Detection Performance Research Articles

Improved object detection method for unmanned driving based on Transformers.

The object detection method serves as the core technology within the unmanned driving perception module, extensively employed for detecting vehicles, pedestrians, traffic signs, and various objects. However, existing object detection methods still encounter three challenges in intricate unmanned driving scenarios: unsatisfactory performance in multi-scale object detection, inadequate accuracy in detecting small objects, and occurrences of false positives and missed detections in densely occluded environments. Therefore, this study proposes an improved object detection method for unmanned driving, leveraging Transformer architecture to address these challenges. First, a multi-scale Transformer feature extraction method integrated with channel attention is used to enhance the network's capability in extracting features across different scales. Second, a training method incorporating Query Denoising with Gaussian decay was employed to enhance the network's proficiency in learning representations of small objects. Third, a hybrid matching method combining Optimal Transport and Hungarian algorithms was used to facilitate the matching process between predicted and actual values, thereby enriching the network with more informative positive sample features. Experimental evaluations conducted on datasets including KITTI demonstrate that the proposed method achieves 3% higher mean Average Precision (mAP) than that of the existing methodologies.

Synchronous Diagnosis of Diabetic Retinopathy by a Handheld Retinal Camera, Artificial Intelligence, and Simultaneous Specialist Confirmation

PurposeDiabetic retinopathy (DR) is a leading cause of preventable blindness, particularly in underserved regions where access to ophthalmic care is limited. This study presents a proof of concept for utilizing a portable handheld retinal camera with an embedded artificial intelligence (AI) platform, complemented by a synchronous remote confirmation by retina specialists, for DR screening in an underserved rural area. DesignRetrospective cohort study Subjects1,115 individuals with diabetes. MethodsA retrospective analysis of a screening initiative conducted in four municipalities in Northeastern Brazil, targeting the diabetic population. A portable handheld retinal camera captured macula-centered and disc-centered images, which were analyzed by the AI system. Immediate push notifications were sent out to retina specialists upon the detection of significant abnormalities, enabling synchronous verification and confirmation, with on-site patient feedback within minutes. Referral criteria were established, and all referred patients underwent a complete ophthalmic work-up and subsequent treatment. Main outcome measuresProof-of-concept implementation success. ResultsOut of 2,052 invited individuals, 1,115 participated, with a mean age of 60.93 years and diabetes duration of 7.52 years, of whom 66.03% were women. The screening covered 2,222 eyes, revealing various retinal conditions. Referable eyes for DR were 11.84%, with an additional 13% for other conditions (diagnoses included various stages of DR, media opacity, nevus, drusen, enlarged cup-to-disc ratio, pigmentary changes, and other). AI performance for overall detection of referable cases (both DR and other conditions) was: sensitivity- 84.23% (95% CI- 82.63-85.84), specificity- 80.79% (95% CI- 79.05- 82.53). When we assessed whether AI matched any clinical diagnosis, be it referable or not, sensitivity was 85.67% (95% CI- 84.12-87.22), specificity was 98.86 (95% CI- 98.39-99.33), and AUC was 0.92 (95% CI- 0.91-0.94). ConclusionsThe integration of a portable device, AI analysis, and synchronous medical validation has the potential to play a crucial role in preventing blindness from DR, especially in socially unequal scenarios.

Detecting Line Segments in Motion-Blurred Images With Events.

Making line segment detectors more reliable under motion blurs is one of the most important challenges for practical applications, such as visual SLAM and 3D line mapping. Existing line segment detection methods face severe performance degradation for accurately detecting and locating line segments when motion blur occurs. While event data shows strong complementary characteristics to images for minimal blur and edge awareness at high-temporal resolution, potentially beneficial for reliable line segment recognition. To robustly detect line segments over motion blurs, we propose to leverage the complementary information of images and events. Specifically, we first design a general frame-event feature fusion network to extract and fuse the detailed image textures and low-latency event edges, which consists of a channel-attention-based shallow fusion module and a self-attention-based dual hourglass module. We then utilize the state-of-the-art wireframe parsing networks to detect line segments on the fused feature map. Moreover, due to the lack of line segment detection datasets with pairwise motion-blurred images and events, we contribute two datasets, i.e., synthetic FE-Wireframe and realistic FE-Blurframe, for network training and evaluation. Extensive analyses on the component configurations demonstrate the design effectiveness of our fusion network. When compared to the state-of-the-arts, the proposed approach achieves the highest detection accuracy while maintaining comparable real-time performance. In addition to being robust to motion blur, our method also exhibits superior performance for line detection under high dynamic range scenes.

