RESUMO
It is a challenging and meaningful task to carry out UAV-based livestock monitoring in high-altitude (more than 4500 m on average) and cold regions (annual average - 4 °C) on the Qinghai Tibet Plateau. The purpose of artificial intelligence (AI) is to execute automated tasks and to solve practical problems in actual applications by combining the software technology with the hardware carrier to create integrated advanced devices. Only in this way, the maximum value of AI could be realized. In this paper, a real-time tracking system with dynamic target tracking ability is proposed. It is developed based on the tracking-by-detection architecture using YOLOv7 and Deep SORT algorithms for target detection and tracking, respectively. In response to the problems encountered in the tracking process of complex and dense scenes, our work (1) Uses optical flow to compensate the Kalman filter, to solve the problem of mismatch between the target bounding box predicted by the Kalman filter (KF) and the input when the target detection in the current frame is complex, thereby improving the prediction accuracy; (2) Using a low confidence trajectory filtering method to reduce false positive trajectories generated by Deep SORT, thereby mitigating the impact of unreliable detection on target tracking. (3) A visual servo controller has been designed for the Unmanned Aerial Vehicle (UAV) to reduce the impact of rapid movement on tracking and ensure that the target is always within the field of view of the UAV camera, thereby achieving automatic tracking tasks. Finally, the system was tested using Tibetan yaks on the Qinghai Tibet Plateau as tracking targets, and the results showed that the system has real-time multi tracking ability and ideal visual servo effect in complex and dense scenes.
RESUMO
Enhanced animal welfare has emerged as a pivotal element in contemporary precision animal husbandry, with bovine monitoring constituting a significant facet of precision agriculture. The evolution of intelligent agriculture in recent years has significantly facilitated the integration of drone flight monitoring tools and innovative systems, leveraging deep learning to interpret bovine behavior. Smart drones, outfitted with monitoring systems, have evolved into viable solutions for wildlife protection and monitoring as well as animal husbandry. Nevertheless, challenges arise under actual and multifaceted ranch conditions, where scale alterations, unpredictable movements, and occlusions invariably influence the accurate tracking of unmanned aerial vehicles (UAVs). To address these challenges, this manuscript proposes a tracking algorithm based on deep learning, adhering to the Joint Detection Tracking (JDT) paradigm established by the CenterTrack algorithm. This algorithm is designed to satisfy the requirements of multi-objective tracking in intricate practical scenarios. In comparison with several preeminent tracking algorithms, the proposed Multi-Object Tracking (MOT) algorithm demonstrates superior performance in Multiple Object Tracking Accuracy (MOTA), Multiple Object Tracking Precision (MOTP), and IDF1. Additionally, it exhibits enhanced efficiency in managing Identity Switches (ID), False Positives (FP), and False Negatives (FN). This algorithm proficiently mitigates the inherent challenges of MOT in complex, livestock-dense scenarios.
Assuntos
Algoritmos , Animais , Bovinos , Criação de Animais Domésticos/métodos , Dispositivos Aéreos não Tripulados , Bem-Estar do Animal , Aprendizado ProfundoRESUMO
A composite solid chloride sensor consisting of two single sensors, i.e., Ag/AgCl working electrode and Mn/MnO2 reference electrode, was developed. The Ag/AgCl electrode was prepared by the anodic polarization method, while the Mn/MnO2 reference electrode was prepared using the powder compaction technique. Then, the electrochemical performances such as stability, reproducibility, and sensitivity of the composite and single sensors were investigated in a saturated Ca(OH)2 solution and mortar specimen. A current density of 0.5 mA/cm2 and polarization time of 2.5 h were the optimal preparation parameters of the Ag/AgCl selective electrode. The Ag/AgCl selective electrode showed a linear potential response with the logarithm of chloride ion content in solution and had good stability, reproducibility, and anti-polarization performances. In addition, the Mn/MnO2 electrode exhibited potential stability after being activated in an alkaline solution for 60 days. The composite sensor demonstrated exceptional sensitivity to the Cl- content, boasting a slope of approximately 51.1 mV/decade, and showcased excellent stability in both solution and mortar specimens. In every measurement, the time needed for the potential of a composite sensor to become stable was less than 30 s. The sensor enables non-destructive in situ monitoring of the chloride ion content in cement mortar, thus realizing early warning of deterioration of reinforcement and guaranteeing long service life of the structure.
RESUMO
The performance of alkali-activated slag (AAS) under thermal treatment has received particular attention. In this study, the effect of five elevated temperatures (25, 200, 400, 600, and 800 °C) and two cooling methods (air cooling and water spraying) on the mechanical and durability properties, microstructure, and phase evolution of AAS was investigated. The results show that AAS mortars exhibit higher resistance to thermal attack than OPC in terms of strength and durability. AAS samples cooled in air show higher residual strength than those cooled by spraying water, which is mainly attributed to fewer cracks formed in the former. The resistance to carbonization of exposed AAS mortars depends on the pore size distribution, while that to chloride ion penetration depends on the porosity. Cooling methods show a minor effect on the phase evolution of reaction products, suggesting that the microstructure degradation is mainly responsible for the damage of AAS structures. This study provides fundamental knowledge for the thermally induced changes on AAS which contributes new ideas for the development of construction structures with higher fire resistance.
