Search

The research groups in computer vision, graphics, and machine learning have dedicated a substantial amount of attention to the areas of 3D object reconstruction, augmentation, and registration. Deep learning is the predominant method used in artificial intelligence for addressing computer vision challenges. However, deep learning on three-dimensional data presents distinct obstacles and is now in its nascent phase. There have been significant advancements in deep learning specifically for three-dimensional data, offering a range of ways to address these issues. This study offers a comprehensive examination of the latest advancements in deep learning methodologies. We examine many benchmark models for the tasks of 3D object registration, augmentation, and reconstruction. We thoroughly analyse their architectures, advantages, and constraints. In summary, this report provides a comprehensive overview of recent advancements in three-dimensional deep learning and highlights unresolved research areas that will need to be addressed in the future. [ABSTRACT FROM AUTHOR]

Image semantic segmentation technology is one of the core research contents in the field of computer vision. With the improvement of computer performance and the continuous development of deep learning technology, researchers have more and more enthusiasm to study the actual effect and performance of image semantic segmentation. The results of deep semantic segmentation allow computers to have a more detailed and accurate understanding of images, and have a wide range of application needs in the fields of autonomous driving, intelligent security, medical imaging, remote sensing images, etc. However, the existing image semantic segmentation algorithms have the disadvantages of easy discontinuous results and insufficient prediction accuracy. In this paper, we take deep learning-based image semantic segmentation technology as the research object to explore the improvement of the image semantic segmentation algorithm and its application in road scenarios. First, this paper proposes MCU-Net method based on residual fusion and multi-scale contextual information. MCU-Net uses residual fusion module to deepen the network structure and improve the ability of U-Net to acquire deeper features. Then a top-down and bottom-up path is constructed for feature information between different levels, and the spatial and semantic information contained in shallow and deep features in the network is fully utilized by fusing features from different levels. In addition, an enhanced void space pyramid pooling module is added for feature information between the same levels, which enables the output features to have a larger range of semantic information. Second, this paper proposes the DAMCU-Net method based on attention mechanism and edge detection based on MCU-Net. DAMCU-Net extracts global contextual information by the attention mechanism optimization module, while fusing features using dense jump connections to facilitate the network to recover more spatial detail information during upsampling, and uses the FReLU activation function to improve the segmentation capability of the network for complex targets. For the edge information lost in the feature extraction process, the edge detection branch is added to supplement the feature information of the main path by feature fusion to achieve the optimization of the edge information. [ABSTRACT FROM AUTHOR]

3D human motion prediction, predicting future poses from a given sequence, is an issue of great significance and challenge in computer vision and machine intelligence, which can help machines in understanding human behaviors. Due to the increasing development and understanding of Deep Neural Networks (DNNs) and the availability of large-scale human motion datasets, the human motion prediction has been remarkably advanced with a surge of interest among academia and industrial community. In this context, a comprehensive survey on 3D human motion prediction is conducted for the purpose of retrospecting and analyzing relevant works from existing released literature. In addition, a pertinent taxonomy is constructed to categorize these existing approaches for 3D human motion prediction. In this survey, relevant methods are categorized into three categories: human pose representation , network structure design , and prediction target. We systematically review all relevant journal and conference papers in the field of human motion prediction since 2015, which are presented in detail based on proposed categorizations in this survey. Furthermore, the outline for the public benchmark datasets, evaluation criteria, and performance comparisons are respectively presented in this paper. The limitations of the state-of-the-art methods are discussed as well, hoping for paving the way for future explorations. [ABSTRACT FROM AUTHOR]

The emergence of data-driven analytics and intelligent monitoring systems is radically transforming the world of competitive sports. However, robust real-time activity recognition remains elusive for rapid-paced sports like table tennis due to the complexity of strokes and quick maneuvering. This paper tries to overcome this challenge through an innovative cloud-supported system integrating the Internet of Things (IoT), machine learning, and wearable sensors for automated analysis of table tennis gameplay. We strategically set up a multi-camera IoT system around a table tennis court to compile a rich labeled image dataset encapsulating over 15,000 frames. To improve model generalization, the images captured various playing styles, lighting conditions, and camera angles. We developed tailored SVM and CNN architectures optimized for table tennis activity classification. The models were trained on GPU-accelerated platforms using the curated dataset. After hyperparameter tuning and cross-validation, the CNN model achieved 96.2% accuracy, a precision value of 96.3%, a recall value of 95.2%, and an F1-score of 96.3% in classifying standard strokes and serves. Additionally, the models exhibited impressive processing speeds of 22–34 fps, enabling real-time utilization. Our proposed model outperformed the latest models in this field with higher accuracy, recall values, F1-score, and precision. While expanding the dataset diversity and testing variations of deep network architectures could further enhance performance, this paper demonstrates a crucial leap toward helping real-time analytics in table tennis using an AI-powered computer vision approach. The hybrid system combining IoT, wearables, and machine learning establishes a framework to transform data into actionable and timely insights for table tennis players and coaches. [ABSTRACT FROM AUTHOR]

