Complex Objects Research Articles

Thermal response function method: A method for predicting the transient surface temperature of black-box objects

In engineering practice, thermal analysis of objects with unknown internal structure and/or thermophysical properties, and uncertainties in contact thermal resistances, is very challenging and even impossible using the traditional approach of direct solving the heat transfer equation. In this work, a thermal response function method (TRFM) is proposed for predicting the transient surface temperature of ‘black-box’ objects (i.e., unknown internal structure and thermophysical properties). The method relies on an introduced measurable quantity called thermal response function, which characterizes the thermal response characteristics of an object. Using the measured thermal response functions as input parameters, the transient temperature distribution on the surface of a black-box object under arbitrary external heat flux boundary condition can be predicted through linear superposition. Proof-of-concept simulations and experiments are conducted to demonstrate the feasibility and effectiveness of the TRFM method. The predicted surface temperature distribution under various external heat fluxes using TRFM agree well with the reference results. The results show that the TRFM is very promising as a solution of the challenging problem of predicting the transient surface temperature of black-box objects, with potential application for thermal imaging modeling of complex objects.

Evaluation on Different Object Selection Visual Feedback in Collaborative Augmented Reality

Collaborative Augmented Reality (CAR) involves multiple users working together in an augmented reality setting to accomplish tasks. In CAR, transparent techniques enable users to see occluded objects in complex environments, yet they often struggle to discern which part of a complex object they have selected. Workspace awareness refers to understanding how others interact within a shared workspace and influence the choice of visualization techniques. This study investigated workspace awareness regarding different object selection visual feedback in co-located CAR. It explored four technique variations: Hi (highlight), Hi-Ray (ray emitting), Hi-View (view switching), and Hi-RV (ray emitting and view switching). Thirty-two participants were divided into 16 pairs, with an instructor demonstrating how to assemble an engine component and a student replicating the process using the four visualization techniques. Results showed the visualization techniques did not affect task completion time significantly. The Hi and Hi-Ray technique had the highest error rate, while the Hi-RV technique had the lowest. However, users preferred the Hi-View technique, which scored highest in interaction, collaboration quality, workspace awareness, and required less workload. To enhance awareness, participants pointed out the weakness in the combination of visual feedback, particularly with the ray emitting technique, which causes confusion when multiple objects are selected due to visual clutter. They suggested that integrating audio feedback could help alert users to their choices, and using color-based indicators could distinguish different actions, such as indicating correct or incorrect placement of virtual objects.

Meta Shack–Hartmann wavefront sensor with large sampling density and large angular field of view: phase imaging of complex objects

Shack–Hartmann wavefront sensors measure the local slopes of an incoming wavefront based on the displacement of focal spots created by a lenslet array, serving as key components for adaptive optics for astronomical and biomedical imaging. Traditionally, the challenges in increasing the density and the curvature of the lenslet have limited the use of such wavefront sensors in characterizing slowly varying wavefront structures. Here, we develop a metasurface-enhanced Shack–Hartmann wavefront sensor (meta SHWFS) to break this limit, considering the interplay between the lenslet parameters and the performance of SHWFS. We experimentally validate the meta SHWFS with a sampling density of 5963 per mm2 and a maximum acceptance angle of 8° which outperforms the traditional SFWFS by an order of magnitude. Furthermore, to the best of our knowledge, we demonstrate the first use of a wavefront sensing scheme in single-shot phase imaging of highly complex patterns, including biological tissue patterns. The proposed approach opens up new opportunities in incorporating exceptional light manipulation capabilities of the metasurface platform in complex wavefront characterization.