A Popular Topic Detection Method based on Microblog Images and Short Text Information

Popular topic detection is a topic identification by the information of documents posted by users in social networking platforms. In a large body of research literature, most popular topic detection methods identify the distribution of unknown topics by integrating information from documents based on social networking platforms. However, among these popular topic detection methods, most of them have a low accuracy in topic detection due to the short text content and the abundance of useless punctuation marks and emoticons. Image information in short texts has also been overlooked, while this information may contain the real topic matter of the user's posted content. In order to solve the above problems and improve the quality of topic detection, this paper proposes a popular topic detection method based on microblog images and short text information. The method uses an image description model to obtain more information about short texts, identifies hot words by a new word discovery algorithm in the preprocessing stage, and uses a PTM model to improve the quality and effectiveness of topic detection during topic detection and aggregation. The experimental results show that the topic detection method in this paper improves the values of evaluation indicators compared with the other three topic detection methods. In conclusion, the popular topic detection method proposed in this paper can improve the performance of topic detection by integrating microblog images and short text information, and outperforms other topic detection methods selected in this paper.

ASF-YOLO: A novel YOLO model with attentional scale sequence fusion for cell instance segmentation

We propose a novel Attentional Scale Sequence Fusion based You Only Look Once (YOLO) framework (ASF-YOLO) which combines spatial and scale features for accurate and fast cell instance segmentation. Built on the YOLO segmentation framework, we employ the Scale Sequence Feature Fusion (SSFF) module to enhance the multiscale information extraction capability of the network, and the Triple Feature Encoder (TFE) module to fuse feature maps of different scales to increase detailed information. We further introduce a Channel and Position Attention Mechanism (CPAM) to integrate both the SSFF and TFE modules, which focus on informative channels and spatial position-related small objects for improved detection and segmentation performance. Experimental validations on two cell datasets show remarkable segmentation accuracy and speed of the proposed ASF-YOLO model. It achieves a box mAP of 0.91, mask mAP of 0.887, and an inference speed of 47.3 FPS on the 2018 Data Science Bowl dataset, outperforming the state-of-the-art methods. The source code is available at https://github.com/mkang315/ASF-YOLO.

A Joint Intensity-Neuromorphic Event Imaging System With Bandwidth-Limited Communication Channel.

We present a novel adaptive multimodal intensity-event algorithm to optimize an overall objective of object tracking under bit rate constraints for a host-chip architecture. The chip is a computationally resource-constrained device acquiring high-resolution intensity frames and events, while the host is capable of performing computationally expensive tasks. We develop a joint intensity-neuromorphic event rate-distortion compression framework with a quadtree (QT)-based compression of intensity and events scheme. The goal of this compression framework is to optimally allocate bits to the intensity frames and neuromorphic events based on the minimum distortion at a given communication channel capacity. The data acquisition on the chip is driven by the presence of objects of interest in the scene as detected by an object detector. The most informative intensity and event data are communicated to the host under rate constraints so that the best possible tracking performance is obtained. The detection and tracking of objects in the scene are done on the distorted data at the host. Intensity and events are jointly used in a fusion framework to enhance the quality of the distorted images, in order to improve the object detection and tracking performance. The performance assessment of the overall system is done in terms of the multiple object tracking accuracy (MOTA) score. Compared with using intensity modality only, there is an improvement in MOTA using both these modalities in different scenarios.