Recently, ConvNeXt and blueprint separable convolution (BSConv) constructed from standard ConvNet modules have demonstrated competitive performance in advanced computer vision tasks. This paper proposes an efficient model (BCRN) based on BSConv and the ConvNeXt residual structure for single image super-resolution, which achieves superior performance with very low parametric numbers. Specifically, the residual block (BCB) of the BCRN utilizes the ConvNeXt residual structure and BSConv to significantly reduce the number of parameters. Within the residual block, enhanced spatial attention and contrast-aware channel attention modules are simultaneously introduced to prioritize valuable features within the network. Multiple residual blocks are then stacked to form the backbone network, with Dense connections utilized between them to enhance feature utilization. Our model boasts extremely low parameters compared to other state-of-the-art lightweight models, while experimental results on benchmark datasets demonstrate its excellent performance. The code will be available at https://github.com/kptx666/BCRN. [ABSTRACT FROM AUTHOR]

Technological advancements have expanded the range of methods for capturing human body motion, including solutions involving inertial sensors (IMUs) and optical alternatives. However, the rising complexity and costs associated with commercial solutions have prompted the exploration of more cost-effective alternatives. This paper presents a markerless optical motion capture system using a RealSense depth camera and intelligent computer vision algorithms. It facilitates precise posture assessment, the real-time calculation of joint angles, and acquisition of subject-specific anthropometric data for gait analysis. The proposed system stands out for its simplicity and affordability in comparison to complex commercial solutions. The gathered data are stored in comma-separated value (CSV) files, simplifying subsequent analysis and data mining. Preliminary tests, conducted in controlled laboratory environments and employing a commercial MEMS-IMU system as a reference, revealed a maximum relative error of 7.6% in anthropometric measurements, with a maximum absolute error of 4.67 cm at average height. Stride length measurements showed a maximum relative error of 11.2%. Static joint angle tests had a maximum average error of 10.2%, while dynamic joint angle tests showed a maximum average error of 9.06%. The proposed optical system offers sufficient accuracy for potential application in areas such as rehabilitation, sports analysis, and entertainment. [ABSTRACT FROM AUTHOR]

Deep learning has achieved immense success in computer vision and has the potential to help physicians analyze visual content for disease and other abnormalities. However, the current state of deep learning is very much a black box, making medical professionals skeptical about integrating these methods into clinical practice. Several methods have been proposed to shed some light on these black boxes, but there is no consensus on the opinion of medical doctors that will consume these explanations. This paper presents a study asking medical professionals about their opinion of current state-of-the-art explainable artificial intelligence methods when applied to a gastrointestinal disease detection use case. We compare two different categories of explanation methods, intrinsic and extrinsic, and gauge their opinion of the current value of these explanations. The results indicate that intrinsic explanations are preferred and that physicians see value in the explanations. Based on the feedback collected in our study, future explanations of medical deep neural networks can be tailored to the needs and expectations of doctors. Hopefully, this will contribute to solving the issue of black box medical systems and lead to successful implementation of this powerful technology in the clinic. [ABSTRACT FROM AUTHOR]