Recognition of Organic Waste Objects Based on Vision Systems Using Attention Convolutional Neural Networks Models

Purpose: High population growth and increasing consumption patterns have resulted in significant organic waste production. The public often does not understand the correct way to deal with the problem of organic waste, including public awareness regarding the need for its management. Therefore, a system is needed to recognize waste objects based on various types. Currently, much research in this field has been studying object recognition, for example, the implementation of the Convolutional Neural Networks (CNN) model. However, there are still various challenges that must be addressed, including objects with diverse visual characteristics such as form, size, color, and physical condition. This research focuses on developing a system that enhances object recognition of waste, specifically organic waste, using an Attention Convolutional Neural Network (ACNN). By integrating attention mechanisms into the CNN model, this study addresses the challenges of recognizing waste objects with diverse visual characteristics. The proposed system seeks to improve the accuracy and efficiency of organic waste identification, which is crucial for advancing waste management practices and reducing environmental impact. Methods: This research combines a CNN architecture with an attention mechanism to create a better object detection environment called Attention-CNN (ACNN). The ACNN architecture employed consists of one layer input, three convoluted layers, three max-pooling layers, one attention layer, one flattened layer, four dropout layers, and two dense layers arranged in a certain way. Result: The research result shows that the model CNN with attention mechanism (ACNN) was slightly better at 86.93% than the standard model of CNN, which accounted for 86.70% in accuracy. Novelty: In general, the current use of CNN architecture to address waste object recognition problems typically employs standard architectures, resulting in lower accuracy for complex waste objects. In contrast, our research integrates attention mechanisms into the CNN architecture (ACNN), enhancing the model's ability to focus on relevant features of waste objects. This leads to improved recognition accuracy and robustness against visual variability. This distinction is important as it overcomes the limitations of standard CNN models in handling visually diverse and complex waste objects, thereby highlighting the novelty and contribution of our research.

Cloud structure and young star distribution in the Dragonfish complex

Context.Star formation is a complex process involving several physical mechanisms that interact with each other at different spatial scales. One way to shed some light on this process is to analyse the relation between the spatial distributions of gas and newly formed stars. In order to obtain robust results, it is necessary for this comparison to be made using quantitative and consistent descriptors that are applied to the same star-forming region.Aims.We used fractal analysis to characterise and compare in a self-consistent way the structure of the cloud and the distribution of young stellar objects (YSO) in the Dragonfish star-forming complex.Methods.Different emission maps of the Dragonfish nebula were retrieved from the NASA/IPAC Infrared Science and thePlanckLegacy archives. Moreover, we used photometric information from the AllWISE catalogue to select a total of 1082 YSOs in the region. We derived the physical properties for some of these from their spectral energy distributions (SEDs). For the cloud images and YSOs, the three-dimensional fractal dimension (Df) was calculated using previously developed and calibrated algorithms.Results.The fractal dimension of the Dragonfish nebula (Df= 2.6–2.7) agrees very well with values previously obtained for the Orion, Ophiuchus, and Perseus clouds. On the other hand, YSOs exhibit a significantly lower value on average (Df= 1.9–2.0), which indicates that their structure is far more clumpy than the material from which they formed. Younger Class I and Class II sources have lower values (Df= 1.7 ± 0.1) than more evolved transition disk objects (Df= 2.2 ± 0.1), which shows a certain evolutionary effect according to which an initially clumpy structure tends to gradually disappear over time.Conclusions.The structure of the Dragonfish complex is similar to that of other molecular clouds in the Galaxy. However, we found clear and direct evidence that the clustering degree of the newly born stars is significantly higher than that of the parent cloud from which they formed. The physical mechanism behind this behaviour is still not clear.

The value of 3D printing model combined PCNL in kidney stones: a systematic review and meta-analysis.