From citizen science to AI models: Advancing cetacean vocalization automatic detection through multi-annotator campaigns

Continuous underwater Passive Acoustic Monitoring (PAM) has emerged as a strong tool for cetacean research. To handle the vast volume of collected data, it is essential to employ automated detection and classification methods. The recent advancement of deep learning, involving model training and testing, requires a large amount of labeled data. These labels are derived through the manual annotation of audio files often reliant on human experts. Based on an annotation campaign focusing on blue whale calls in the Indian Ocean involving 19 novice annotators and an expert in bioacoustics, this study explores the integration of novice annotators in marine bioacoustics research, through citizen science programs, which could drastically increase the size of labeled datasets and enhance the performance of detection and classification models. The analysis reveals distinctive annotation profiles influenced by the complexity of vocalizations and the annotators' strategies, ranging from conservative to permissive. To address the challenges of annotation discrepancies, Convolutional Neural Networks (CNNs) are trained on annotations from both novices and the expert. The results show variations in model performance. Our work highlights the importance of annotation guidelines encouraging a more conservative approach to improve overall annotation quality. In an effort to optimize the potential of multi-annotation and mitigate the presence of noisy labels, two annotation aggregation methods (majority voting and soft labeling) are proposed and tested. The results demonstrate that both methods, particularly when a sufficient number of annotators are involved, significantly improve model performance and reduce variability: the standard deviation of the area under PR and ROC curves fall under 0.02 for both vocalizations with 13 aggregated annotators, while it was at 0.17 and 0.21 for the Blue Whale Dcalls and 0.05 and 0.04 for the SEIO PBW vocalizations with all annotator separately. Moreover, these aggregation methods enable the training of models using non-expert annotations that achieve performances of models trained with expert annotations. These findings suggest that crowdsourced annotations from novice annotators can be a viable alternative to expert annotations.

A near-infrared fluorescent probe with thiadiazole unit as key skeleton for ICT and ESIPT mechanism and effective detection of Cu2+

Fluorescent probe L-I was synthesized to demonstrate that 1,3,4-thiadiazole is an attractive moiety and could be utilized as positive hydrogen bond acceptor for excited state intramolecular proton transfer (ESIPT) processes, guider of electrons movement for intramolecular charge transfer (ICT) process and identify group for mental ions. Furthermore, dicyanoisophorone framework was employed to improve the fluorescence characteristics and near-infrared (NIR) fluorescent emission at 695 nm accompanied by a Stoke's shift as large as 260 nm was obtained. L-I could selectively detect Cu2+ over other analytes taking advantages of high sensitivity, fast response within 30 s and low detection limit (0.026 μM). More important, L-I exhibited good performance for detection of Cu2+ in actual water samples, food products, traditional Chinese medicine and for cell imaging which demonstrates practical significance in the fields of environmental monitor, food safety and biotechnology.

The layer-by-layer assembled ERGO+/ERGO− multilayer modified electrode for sensitive detection of dopamine

Graphene materials represented by graphene oxide (GO) have been widely regarded as functional coatings or films to modify surface of the electrode for detecting dopamine molecules. However, interfacial material properties for detection sensitivity, film stability, and applicability to electrodes are still highly desired. Herein, we first present a screen-printing carbon electrode (SPCE) coated with an electrochemically reduced layer-by-layer (LbL) assembled multilayer driven by an electrostatic interaction between positively charged polyethyleneimine-modified GO with amine groups (ERGO+) and negatively charged carboxyl-functionalized GO (ERGO−), which is briefly described as (ERGO+/ERGO−)n/SPCE. Firstly, without using conventional glassy carbon and gold electrodes, SPCE was tried to make coatings adapt to more flexible and unstable electrodes, simultaneously guaranteeing higher detection performance. Secondly, although a variety of electrochemical sensors such as GO−/SPCE and ERGO−/SPCE were obtained through the drop-casting technique, as-prepared (ERGO+/ERGO−)n/SPCE showed much higher electrocatalytic activities with enhanced peak current signals and reduced charge transfer resistance. Finally, excellent electrochemical properties and sensing performances of the (ERGO+/ERGO−)n/SPCE sensor for detection of dopamine were demonstrated, especially having a linear range of 1 μM to 1000 μM. Meanwhile, the detection limit is as low as 0.39 μM and S/N is equal to 3. The present work offers a potential direction to develop GO modified electrodes for sensitive biomolecular detection.