Remote sensing datasets usually have a wide range of spatial and spectral resolutions. They provide unique advantages in surveillance systems, and many government organizations use remote sensing multispectral imagery to monitor security-critical infrastructures or targets. Artificial Intelligence (AI) has advanced rapidly in recent years and has been widely applied to remote image analysis, achieving state-of-the-art (SOTA) performance. However, AI models are vulnerable and can be easily deceived or poisoned. A malicious user may poison an AI model by creating a stealthy backdoor. A backdoored AI model performs well on clean data but behaves abnormally when a planted trigger appears in the data. Backdoor attacks have been extensively studied in machine learning-based computer vision applications with natural images. However, much less research has been conducted on remote sensing imagery, which typically consists of many more bands in addition to the red, green, and blue bands found in natural images. In this paper, we first extensively studied a popular backdoor attack, BadNets, applied to a remote sensing dataset, where the trigger was planted in all of the bands in the data. Our results showed that SOTA defense mechanisms, including Neural Cleanse, TABOR, Activation Clustering, Fine-Pruning, GangSweep, Strip, DeepInspect, and Pixel Backdoor, had difficulties detecting and mitigating the backdoor attack. We then proposed an explainable AI-guided backdoor attack specifically for remote sensing imagery by placing triggers in the image sub-bands. Our proposed attack model even poses stronger challenges to these SOTA defense mechanisms, and no method was able to defend it. These results send an alarming message about the catastrophic effects the backdoor attacks may have on satellite imagery. [ABSTRACT FROM AUTHOR]

High-pressure pipelines are critical for transporting hazardous materials over long distances, but they face threats from third-party interference activities. Preventive measures are implemented, but interference accidents can still occur, making the need for high-quality detection strategies vital. This paper proposes an end-to-end Artificial Intelligence of Things (AIoT) solution to detect potential interference threats in real time. The solution involves developing a smart visual sensor capable of processing images using state-of-the-art computer vision algorithms and transmitting alerts to pipeline operators in real time. The system's core is based on the object-detection model (e.g., You Only Look Once version 4 (YOLOv4) and DETR with Improved deNoising anchOr boxes (DINO)), trained on a custom Pipeline Visual Threat Assessment (Pipe-VisTA) dataset. Among the trained models, DINO was able to achieve the best Mean Average Precision (mAP) of 71.2% for the unseen test dataset. However, for the deployment on a limited computational-ability edge computer (i.e., the NVIDIA Jetson Nano), the simpler and TensorRT-optimized YOLOv4 model was used, which achieved a mAP of 61.8% for the test dataset. The developed AIoT device captures the image using a camera, processes on the edge using the trained YOLOv4 model to detect the potential threat, transmits the threat alert to a Fleet Portal via LoRaWAN, and hosts the alert on a dashboard via a satellite network. The device has been fully tested in the field to ensure its functionality prior to deployment for the SEA Gas use-case. The AIoT smart solution has been deployed across the 10km stretch of the SEA Gas pipeline across the Murray Bridge section. In total, 48 AIoT devices and three Fleet Portals are installed to ensure the line-of-sight communication between the devices and portals. [ABSTRACT FROM AUTHOR]

Occluded person re‐identification (Re‐ID) is to identify a particular person when the person's body parts are occluded. However, challenges remain in enhancing effective information representation and suppressing background clutter when considering occlusion scenes. This paper proposes a novel attention map‐driven network (AMD‐Net) for occluded person Re‐ID. In AMD‐Net, human parsing labels are introduced to supervise the generation of partial attention maps, while a spatial‐frequency interaction module is suggested to complement the higher‐order semantic information from the frequency domain. Furthermore, a Taylor‐inspired feature filter for mitigating background disturbance and extracting fine‐grained features is proposed. Moreover, a part‐soft triplet loss, which is robust to non‐discriminative body partial features is also designed. Experimental results on Occluded‐Duke, Occluded‐Reid, Market‐1501, and Duke‐MTMC datasets show that this method outperforms existing state‐of‐the‐art methods. The code is available at: https://github.com/ISCLab‐Bistu/SA‐ReID. [ABSTRACT FROM AUTHOR]

Most existing multi‐view stereo (MVS) methods fail to consider global context information in the stage of feature extraction and cost aggregation. As transformers have shown remarkable performance on various vision tasks due to their ability to perceive global contextual information, this paper proposes a transformer‐based feature enhancement network (TF‐MVSNet) to facilitate feature representation learning by combining local features (both 2D and 3D) with long‐range contextual information. To reduce memory consumption of feature matching, the cross‐attention mechanism is leveraged to efficiently construct 3D cost volumes under the epipolar constraint. Additionally, a colour‐guided network is designed to refine depth maps at a coarse stage, hence reducing incorrect depth predictions at a fine stage. Extensive experiments were performed on the DTU dataset and Tanks and Temples (T&T) benchmark and results are reported. [ABSTRACT FROM AUTHOR]