With the continuous advancement of medical imaging, 3D printing technology is emerging. This technology allows for the representation of complex objects in a model form. This research aims to delve into the irreplaceable value of percutaneous nephrolithotomy (PCNL) in conjunction with 3D printed models in urinary stone surgery. This forward-looking approach provides doctors with a new perspective, enabling them to plan and execute surgeries with greater precision, ultimately delivering a safer and more efficient treatment experience for patients. We evaluated the literature on PCNL for the kidney stones with the introduction of 3D printing models and conducted a meta-analysis. The assessed parameters included stone clearance rate, operation time, hospital stay, blood loss, puncture accuracy, and the rate of complications. We systematically searched the EMBASE, PubMed, Cochrane Library, SCIE, and Chinese Biomedical Literature Search databases for articles related to PCNL (Percutaneous Nephrolithotomy) with 3D printing models from January 2000 to January 2023. Data were managed and screened using Excel . Meta-analysis was performed for operation time, stone clearance rate, blood loss, puncture accuracy, length of hospital stay, and complications in PCNL combined with 3D printing model for kidney stone treatment. The quality of included articles was assessed using the risk of bias tool by the Cochrane Collaboration. Sensitivity analysis was conducted to assess the reliability of the results. Data were recorded using StataSE 17 software, and publication bias was examined using Egger's linear regression test. We followed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines to conduct a systematic search and screening of literature relevant to the use of 3D printed models in the treatment of kidney stones. We conducted an extensive literature search across several major academic databases, including EMBASE, PubMed, Cochrane Library, SCIE, and Chinese Biomedical Literature Search databases, to ensure comprehensive coverage of relevant studies. Following the PRISMA process of screening and analysis, we ultimately included 10 randomized controlled trials with a combined sample of 608 for systematic review. Across these studies, we identified the introduction of 3D printing models prior to surgery for kidney stones resulted in significant advantages for the experimental group compared to the control group in terms of operation time, stone clearance rates, puncture accuracy, hospital stay, blood loss, and the incidence of complications, providing valuable insights for further research and clinical practice.

Literature Review Application of YOLO Algorithm for Detection and Tracking

A vehicle tracking system is a computer program that utilizes devices to monitor the position, movement and condition of a vehicle or fleet of vehicles. Multi-vehicle tracking on highways has significant research interest and practical value in building intelligent transportation systems. Nevertheless, traffic road video frames consist of various complex backgrounds and objects. Detection and tracking are very challenging because foreground to background switching occurs frequently. One-stage algorithm approaches such as YOLO and its various variants have been proven to be accurate for detecting vehicles. Meanwhile, the SORT, DeepSORT, ByteTrack and other algorithms can be combined in YOLO. The aim of this study is to highlight existing research on the application of YOLO and its variants in detecting and tracking vehicles, especially in traffic management. The journals used are limited to 2019 – 2024 and the journal sources consist of Hindawi, IEEE, MDPI, Research Gate, Science Direct, and Springer. Based on the research that has been reviewed, the YOLO variant algorithm approach has been successfully applied in the field of vehicle monitoring to support smart cities. In addition, many new model combinations and improvements have been proposed, proving that this algorithm has a big influence in the field of computer vision.

Создание и развитие высоконадежных информационно-управляющих систем с элементами искусственного интеллекта для перспективных технологических комплексов

Methods and means of improving complex technological equipment are shown through the operational assessment of the quality of implemented technologies realtime. This is proved by the fact that implementing technological operations on universal equipment each time requires modeling dynamic processes and taking into account a large number of uncertainty factors that affect the geometry generation quality. It is not possible to be a priori aware of these factors. There is a need to create new information technologies with the possibilities of universal application for immediate understanding of various dynamic processes in diagnostic, identification and control systems. Standard computer systems for statistical analysis and optimization of dynamic processes with the possibilities of universal application for various implementations of modern technologies have been introduced. The possibility of using integrative criteria and methods of artificial intelligence for diagnostic systems, identification and control of advanced technological complexes is shown. The implementation of information systems for the management of complex objects of various technological purposes is presented. The proposed modeling methods and approaches have been tested at various machine-building enterprises when processing parts on turning, milling and grinding machines, both universal and CNC. The research results made it possible to implement new principles of automated control and optimal adjustment of technological processes in real time and create an automated system for evaluating their quality, which allows increasing the efficiency and reliability of management decisions by conducting optimization directly on operating equipment. Based on the methods and approaches described above, new results have been obtained in the implementation of plasma technologies for the modification of geometrically complex surfaces of mechanical engineering products aimed at increasing wear resistance, hardness and other technical characteristics of the working surfaces of precision engineering products. A fairly complete approbation of methods, approaches, procedures and decision-making criteria for various technologies allows them to be recommended for universal applicability.