RESUMO
In order to better predict the development of shrinkage deformation of steam-cured concrete mixed with slag, a deformation-temperature-humidity integrated model test, a hydration heat test, and an elastic modulus test were performed. The effects of the steam-curing process and the content of slag on shrinkage deformation, hydration degree and elastic modulus of concrete were studied. The results indicate that during the steam-curing process, the concrete has an "expansion-shrinkage" pattern. After the steam curing, the deformation of concrete is dominated by drying shrinkage. After the addition of slag, the shrinkage deformation of steam-cured concrete is increased. The autogenous shrinkage increases by 0.5-12%, and the total shrinkage increases by 1.5-8% at 60 days. At the same time, slag reduces the hydration degree of steam-cured concrete and modulus of elasticity. A prediction model for the hydration degree of steam-cured concrete is established, which can be used to calculate the degree of hydration at any curing age. Based on the capillary tension generated by the capillary pores in concrete, an integrated model of autogenous shrinkage and total shrinkage is established with the relative humidity directly related to the water loss in the concrete as the driving parameter. Whether the shrinkage deformation is caused by hydration reaction or the external environment, this model can better predict the shrinkage deformation of steam-cured concrete.
RESUMO
Traditional cement-based repair materials are brittle and prone to cracking. The failure of more than half of repaired concrete structure is due to the re-cracking of the repair material itself or delamination and peeling from the concrete matrix. Thus, a second repair is required in a short period, increasing the maintenance cost. To reduce cracking, Strain Hardening Cement-based Composite (SHCC), with strain hardening and multiple cracking property, is prepared to study the influence of interface roughness and repair layer thickness on the shrinkage, cracking and delamination modes of SHCC-repaired concrete beams. The results show that under the shrinkage stress, multiple fine cracks instead of local fractures occur in the SHCC repair layer, and the interfacial delamination is effectively controlled. Interfacial bonding property is the main factor that affects the shrinkage and deformation coordination of SHCC-repaired beams. When the interface roughness is different, the crack width of the SHCC repair layer is similar. However, it has a greater influence on the interfacial delamination length and maximum delamination height of the repaired beam. With the increase of interface roughness, the delamination length and height of the repaired beam are greatly reduced. Therefore, before using SHCC to repair the existing structures or components, the bonding surface should be roughened to improve the bond strength between SHCC and the old concrete. With the increase of the repair layer thickness, the cracking and delamination of the repair layer tend to be alleviated. Although the crack width of the repair layer can be effectively controlled after cracking, the overlarge shrinkage (985.35 × 10-6, about twice the shrinkage value of ordinary concrete) of the SHCC prepared in this research results in the cracking of the repair layer and the delamination of the repair interface under the restraint of concrete; thus, SHCC fails to repair the concrete efficiently. In terms of shrinkage deformation control, materials with high toughness and low shrinkage are required to repair the existing concrete structures. The implication of this research may provide a theoretical basis for the preparation and application of SHCC with high toughness and low shrinkage.
RESUMO
Architectural concrete has been wildly used nowadays, and those served in an offshore environment often suffer from chloride penetration and carbonation. To assess the protection and decoration performances of architectural concrete, this study exposed architectural concrete to actual marine environments and accelerated carbonation conditions. The chloride and carbonation resistance of architectural concrete was determined to evaluate the protection performance, and the corresponding surface-color-consistency was adopted to characterize its decoration performance. The results show that the total and free chloride of concrete in the marine atmosphere zone and the tidal zone generally decreases with depth; chloride content arguments significantly with exposure time, with a chloride maximum peak near the surface. Moreover, the chloride diffusion coefficient is small throughout the measurements, indicating the superior chloride resistance of architectural concrete. Furthermore, architectural concrete also possesses excellent carbonation resistance based on the carbonation depth data obtained from the carbonation experiment. Therefore, architecture concrete served as protection covers can withstand both the chloride attack and carbonation tested in this paper. In addition, carbonation was found to have a profound influence on the aesthetics of architectural concrete. Therefore, carbonation should be carefully handled for better maintaining the aesthetic appearance of architectural concrete in long-term service.
RESUMO
Porous metal foams have been one of the most sought-after materials owing to their combination of bulk metallic characteristics (e.g., thermal/electrical conductivity and ductility) and nanometric size-effect properties (e.g., catalytic reactivity, plasmonic behavior, and high surface area). Traditional sol-gel approaches, though one of the most frequently used method to produce mesoporous metal foams, were hindered for scalable production and wide applications because of its tedious multistep procedure, time-consuming gelation time, and polydisperse pore sizes. Herein, by depositing biological nanofibrils (chitin, cellulose, and silk) on commercial filtration membranes, we report a facile approach to sieve and recycle sub-6 nm nanoparticles of noble metals (Au and Pt) via nonclogging filtration into three-dimensional (3D) networks with interconnected mesopores. The porous networks could withstand air-drying, in contrast to freezing/supercritical drying conventionally used for mesoporous foams preparation. This approach was also applicable to both mesoporous monometallic (Au, Pt) and bimetallic (Au-Pt) foams. Moreover, the resultant mesoporous metallic foams show high porosity up to 90%, homogeneous mesoporous structure, and metallic conductivity up to 104 S/cm. Thus, this rapid and scalable sieving procedure not only offers a possibility of sieving noncloggingly for efficient recovery of metal nanoparticles but also starts a pathway to produce conductive and flexible mesoporous foams applicable in broad fields such as continuous flow catalysis and smart actuating.