In this study, we investigated autonomous vessel obstacle avoidance using advanced techniques within the Guidance, Navigation, and Control (GNC) framework. We propose a Mixed Integer Linear Programming (MILP) based Guidance system for robust path planning avoiding static and dynamic obstacles. For Navigation, we suggest a multi-modal neural network for perception, demonstrating the identification of obstacle type, position, and orientation using imaging sensors. Additionally, the paper compares an error-based PID control strategy and a Model Predictive Control (MPC) scheme as well. This evaluation aids in better evaluating their performance and determining their applicability within the GNC scheme. We detail the implementation of these systems, present simulation results, and offer a performance evaluation using an experimental dataset. Our findings, analysed through qualitative discussion and quantitative performance indicators, contribute to advancements in autonomous navigation and the control strategies to achieve it. [ABSTRACT FROM AUTHOR]

The increase in both the frequency and magnitude of natural disasters, coupled with recent advancements in artificial intelligence, has introduced prospects for investigating the potential of new technologies to facilitate disaster response processes. Preliminary Damage Assessment (PDA), a labor-intensive procedure necessitating manual examination of residential structures to ascertain post-disaster damage severity, stands to significantly benefit from the integration of computer vision-based classification algorithms, promising efficiency gains and heightened accuracy. Our paper proposes a Vision Transformer (ViT)-based model for classifying damage severity, achieving an accuracy rate of 95%. Notably, our model, trained on a repository of over 18,000 ground-level images of homes with damage severity annotated by damage assessment professionals during the 2020–2022 California wildfires, represents a novel application of ViT technology within this domain. Furthermore, we have open sourced this dataset—the first of its kind and scale—to be used by the research community. Additionally, we have developed a publicly accessible web application prototype built on this classification algorithm, which we have demonstrated to disaster management practitioners and received feedback on. Hence, our contribution to the literature encompasses the provision of a novel imagery dataset, an applied framework from field professionals, and a damage severity classification model with high accuracy. [ABSTRACT FROM AUTHOR]

The field of human event recognition using visual data in smart environments has emerged as a fruitful and successful area of study, with extensive research and development efforts driving significant advancements. These advancements have not only provided valuable insights, but also led to practical applications in various domains. In this context, human actions, activities, interactions, and behaviors can all be considered as events of interest in smart environments. However, when it comes to smart classrooms, there is a lack of unified consensus on the definition of the term "human event." This lack of agreement presents a significant challenge for educators, researchers, and developers, as it hampers their ability to precisely identify and classify the specific situations that are relevant within the educational context. The aim of this paper is to address this challenge by conducting a systematic literature review of relevant events in smart classrooms, with a focus on their applications in assistive technology. The review encompasses a comprehensive analysis of 227 published documents spanning from 2012 to 2022. It delves into key algorithms, methodologies, and applications of vision-based event recognition in smart environments. As the primary outcome, the review identifies the most significant events, classifying them according to single person behavior, or multiple-person interactions, or object-person interactions. It also examines their practical applications within the educational context. The paper concludes with a discussion on the relevance and practicality of vision-based human event recognition in smart classrooms, particularly in the post-COVID era. [ABSTRACT FROM AUTHOR]

Detecting skeletal or bone-related deformities in model and aquaculture fish is vital for numerous biomedical studies. In biomedical research, model fish with bone-related disorders are potential indicators of various chemically induced toxins in their environment or poor dietary conditions. In aquaculture, skeletal deformities are affecting fish health, and economic losses are incurred by fish farmers. This survey paper focuses on showcasing the cutting-edge image analysis tools and techniques based on artificial intelligence that are currently applied in the analysis of bone-related deformities in aquaculture and model fish. These methods and tools play a significant role in improving research by automating various aspects of the analysis. This paper also sheds light on some of the hurdles faced when dealing with high-content bioimages and explores potential solutions to overcome these challenges. [ABSTRACT FROM AUTHOR]

Artificial Intelligence has been touted as the next big thing that is capable of altering the current landscape of the technological domain. Through the use of Artificial Intelligence and Machine Learning, pioneering work has been undertaken in the area of Visual and Object Detection. In this paper, we undertake the analysis of a Visual Assistant Application for Guiding Visually-Impaired Individuals. With recent breakthroughs in computer vision and supervised learning models, the problem at hand has been reduced significantly to the point where new models are easier to build and implement than the already existing models. Different object detection models exist now that provide object tracking and detection with great accuracy. These techniques have been widely used in automating detection tasks in different areas. A few newly discovered detection approaches, such as the YOLO (You Only Look Once) and SSD (Single Shot Detector) approaches, have proved to be consistent and quite accurate at detecting objects in real-time. This paper attempts to utilize the combination of these state-of-the-art, realtime object detection techniques to develop a good base model. This paper also implements a 'Visual Assistant' for visually impaired people. The results obtained are improved and superior compared to existing algorithms. [ABSTRACT FROM AUTHOR]