Legal nature of the metaverse

Representing a network of virtual worlds, the metaverse ultimately forms a complex object of legal regulation due to the possibility of its normalization according to the provisions of different branches of law. The present work sets out to reveal the legal nature of the metaverse from a legal perspective. The selected methodology for determining its legal nature consists in comparing objects that are similar to the metaverse, but are already regulated by legal provisions. Such objects include the Internet, websites, multiplayer online video games, and virtual space in general. In order to identify their similarities and differences, the metaverse is compared to the specified objects. While the multifaceted nature of the metaverse permits its definition from a Russian legal perspective as information, as an object of intellectual property, or as a means of communication, the metaverse resembles the compared objects only in the most general way, while their differences are so significant that reducing its legal nature to only one of them does not fully account for its salient characteristics. By analogy with other spatial categories, but taking into account its specific features, the metaverse can be considered as a virtual space sui generis. While there is a lack of current legal regulation to support such a conclusion, future legislation of the metaverse should be built with this in mind.

Mutual capabilities: digital platforms in unpredictable pedagogical encounters

ABSTRACT This paper examines the implications of platforms as a repertoire for knowing and relating the intensities of pandemic restrictions on teaching and schoolwork. Building on platformisation in education, what work platforms do in unpredictable everyday pedagogical encounters is investigated. Specifically, the paper explores a methodological potential with platforms’ capabilities to pull some things together while supressing others. Drawing on ethnographic interviews with teachers and students in Sweden in 2021, everyday platform practices such as handling assignments, requests to connect online, and repetitive notifications are analysed with actor-network theory. Tensions of discomforts, resistance, and trust unfold critical acknowledgements of digital platforms as more complex objects than shaping pedagogical encounters prior to their practices. Instead, capabilities emerge as mutually rendered. The analysis shows that platforming well-bounded domains for clearer and more flexible teaching and schoolwork incoherently make educational practices less so, highlighting crucial openings to surprise and curiosity of pedagogical encounters.

MUSE spectroscopy of the high abundance discrepancy planetary nebula NGC\,6153

The abundance discrepancy problem in planetary nebulae (PNe) has long puzzled astronomers. NGC\,6153, with its high abundance discrepancy factor (ADF sim 10), provides a unique opportunity to study the chemical structure and ionisation processes within these objects. We aim to understand the chemical structure and ionisation processes in this high-ADF nebula by constructing detailed emission line maps and examining variations in electron temperature and density. This study also explores the discrepancies between ionic abundances derived from collisional and recombination lines, shedding light on the presence of multiple plasma components. We used the MUSE spectrograph to acquire IFU data covering the wavelength range 4600$-$9300 with a spatial sampling of 0.2 arcsec and spectral resolutions ranging from R = 1609 to R = 3506. We created emission line maps for 60 lines and two continuum regions. We developed a tailored methodology for the analysis of the data, including correction for recombination contributions to auroral lines and the contributions of different plasma phases. Our analysis confirmed the presence of a low-temperature plasma component in NGC\,6153. We find that electron temperatures derived from recombination line and continuum diagnostics are significantly lower than those derived from collisionally excited line diagnostics. Ionic chemical abundance maps were constructed, considering the weight of the cold plasma phase in the emission. Adopting this approach we found ionic abundances that could be up to 0.2 dex lower for those derived from CELs and up to 1.1 dex higher for those derived from RLs than in the case of a homogeneous emission. The abundance contrast factor (ACF) between both plasma components was defined, with values, on average, 0.9 dex higher than the ADF. Different methods for calculating ionisation correction factors (ICFs), including state-of-the-art literature ICFs and machine learning techniques, yielded consistent results. Our findings emphasise that accurate chemical abundance determinations in high-ADF PNe must account for multiple plasma phases. Future research should focus on expanding this methodology to a broader sample of PNe, with spectra deep enough to gather physical condition information of both plasma components, which will enhance our understanding of their chemical compositions and the underlying physical processes in these complex objects.

