieve highly efficient perovskite solar cells. Here, we report that by replacing spiro-OMeTAD with much cheaper and highly conductive poly(3,4-ethylenedioxythiophene) (PEDOT) we can achieve PCE of up to 14.5%, with PEDOT cast from a toluene based ink. However, the stabilized power output of the PEDOT-based devices is only 6.6%, in comparison to 9.4% for the spiro-OMeTAD-based cells. We deduce that accelerated recombination is the cause for this lower stabilized power output and postulate that reduced levels of p-doping are required to match the stabilized performance of Spiro-OMeTAD. The entirely of the materials employed in the perovskite solar cell are now available at commodity scale and extremely inexpensive.

Phosphonic anchoring groups in organic dyes for solid-state solar cells.

We report the synthesis and the optoelectronic characterization of three new 4H-pyran-4-ylidene and thiazole derivatives (pyt) as metal-free organic dyes for solid-state dye-sensitized solar cells (DSSCs). We investigate the performance and the long-term stability of devices employing pyt dyes functionalized with carboxylic and phosphonic acids as TiO2 anchoring groups. In contrast to reports on liquid electrolyte DSSCs, we show that solid-state DSSCs prepared with phosphoric pyt derivatives can achieve similar power conversion efficiency to their carboxyl analogues. We make use of the Mott-Schottky analysis and equivalent circuit models to demonstrate that a phosphonic group induces a significant increase in built-in voltage at the TiO2-hole transporter interface, which results in a higher open circuit voltage.

Enhanced Amplified Spontaneous Emission in Perovskites Using a Flexible Cholesteric Liquid Crystal Reflector.

Organic-inorganic perovskites are highly promising solar cell materials with laboratory-based power conversion efficiencies already matching those of established thin film technologies. Their exceptional photovoltaic performance is in part attributed to the presence of efficient radiative recombination pathways, thereby opening up the possibility of efficient light-emitting devices. Here, we demonstrate optically pumped amplified spontaneous emission (ASE) at 780 nm from a 50 nm-thick film of CH3NH3PbI3 perovskite that is sandwiched within a cavity composed of a thin-film (∼7 µm) cholesteric liquid crystal (CLC) reflector and a metal back-reflector. The threshold fluence for ASE in the perovskite film is reduced by at least two orders of magnitude in the presence of the CLC reflector, which results in a factor of two reduction in threshold fluence compared to previous reports. We consider this to be due to improved coupling of the oblique and out-of-plane modes that are reflected into the bulk in addition to any contributions from cavity modes. Furthermore, we also demonstrate enhanced ASE on flexible reflectors and discuss how improvements in the quality factor and reflectivity of the CLC layers could lead to single-mode lasing using CLC reflectors. Our work opens up the possibility of fabricating widely wavelength-tunable "mirror-less" single-mode lasers on flexible substrates, which could find use in applications such as flexible displays and friend or foe identification.

Heterojunction modification for highly efficient organic-inorganic perovskite solar cells.

Organic-inorganic perovskites, such as CH3NH3PbX3 (X=I, Br, Cl), have emerged as attractive absorber materials for the fabrication of low cost high efficiency solar cells. Over the last 3 years, there has been an exceptional rise in power conversion efficiencies (PCEs), demonstrating the outstanding potential of these perovskite materials. However, in most device architectures, including the simplest thin-film planar structure, a current-voltage response displays an "anomalous hysteresis", whereby the power output of the cell varies with measurement time, direction and light exposure or bias history. Here we provide insight into the physical processes occurring at the interface between the n-type charge collection layer and the perovskite absorber. Through spectroscopic measurements, we find that electron transfer from the perovskite to the TiO2 in the standard planar junction cells is very slow. By modifying the n-type contact with a self-assembled fullerene monolayer, electron transfer is "switched on", and both the n-type and p-type heterojunctions with the perovskite are active in driving the photovoltaic operation. The fullerene-modified devices achieve up to 17.3% power conversion efficiency with significantly reduced hysteresis, and stabilized power output reaching 15.7% in the planar p-i-n heterojunction solar cells measured under simulated AM 1.5 sunlight.

A transparent conductive adhesive laminate electrode for high-efficiency organic-inorganic lead halide perovskite solar cells.

A self-adhesive laminate solar-cell electrode is presented based on a metal grid embedded in a polymer film (x-y conduction) and set in contact with the active layer using a pressure-sensitive adhesive containing a very low quantity (1.8%) of organic conductor, which self-organizes to provide z conduction to the grid. This ITO-free material performs in an identical fashion to evaporated gold in high-efficiency perovskite solar cells.