Double reuses based residual network

Deep residual network (ResNet) had shown remarkable performance in image recognition tasks, due to its shorter connections between layers close to the input and those close to the output. And densely connected convolutional network (DenseNet) had further improved recognition performance by dense feature reuses. To improve the performance of residual units in ResNet and feature reuses in DenseNet, we propose a simple and effective convolutional network architecture, named double reuses based residual network (DRRNet). DRRNet improves the residual unit of ResNet, where the feature reuse connections are added to combine all feature maps from the convolutional layers to produce the residual, and uses a residual reuse path outside units to reuse all residuals as the final feature maps for classification. Residual learning used in DRRNet can alleviate the vanishing-gradient problem. The double reuses including inner-unit feature reuses and outer-unit residual reuses effectively decrease computational cost as compared with dense connections in DenseNet, and further strengthen the forward feature propagation. DRRNet is evaluated on three object recognition benchmark datasets and an object detection dataset. In comparison with the state-of-the-art, DRRNet achieves a good balance between classification accuracy and computational cost, and optimal detection performance.

Quantification and cultivation of Helicobacter pylori (H. pylori) from various urban water environments: A comprehensive analysis of precondition methods and sample characteristics

Substantial evidence suggests that all types of water, such as drinking water, wastewater, surface water, and groundwater, can be potential sources of Helicobacter pylori (H. pylori) infection. Thus, it is critical to thoroughly investigate all possible preconditioning methods to enhance the recovery of H. pylori, improve the reproducibility of subsequent detection, and optimize the suitability for various water types and different detection purposes. In this study, we proposed and evaluated five distinct preconditioning methods for treating water samples collected from multiple urban water environments, aiming to maximize the quantitative qPCR readouts and achieve effective selective cultivation. According to the experimental results, when using the qPCR technique to examine WWTP influent, effluent, septic tank, and wetland water samples, the significance of having a preliminary cleaning step becomes more evident as it can profoundly influence qPCR detection results. In contrast, the simple, straightforward membrane filtration method could perform best when isolating and culturing H. pylori from all water samples. Upon examining the cultivation and qPCR results obtained from groundwater samples, the presence of infectious H. pylori (potentially other pathogens) in aquifers must represent a pressing environmental emergency demanding immediate attention. Furthermore, we believe groundwater can be used as a medium to reflect the H. pylori prevalence in a highly populated community due to its straightforward analytical matrix, consistent detection performance, and minimal interferences from human activities, temperature, precipitation, and other environmental fluctuations.

Remarkable fluorescence enhancement of acridine orange and rhodamine B through immobilization on zirconia nanotube array film and its application on nitrite sensing

Zirconia nanotube array films (ZNAF) prepared by anodic oxidation method were used as immobilization materials for acridine orange (AO), rhodamine B (RB) and AO-RB systems. A comparative study on their fluorescence emission intensity, fluorescence resonance energy transfer (FRET) and fluorescence detection of nitrite in aqueous solutions and on immobilization films with ZNAF as carriers was carried out. Results demonstrate that the solution pH values and immobilization on ZNAF have a great influence on the performance of these fluorescent molecules. Compared with aqueous solutions, the fluorescence emission intensity of AO and RB is considerably increased by immobilization, which is 8.0 and 4.2 times higher than the original, respectively. The energy transfer efficiency (E) of the AO-RB system increases from 40.9% to 84.8% by loading it on ZNAF. Moreover, after immobilization onto ZNAF, the fluorescence detection performance of nitrite is also significantly improved. The limit of detection decreases from 0.95 ng/mL to 0.22 ng/mL and the sensitivity increases from 939.18 mL/μg to 15031.68 mL/μg through loading AO onto ZNAF.