Моделирование системы очистки сточных вод животноводческих ферм

Among the sources of pollution of surface water bodies from agricultural activities, livestock, pig and poultry complexes can be prioritized, which are uncontrolled and diffuse sources of suspended solids, organic compounds, biogenic elements, heavy metals and pathogenic microflora, which causes biochemical pollution and has a particularly detrimental effect on the state of inland reservoirs. Wastewater from agricultural processing enterprises and household water from rural settlements with unpredictable pollutants play a significant role in pollution. The livestock sector is one of the largest consumers of water. The large number of animals in a confined space, the use of hydraulic harvesting systems when removing their waste products, leads to the formation of manure in significant quantities. Sanitary and hygienic standards in industrial premises are supported with the help of water – animals are washed with it, rooms are cleaned, and they are disinfected, food is prepared, dishes and equipment are washed, manure is washed off with water, and so on. Accordingly, as the demand for water in animal husbandry increases, the volume of wastewater discharge that contains manure into nearby water bodies increases. The effluents that are formed as a result of the activities of the livestock sector are classified as containing a large amount of harmful substances with a high concentration. Depending on the sources of pollution and the main pollutants, technical solutions should be developed to reduce the volume of wastewater and its treatment. The effectiveness of their functioning can be ensured with the help of modern information processing methods, using methods of system analysis of complex objects based on a mathematical description of the technological process. To analyze the state of the treatment system as a whole and predict the development of emergency situations, a software implementation of a wastewater treatment system for livestock farms was created.

Semantic segmentation algorithm for video from UAV based on adaptive keyframe scheduling via similarity measurement

Abstract Unmanned aerial vehicle (UAV) videos exhibit complex object motion features and significant differences between frame features. To solve the problems of feature information loss and drastic accuracy decline in applying the video semantic segmentation method based on the fixed-period update strategy of keyframes, a keyframe recognition method based on similarity measurement is proposed, forming a video semantic segmentation algorithm based on adaptive keyframe scheduling. one keyframe recognition method based on pixel similarity measurement is established by modeling the similarity relationship between low-level pixels in adjacent frames. Meanwhile, the other keyframe recognition method based on feature similarity measurement is established by constructing a shallow Siamese network to measure the similarity relationship between features of frames. Then a discriminative network is constructed based on the obtained similarity of inter frames, and the segmentation process is accelerated by reusing features of keyframes through the optical flow network. Thereby a video semantic segmentation method for UAV based on adaptive keyframe strategy is established. The effectiveness of the proposed video semantic segmentation algorithm is verified on UAVid dataset. The results demonstrated that the speed of the proposed algorithm reaches 53.2 FPS and 54.5 FPS on the premise that the mean intersection over union is higher than 40% (this value is compared with the segmentation accuracy in the balanced mode when the similarity threshold is 0.76 and 0.88, respectively), which is 18.5 FPS and 19.8 FPS higher than the PSPNet image semantic segmentation algorithm. In addition, analysis of experiment results shows that the pixel-similarity-based keyframe recognition is suitable for high-precision video semantic segmentation scenes that need to improve segmentation efficiency, and the feature-similarity-based keyframe recognition is more suitable for high real-time video semantic segmentation tasks that require a small decrease in overall algorithm accuracy. 
In a word, the proposed video semantic segmentation algorithm based on adaptive keyframe scheduling via similarity measurement can improve segmentation speed while ensuring segmentation accuracy and stability.

Examining the role of stimulus complexity in item and associative memory.