As urbanization increases, streetlights have become significant consumers of electrical power, making it imperative to develop effective control methods for sustainability. This paper offers a comprehensive review on control methods of smart streetlight systems, setting itself apart by introducing a novel light scheme framework that provides a structured classification of various light control patterns, thus filling an existing gap in the literature. Unlike previous studies, this work dives into the technical specifics of individual research papers and methodologies, ranging from basic to advanced control methods like computer vision and deep learning, while also assessing the energy consumption associated with each approach. Additionally, the paper expands the discussion to explore alternative functionalities for streetlights, such as serving as communication networks, environmental monitors, and electric vehicle charging stations. This multidisciplinary research aims to be a pivotal resource for both academics and industry professionals, laying the groundwork for future innovation and sustainable solutions in urban lighting. [ABSTRACT FROM AUTHOR]

Photovoltaic (PV) fault detection is crucial because undetected PV faults can lead to significant energy losses, with some cases experiencing losses of up to 10%. The efficiency of PV systems depends upon the reliable detection and diagnosis of faults. The integration of Artificial Intelligence (AI) techniques has been a growing trend in addressing these issues. The goal of this systematic review is to offer a comprehensive overview of the recent advancements in AI-based methodologies for PV fault detection, consolidating the key findings from 31 research papers. An initial pool of 142 papers were identified, from which 31 were selected for in-depth review following the PRISMA guidelines. The title, objective, methods, and findings of each paper were analyzed, with a focus on machine learning (ML) and deep learning (DL) approaches. ML and DL are particularly suitable for PV fault detection because of their capacity to process and analyze large amounts of data to identify complex patterns and anomalies. This study identified several AI techniques used for fault detection in PV systems, ranging from classical ML methods like k-nearest neighbor (KNN) and random forest to more advanced deep learning models such as Convolutional Neural Networks (CNNs). Quantum circuits and infrared imagery were also explored as potential solutions. The analysis found that DL models, in general, outperformed traditional ML models in accuracy and efficiency. This study shows that AI methodologies have evolved and been increasingly applied in PV fault detection. The integration of AI in PV fault detection offers high accuracy and effectiveness. After reviewing these studies, we proposed an Artificial Neural Network (ANN)-based method for PV fault detection and classification. [ABSTRACT FROM AUTHOR]

The manufacturing sector is a fundamental pillar of worldwide economies, contributing markedly to global economic growth. However, the manufacturing industry is persistently confronted with issues impeding its development and expansion, such as manpower shortages, safety concerns, high initial investment for installation, and long return on investment. Within this context, machine tending has become a crucial component of the manufacturing process and potentially serves as a viable solution to the afore-mentioned predicaments. Over the past 5 years, implementing automated machine-tending systems has widely extended from simulation or laboratory environments to practical applications in manufacturing workshops as robotics and artificial intelligence develop rapidly. To fully benefit from the potential of machine-tending applications, it is necessary to comprehend and tackle its associated challenges. Therefore, this paper aims to contribute to the evolution of machine-tending applications by investigating the impacts of emerging trends of advanced technologies, such as autonomous mobile robots, computer vision, machine learning, and deep learning. This systematic literature review is based on the Protocol of Preferred Reporting Items for Systematic Review and Meta-Analyses to analyze the 50 scientific literature related to machine tending in the last five years. [ABSTRACT FROM AUTHOR]