A superior near infrared fluorescent probe for revealing the relationship between peroxynitrite and Alzheimer's disease

The typical neurodegenerative Alzheimer's disease (AD) poses an increasing threat to human health as the population ages. Though increasing attention has been drawn for the etiology of AD over decades, regretfully, the exact pathogenesis of AD is not fully elucidated. The elevated levels of ROS are among the major pathological alterations in AD. Among them, peroxynitrite (ONOO-) exhibits a greater impact compared to other reactive oxygen species and plays an important role in AD, but the role ONOO- plays in AD progression remains unclear. In this work, the near-infrared (NIR) fluorophore (benzopyran derivative) was optimized by molecular skeleton modification, and a fluorophore DCM-Cl-OH with better spectral properties was obtained. On this basis, a NIR fluorescence probe DCM-Cl-P with excellent detection performance was obtained. Based on the high selectivity and fast response of the probe to ONOO-, DCM-Cl-P was used to visual detection of ONOO- in living cells and zebrafish, and further demonstrated the excessive accumulation of ONOO- in AD model mice. More importantly, through analysis of the correlation between ONOO- and amyloid-β protein (Aβ), ONOO- and the aggregation of Aβ were closely related and mutually reinforcing was demonstrated and ONOO- underwent significant changes in the early stage of the change of Aβ aggregation, indicating that ONOO- may serve as an early marker of AD. These findings have greatly promoted the research on the intrinsic relationship between ONOO- and AD, and provides a powerful means for pathological research of AD.

GAMA: A multi-graph-based anomaly detection framework for business processes via graph neural networks

Anomalies in business processes are inevitable for various reasons such as system failures and operator errors. Detecting anomalies is important for the management and optimization of business processes. However, prevailing anomaly detection approaches often fail to capture crucial structural information about the underlying process. To address this, we propose a multi-Graph based Anomaly detection fraMework for business processes via grAph neural networks, named GAMA. GAMA makes use of structural process information and attribute information in a more integrated way. In GAMA, multiple graphs are applied to model a trace in which each attribute is modelled as a separate graph. In particular, the graph constructed for the special attribute activity reflects the control flow. Then GAMA employs a multi-graph encoder and a multi-sequence decoder on multiple graphs to detect anomalies in terms of the reconstruction errors. Moreover, three teacher forcing styles are designed to enhance GAMA’s ability to reconstruct normal behaviours and thus improve detection performance. We conduct extensive experiments on both synthetic logs and real-life logs. The experiment results demonstrate that GAMA outperforms state-of-the-art methods for both trace-level and attribute-level anomaly detection.

Real-time lightweight drone detection model: Fine-grained Identification of four types of drones based on an improved Yolov7 model

Recently, the rapid progress of artificial intelligence has enhanced the human-robot relationship through the development of several autonomous robots; such as drones. The overwhelming rise of drones has brought both relevant advantages and threatening risks into our daily lives. They are strongly deployed to achieve hard tasks and reach critical areas within a short period of time. In the past few years, drones' anarchic and malicious use has generated many incidents and accidents, causing far-reaching impacts. Due to their dual-edged nature, they are regarded as potential threats. Recognizing the type of flying drones represents a challenging task for anti-drone systems to reinforce airspace safety and security. To this end, we propose a novel lightweight model able to differentiate between the main types of drones in real-time using appropriate modules. To find the optimal compromise between size, performance and speed, a lightweight model is proposed based on Yolov7 with the incorporation of CNeB and C3C2 modules as well as the Re- Parameterization Decoupled (RePD) head structure. Further, a CNeB module is used to reduce the model’s size and improve the model’s performance, a C3C2 module to enhance the feature extraction and fusion and a Re- Parameterization Decoupled RePD to improve both the efficacy and accuracy of the prediction part while reducing the inference time. The experimental results show that the Yolov7-CNeB-C3C2-RePD meets the anti-drone requirements by improving the detection performance, minimizing the inference speed and reducing the model size. In comparison to other models, the developed has provided high results reaching 91.9% precision, 90.5% recall, 95% mAP@0.5, and 20.3 ms during the inference stage, which outperforms the other algorithms in the benchmark. Furthermore, the model has an average detection speed of 0.003 ms per image and a capacity to process 27.88 frames per second, thus satisfying the real-time requirements.