Episodic memory comprises memory for individual information units (item memory) and for the connections among them (associative memory). In two experiments using an object pair learning task, we examined the effect of visual stimulus complexity on memory encoding and retrieval mechanisms and on item and associative memory performance. Subjects encoded pairs of black monochrome object images (low complexity, LC condition) or color photographs of objects (high complexity, HC condition) via interactive imagery, and subsequently item and associative recognition were tested. In Experiment 1, event-related potentials (ERPs) revealed an enhanced frontal N2 during encoding and an enhanced late posterior negativity (LPN) during item recognition in the HC condition, suggesting that memory traces containing visually more complex objects elicited a stronger effort in reconstructing the past episode. Item memory was consistently superior in the HC compared to the LC condition. Associative memory was either statistically unaffected by complexity (Experiment 1) or improved (Experiment 2) in the HC condition, speaking against a tradeoff between resources allocated to item versus associative memory, and hence contradicting results of some prior studies. In Experiment 2, in both young and older adults, both item and associative memory benefitted from stimulus complexity, such that the magnitude of the age-related associative deficit was not influenced by stimulus complexity. Together, these results suggest that if familiar objects are presented in a form that exhibits a higher visual complexity, which may support semantic processing, complexity can benefit both item and associative memory. Stimulus properties that enhance item memory can scaffold associative memory in this situation.

An effective textured Novel Object Recognition Test (tNORT) for repeated measure of whisker sensitivity of rodents

Rodents use their whisker system to discriminate surface texture. Whisker-based texture discrimination tasks are often used to investigate the mechanisms encoding tactile sensation. One such task is the textured Novel Object Recognition Test (tNORT). It takes advantage of a tendency of rodents to explore novel objects more than familiar ones and assesses the sensitivity of whiskers in discriminating different textures of objects. It requires little training of the animals and the equipment involved is a simple arena with typically two objects placed inside. The success of the test relies on rodents spending sufficient time exploring these objects. Animals may lose interests in such tasks when performed repetitively within a limited time frame. However, such repeated tests may be crucial when establishing a sensitivity threshold of the whisker system. Here we present an adapted rodent tNORT protocol designed to maintain sustained interest in the objects even with repeated testing. We constructed complex objects from three simple-shaped objects. Different textures were provided by sandpapers of varying grit sizes. To minimise olfactory clues, we used the sandy and the laminar side of the same sandpaper as the familiar and novel textures assigned at random. We subsequently conducted repeated tNORTs on eight rats in order to identify a critical threshold of the sandpaper grit size below which rats would be unable to discriminate the sandy from the laminar side. With an inter-test-interval of seven days and after five tNORTs, the protocol enabled us to successfully identify the threshold. We suggest that the proposed tNORT is a useful tool for investigating the sensitivity threshold of the whisker system of rodent, and for testing the effectiveness of an intervention by comparing sensitivity threshold pre- and post-intervention.

LA-Net: An End-to-End Category-Level Object Attitude Estimation Network Based on Multi-Scale Feature Fusion and an Attention Mechanism

In category-level object pose estimation tasks, determining how to mitigate intra-class shape variations and improve pose estimation accuracy for complex objects remains a challenging problem to solve. To address this issue, this paper proposes a new network architecture, LA-Net, to efficiently ascertain object poses from features. Firstly, we extend the 3D graph convolution network architecture by introducing the LS-Layer (Linear Connection Layer), which enables the network to acquire features from different layers and perform multi-scale feature fusion. Secondly, LA-Net employs a novel attention mechanism (PSA) and a Max-Pooling layer to extract local and global geometric information, which enhances the network’s ability to perceive object poses. Finally, the proposed LA-Net recovers the rotation information of an object by decoupling the rotation mechanism. The experimental results show that LA-Net can has much better accuracy in object pose estimation compared to the baseline method (HS-Pose). Especially for objects with complex shapes, its performance is 8.2% better for the 10°5 cm metric and 5% better for the 10°2 cm metric.