The recognition of steel microstructure images plays a crucial role in the metallographic analysis process. Although some progress has been made through the application of artificial intelligence algorithms, several challenges remain. First, existing algorithms exhibit weak nonlinear feature extraction capabilities and noticeable limitations. Second, they overlook the intrinsic noise and redundant interference present in microscopic images. To address these issues, this paper investigates the automatic recognition of metallographic tissues by leveraging residual structures in deep neural networks. An enhanced residual network model based on transfer learning is proposed, which utilizes the pre-trained weights from the ImageNet dataset to facilitate learning with small sample data. This network offers higher classification accuracy and higher F1 scores. In addition, a deep residual shrinkage network model based on an attention mechanism is proposed. This model incorporates an attention sub-network into the original residual module and employs a soft threshold function to eliminate redundant features, including noise. The proposed algorithms are evaluated against various convolutional neural networks using 20 types of metallographic test sets. The experimental results showed that both methods have high accuracy rates of 95% and 94.44%, respectively, and F1 scores of 0.9464 and 0.9419. While maintaining the complexity of the model, there has been a significant improvement in accuracy, and the models exhibit strong generalization capabilities. Our research contributes to enhancing production efficiency, strengthening quality control, and improving material performance through computer vision technology. [ABSTRACT FROM AUTHOR]

In recent years the popularity of smartphones has been on the rise, the importance of user experience is being discussed more frequently, and interface design is determined as a crucial technique in the interactive design of mobile devices. As both supply and demand for smartphones have grown, the interactive interface designs are obtained as significant, and attention is paid to their effects. The traditional method is only applicable to computers, has a limited user base, and has poor efficiency and effectiveness. However, the operation and functionality of mobile phones are diminished due to the installation of unwanted applications. Hence it is particularly evident in the interactive art approach in which there has been limited innovation in core capabilities and few distinguishing features among more established programmes. Inorder to perform speedy progress, the Convolutional Neural Network (CNN) and Deep Learning (DL) are widely determined. Furthermore, Style Transfer and Target Detection are emerging as popular because of their significance to the field of visual research. So this paper proposes the prevalent quasi- and flat-materialized style and analyzes the skills necessary for applications. The proposed method achieved superior performance when validated with MPI Sintel and Train2020 MSCOCO datasets. [ABSTRACT FROM AUTHOR]

The recognition of steel microstructure images plays a crucial role in the metallographic analysis process. Although some progress has been made through the application of artificial intelligence algorithms, several challenges remain. First, existing algorithms exhibit weak nonlinear feature extraction capabilities and noticeable limitations. Second, they overlook the intrinsic noise and redundant interference present in microscopic images. To address these issues, this paper investigates the automatic recognition of metallographic tissues by leveraging residual structures in deep neural networks. An enhanced residual network model based on transfer learning is proposed, which utilizes the pre-trained weights from the ImageNet dataset to facilitate learning with small sample data. This network offers higher classification accuracy and higher F1 scores. In addition, a deep residual shrinkage network model based on an attention mechanism is proposed. This model incorporates an attention sub-network into the original residual module and employs a soft threshold function to eliminate redundant features, including noise. The proposed algorithms are evaluated against various convolutional neural networks using 20 types of metallographic test sets. The experimental results showed that both methods have high accuracy rates of 95% and 94.44%, respectively, and F1 scores of 0.9464 and 0.9419. While maintaining the complexity of the model, there has been a significant improvement in accuracy, and the models exhibit strong generalization capabilities. Our research contributes to enhancing production efficiency, strengthening quality control, and improving material performance through computer vision technology. [ABSTRACT FROM AUTHOR]

Given that AI has been developing quickly in recent years, its usage has become increasingly important. It has had a significant influence on a variety of industries, including sports. Although not many experts are discussing it, the use of AI in sports has become commonplace. Predictive analytics has made it possible for many different kinds of athletic events to produce more precise outcomes and judgements. Making the game more difficult on and off the pitch is one of sports AI's main objectives. As a result, it is critical for sports firms to always stay current. As we analyse this document, our goal is to comprehend and research fresh, cutting-edge ways to apply artificial intelligence (AI) to the world of sports. Elite sports require objective evaluation of an athlete's performance to enable in-depth quantum photonics research. The shortcomings of manual performance analysis techniques are solved by the application of automatic detection as well as recognition of sport-specific motions. Inertial measurement unit (IMU) and/or computer vision data inputs were used in this work to recognise sport-specific movements. The goal of the study was to conduct a comprehensive evaluation of literature on ML and DL for these purposes. There was a multi-database search done. Included papers must to have examined a sport-specific movement and used machine learning or deep learning techniques to construct a model. [ABSTRACT FROM AUTHOR]