Mechanistic understanding of nanoparticle interactions to achieve highly-ordered arrays through self-assembly for sensitive surface-enhanced Raman scattering detection of trace thiram

Over the last few decades, there is increasing worldwide concern over human health risks associated with extensive use of pesticides in agriculture. Developing excellent SERS substrate materials to achieve highly sensitive detection of pesticide residues in the food is very necessary owing to their serious threat to human health through food chains. Self-assembled metallic nanoparticles have been demonstrated to be excellent SERS substrate materials. Hence, alkanethiols-protected gold nanoparticles have been successfully prepared for forming larger-scale two-dimensional monolayer films. These films can be disassembled into a fluid state and re-assembled back to crystallized structure by controlling surface pressure. Further investigations reveal that their self-assembled structures are mainly dependent on the diameter of gold nanoparticles and ligand length. These results suggest that the size ratio of nanoparticle diameter/ligand length within the range of 4.45–2.35 facilitates the formation of highly ordered 2D arrays. Furthermore, these arrays present excellent Surface-Enhanced Raman Scattering performances in the detection of trace thiram, which can cause environmental toxicity to the soil, water, animals and result in severe damage to human health. Therefore, the current study provides an effective way for preparing monodispersed hydrophobic gold nanoparticles and forming highly ordered 2D close-packed SERS substrate materials via self-assembly to detect pesticide residues in food. We believe that, our research provides not only advanced SERS substrate materials for excellent detection performance of thiram in food, but also novel fundamental understandings of self-assembly, manipulation of nanoparticle interactions, and controllable synthesis.

Hybrid Optimization Enabled Squeeze Net For Phishing Attack Detection

Nowadays, phishing attacks are considered as one of the most common cyber attacks which generally harm the security of various internet and communication systems. The phishing websites are produced with the intention of determining the user's financial information by creating cyber threats. The loss of valuable user assets occurs due to the frequent creation and circulation of fake websites all over the internet. The negative impacts of phishing websites include financial loss, loss of intellectual property, reputational harm, and interruption of daily operations. To identify and lessen these attempts, several anti-phishing strategies have been put forth during the past ten years. However, they are still inaccurate and inefficient. To overcome this problem, intelligent approaches, like Deep Learning (DL) is used, which can accurately learn the inherent characteristics of the websites and identify phishing websites. In this paper, the phishing websites are determined effectively using the Fractional Dingo Hunter Prey Optimization-SqueezeNet (FDHPO-SqueezeNet) technique. The different features, like web features, ocular features, and Natural Language Processing (NLP) features are extracted separately from the website data. Later, the optimal features are selected, fused, and augmented, and allowed for the detection of phishing websites using SqueezeNet. Finally, the phishing detection is performed using SqueezeNet, where the detection performance of the SqueezeNet is increased by training using the FDHPO technique. The investigation results revealed that the designed FDHPO-SqueezeNet technique recorded greater performance when compared with other prevailing phishing detection approaches with a maximal of 93.05% accuracy, 94.26% sensitivity, and 93.75% specificity, respectively.

Fabrication of chitosan-based fluorescent hydrogel membranes cross-linked with bisbenzaldehyde for efficient selective detection and adsorption of Fe2+

Chitosan, as a natural biomass material, is green, recyclable, sustainable and well biocompatible. The molecular chain is rich in active groups such as amino and hydroxyl groups, and its preparation of fluorescent probes has the advantages of biocompatibility and efficient detection performance. In this study, a bis(benzaldehyde) (BHD) fluorescent functional molecule was designed. Then a series of fluorescent chitosan-based hydrogel films (CSBHD) were prepared using chitosan as raw material and BHD as cross-linking agent. As a fluorescent probe for metal ions, CSBHD was able to efficiently detect Fe2+ with a linear correlation of fluorescence intensity in the range of 0–160 μM, and the limit of detection (LOD) was 0.55 μM. Moreover, it has excellent adsorption performance for Fe2+ ions, with a maximum adsorption capacity of 223.5 g/mg at 500 mg/L Fe2+ concentration. Finally, we characterised the structure and microscopic morphology of CSBHD films and found that CSBHD as a hydrogel film has a high cross-linking density, good water resistance, excellent thermal stability, strong resistance to swelling, and excellent stability in cycling tests. Hence, it has great potential for application in adsorption and detection of Fe2+ ions. It also provides a good strategy for the application of chitosan based fluorescent probe materials in environmental monitoring and heavy metal ion adsorption.