MotionTrack: Learning motion predictor for multiple object tracking

Significant progress has been achieved in multi-object tracking (MOT) through the evolution of detection and re-identification (ReID) techniques. Despite these advancements, accurately tracking objects in scenarios with homogeneous appearance and heterogeneous motion remains a challenge. This challenge arises from two main factors: the insufficient discriminability of ReID features and the predominant utilization of linear motion models in MOT. In this context, we introduce a novel motion-based tracker, MotionTrack, centered around a learnable motion predictor that relies solely on object trajectory information. This predictor comprehensively integrates two levels of granularity in motion features to enhance the modeling of temporal dynamics and facilitate precise future motion prediction for individual objects. Specifically, the proposed approach adopts a self-attention mechanism to capture token-level information and a Dynamic MLP layer to model channel-level features. MotionTrack is a simple, online tracking approach. Our experimental results demonstrate that MotionTrack yields state-of-the-art performance on datasets such as Dancetrack and SportsMOT, characterized by highly complex object motion.

КОМПЛЕКСНАЯ ИНФОЛОГИЧЕСКАЯ МОДЕЛЬ ОБЪЕКТОВ ЗАЩИТЫ КОНФИДЕНЦИАЛЬНОЙ ИНФОРМАЦИИ

The problem of harmonization of approaches to the definition of information security objects is becoming increasingly relevant due to the growth of information arrays, the complexity of information technologies, technical and cryptographic means of information protection, and the increasing number of computer attacks, including on critical information infrastructure. Historically, the concept of objects of protection in Russia is associated with the requirements of state regulators, so it has different interpretations. The purpose of the study is to develop an infological model of information security objects. The goal of infological modeling may be to provide the most natural ways for a person to collect and present information about objects of protection for its consideration when creating protection systems and storing in a database. The author based on the analysis of the requirements of the main regulators of the Federal service according to the technical and export control of Russia and the Federal security service of Russia and the modeling method, an infological model of information security objects has been developed. This model is most consistent with the concept of object-oriented design, which is the basis for the development of complex software systems, the development of technology for designing databases of information security objects based on the ER-model. The entity-relationship model (ER-model) has several basic concepts, from which more complex objects are built according to predefined rules.

Millimeter-Wave Radar Detection and Localization of a Human in Indoor Complex Environments

Nowadays, it is still a great challenge to detect and locate indoor humans using a frequency-modulated continuous-wave radar accurately. Due to the interference of the indoor environment and complex objects such as green plants, the radar signal may penetrate, reflect, refract, and scatter, and the echo signals will contain noise, clutter, and multipath of different characteristics. Therefore, a method combined with comprehensive non-target signal removal and human localization is proposed to achieve position estimation of a human target. Time-variant clutter is innovatively mitigated through time accumulation using point clustering. Ghost targets are reduced according to propagation path matching. The experimental results show that the method can locate the real target human within an average error of 0.195 m in multiple complex environments with green plants, curtains, or furniture using a 77 GHz millimeter-wave radar. Meanwhile, the proposed method performs better than conventional methods. The detection probability is 81.250% when the human is behind a potted plant and is 90.286% when beside it.

Manipulation of a Complex Object Using Dual-Arm Robot with Mask R-CNN and Grasping Strategy

Hot forging is one of the common manufacturing processes for producing brass workpieces. However forging produces flash which is a thin metal part around the desired part formed with an excessive material. Using robots with vision system to manipulate this workpiece has encountered several challenging issues, e.g. the uncertain shape of flash, color, reflection of brass surface, different lighting condition, and the uncertainty surrounding the position and orientation of the workpiece. In this research, Mask region-based convolutional neural network together with image processing is used to resolve these issues. The depth camera can provide images for visual detection. Machine learning Mask region-based convolutional neural network model was trained with color images and the position of the object is determined by the depth image. A dual arm 7 degree of freedom collaborative robot with proposed grasping strategy is used to grasp the workpiece that can be in inappropriate position and pose. Eventually, experiments were conducted to assess the visual detection process and the grasp planning of the robot.