Assuntos
Celulose/química , Quitina/química , Nanopartículas Metálicas/química , Nanofibras/química , Seda/química , Condutividade Elétrica , Ouro/química , Tamanho da Partícula , Platina/química , Porosidade , Propriedades de SuperfícieRESUMO
Iridium oxide pH electrodes employing the carbonate melt oxidation method were fabricated with oxidation temperatures of 750 °C, 800 °C and 850 °C, respectively. Scanning electron microscope (SEM) and atomic force microscope (AFM) images showed that the oxide film regularized with the increase in oxidation temperatures. The pH response, response time and long-term stability of the electrodes indicated that the electrodes made at 850 °C had the best performance. X-ray photoelectron spectra (XPS) surveys investigated the change in the electrodes' chemical composition and element oxidation states at 850 °C, and the results showed that the relative content of Ir3+ had increased by 23.9%, and the Ir4+ and Ir6+ had decreased by 10.9% and 13%, respectively, in the surface oxide layer after one month of aging. However, the relative contents of Ir3+, Ir4+ and Ir6+ were almost constant for the inner oxide layer. Meanwhile, the XPS result also indicated that the outer oxide layer of the electrode had a higher hydration degree than the inner oxide layer.
RESUMO
In this study, we examined the influence of moisture content on the electromagnetic response of concrete. A novel homemade electromagnetic monitoring apparatus was developed and used to evaluate the Hall effect voltage at both ends of concrete based on our previous study of the Hall effect. We used four different concrete mix water/binder ratios: 0.30, 0.28, 0.26, and 0.24, and three conditions (relative humidity, carbonation, and water absorption) were examined in this experiment. The results show that the moisture content inside concrete influences the relative permeability of concrete. The variation in the Hall effect voltage is more influenced by carbonation than changes in relative humidity; water absorption increases the Hall effect voltage the least amongst the other examined factors. According to the experiment, a calibration system was established, and the relevant correction factors are provided.
RESUMO
As a promising layered double hydroxide, Friedel's salt has gained popularity. The transport and adsorption behavior of ions and water molecules at the interface is the basis for investigating the durability of concrete, in marine environments in particular. In this paper, the transport behavior of water and ions in the nanopores of Friedel's salt and the adsorption mechanism of the ions were systematically investigated by molecular dynamics. The water molecules share a larger bulk density and good orientations at the interface while the adsorption rate of chloride ions climbs to 66.62%, owing to the desorption of the surface structural anions forming Ca-Clw ion clusters. The time correlation function was employed to examine the stability of the Ca-Clw bonds formed near the Friedel's salt interface. The Ca-Clw bonds were demonstrated to be very stable, implying that the aqueous chloride ion is difficult to desorb once it is adsorbed by the interface. The surface of the ordered Friedel's salt structure could form a hydrated shell to hinder the interaction between sodium ions and oxygen atoms. In addition, Friedel's salt exhibits a poor adsorption capacity for sodium ions since it provides few adsorption sites due to the limited amount of structural chloride ions. After all, the interaction between Friedel's salt and the external environment on the nano scale was explored for a better understanding of the inherent mechanism from a molecular simulation perspective.
RESUMO
This study comparably assessed the pozzolanic effect of silica fume (SF) and ground rice husk ash (RHA) as supplementary cementing materials on the properties of blended cement pastes and concretes. A commonly commercial silica fume (SF) and locally-produced rice husk ash (RHA) samples with two finenesses (one with larger size than cement and the other with smaller size than cement) were used in this study. Material properties of SF and RHA were experimentally characterized. Hydration and mechanical properties of cement pastes incorporating SF and RHA were determined by thermogravimetric analysis (TGA) and compressive strength tests, respectively. Properties of concretes regarding workability, mechanical property, durability, and microstructure were evaluated. Results showed that, although the finely ground RHA used in this study possessed lower SiO2 content and higher particle size compared to SF, it exhibited comparable pozzolanic reactivity with SF due to the nano-scale pores on its each single particle, leading to a higher specific surface area. The optimal replacement levels of SF and RHA were 10% by weight of cement in pastes and concretes. Although addition of SF and RHA led to a significant reduction in slump for the fresh mixtures, inclusion of up to 30% of SF or 15% of ground RHA did not adversely affect the strength of concretes. At the same mix, incorporation of finely-ground RHA in cement composites provided comparable mechanical properties, hydration degree, and durability with SF blended cement composites, owing to the porous structure and high specific surface area of RHA particles. Microstructure morphology analysis of concretes explored by scanning electron microscopy (SEM) further validated the strength and the durability test results.