Exploration of factors affecting webcam-based automated gaze coding.

Online experiments have been transforming the field of behavioral research, enabling researchers to increase sample sizes, access diverse populations, lower the costs of data collection, and promote reproducibility. The field of developmental psychology increasingly exploits such online testing approaches. Since infants cannot give explicit behavioral responses, one key outcome measure is infants' gaze behavior. In the absence of automated eyetrackers in participants' homes, automatic gaze classification from webcam data would make it possible to avoid painstaking manual coding. However, the lack of a controlled experimental environment may lead to various noise factors impeding automatic face detection or gaze classification. We created an adult webcam dataset that systematically reproduced noise factors from infant webcam studies which might affect automated gaze coding accuracy. We varied participants' left-right offset, distance to the camera, facial rotation, and the direction of the lighting source. Running two state-of-the-art classification algorithms (iCatcher+ and OWLET) revealed that facial detection performance was particularly affected by the lighting source, while gaze coding accuracy was consistently affected by the distance to the camera and lighting source. Morphing participants' faces to be unidentifiable did not generally affect the results, suggesting facial anonymization could be used when making online video data publicly available, for purposes of further study and transparency. Our findings will guide improving study design for infant and adult participants during online experiments. Moreover, training algorithms using our dataset will allow researchers to improve robustness and allow developmental psychologists to leverage online testing more efficiently.

АНАЛІЗ АЛГОРИТМІВ ВИЯВЛЕННЯ ЗІТКНЕНЬ У ТРИВИМІРНИХ ВІРТУАЛЬНИХ СЕРЕДОВИЩАХ

The problem addressed in this paper concerns the real-time detection of collisions in virtual environments, which can consume a significant portion of computational re-sources, particularly in complex simulations with numerous objects. Ensuring a minimum frame rate of 30 FPS is crucial for user-friendly simulations. The focus is on the narrow phase of collision detection, where objects in close proximity are examined for potential collisions. This paper proposes a collision detection algorithm leveraging Directed Bounding Parallels (AABB) R-tree structure and Oriented Bounding Parallelepiped Inter-section (OAABB) method to address this phase efficiently. Experimental results demon-strate the effectiveness of the algorithm in detecting intersections with high interaction rates. Various publicly available toolkits exist for narrow phase collision detection, em-ploying different bounding volume hierarchies and constraint volumes. Comparing these approaches is challenging due to performance variations influenced by factors such as object shapes, contact types, and model sizes. Nonetheless, these algorithms are crucial for accurately detecting collisions in virtual environments and gaming applications. Bounding Volume Hierarchies (BVH), commonly used for collision detection, organ-ize object geometry and improve performance by reducing test pair numbers through vol-ume constraints. The proposed algorithm utilizes R-tree hierarchies of directed bounding parallelepipeds and OAABB to enhance collision detection efficiency by minimizing up-date and intersect operations. The choice of constraint volume type impacts collision de-tection performance, with oriented parallelepipeds offering faster intersections. To expedite collision detection, each feature is represented by an R-tree data struc-ture in its local coordinate system. Hierarchical trees are constructed by grouping adja-cent surfaces, with leaves indicating surface geometry. Additionally, R-trees are em-ployed to spatially organize triangles within surfaces to quickly discard non-intersecting triangles. The algorithm leverages OAABB, a concept involving the common volume between two oriented bounding parallelepipeds, to filter out primitives that cannot intersect. Tra-versal algorithms are utilized to reduce the number of node visits, addressing inefficien-cies observed in traditional schemes. OAABB contributes significantly to reducing volume refresh operations. Experimental evaluations demonstrate the proposed algorithm's efficacy in real-world industrial applications, achieving interactive performance. Comparisons with al-ternative methods highlight the algorithm's effectiveness in collision detection. Overall, the proposed approach offers a robust solution to the narrow phase collision detection problem in virtual environments.