Image recognition methods for the partial inspection of fire safety equipment – a study considering machine learning techniques and the integration of expert knowledge This paper explores the potential application of artificial intelligence (AI) and computer vision in the context of Building Information Modeling (BIM) for documenting fire safety equipment. Detection algorithms, particularly current You Only Look Once (YOLO) models, are utilized to automatically identify fire safety equipment such as fire extinguishers, fire blankets, smoke detectors, and fire alarms in images. The results demonstrate high detection accuracy in both images. Future work aims to expand automated detection by directly integrating it into BIM models. In addition, the importance of expert knowledge in determining the extinguishing agent type of a fire extinguisher is addressed to verify and, if necessary, correct the prediction of an AI‐based fire safety inspection. The developed AI applications aim to increase the level of automation in fire safety inspections to improve the safety of buildings in the operational phase. [ABSTRACT FROM AUTHOR]

Neuropsychiatric disorders affect the lives of individuals from cognitive, emotional, and behavioral aspects, impact the quality of their lives, and even lead to death. Outside the medical area, these diseases have also started to be the subject of investigation in the field of Artificial Intelligence: especially Natural Language Processing (NLP) and Computer Vision. The usage of NLP techniques to understand medical symptoms eases the process of identifying and learning more about language-related aspects of neuropsychiatric conditions, leading to better diagnosis and treatment options. This survey shows the evolution of the detection of linguistic markers specific to a series of neuropsychiatric disorders and symptoms. For each disease or symptom, the article presents a medical description, specific linguistic markers, the results obtained using markers, and datasets. Furthermore, this paper offers a critical analysis of the work undertaken to date and suggests potential directions for future research in the field. [ABSTRACT FROM AUTHOR]

This paper presents a computer vision-based approach to chronic subdural hematoma segmentation that can be performed by one click. Chronic subdural hematoma is estimated to occur in 0.002–0.02% of the general population each year and the risk increases with age, with a high frequency of about 0.05–0.06% in people aged 70 years and above. In our research, we developed our own dataset, which includes 53 series of CT scans collected from 21 patients with one or two hematomas. Based on the dataset, we trained two neural network models based on U-Net architecture to automate the manual segmentation process. One of the models performed segmentation based only on the current frame, while the other additionally processed multiple adjacent images to provide context, a technique that is more similar to the behavior of a doctor. We used a 10-fold cross-validation technique to better estimate the developed models' efficiency. We used the Dice metric for segmentation accuracy estimation, which was 0.77. Also, for testing our approach, we used scans from five additional patients who did not form part of the dataset, and created a scenario in which three medical experts carried out a hematoma segmentation before we carried out segmentation using our best model. We developed the OsiriX DICOM Viewer plugin to implement our solution into the segmentation process. We compared the segmentation time, which was more than seven times faster using the one-click approach, and the experts agreed that the segmentation quality was acceptable for clinical usage. [ABSTRACT FROM AUTHOR]

This work was aimed at developing a prototype system based on multispectral digital photogrammetry to support tests required by international regulations for new Plant Protection Products (PPPs). In particular, the goal was to provide a system addressing the challenges of a new PPP evaluation with a higher degree of objectivity with respect to the current one, which relies on expert evaluations. The system uses Digital Photogrammetry, which is applied to multispectral acquisitions and Artificial Intelligence (AI). The goal of this paper is also to simplify the present screening process, moving it towards more objective and quantitative scores about phytotoxicity. The implementation of an opportunely trained AI model for phytotoxicity prediction aims to convert ordinary human visual observations, which are presently provided with a discrete scale (forbidding a variance analysis), into a continuous variable. The technical design addresses the need for a reduced dataset for training the AI model and relating discrete observations, as usually performed, to some proxy variables derived from the photogrammetric multispectral 3D model. To achieve this task, an appropriate photogrammetric multispectral system was designed. The system operates in multi-nadiral-view mode over a bench within a greenhouse exploiting an active system for lighting providing uniform and diffuse illumination. The whole system is intended to reduce the environmental variability of acquisitions tending to a standard situation. The methodology combines advanced image processing, image radiometric calibration, and machine learning techniques to predict the General Phytotoxicity percentage index (PHYGEN), a crucial measure of phytotoxicity. Results show that the system can generate reliable estimates of PHYGEN, compliant with existing accuracy standards (even from previous PPPs symptom severity models), using limited training datasets. The proposed solution addressing this challenge is the adoption of the Logistic Function with LASSO model regularization that has been shown to overcome the limitations of a small sample size (typical of new PPP trials). Additionally, it provides the estimate of a numerical continuous index (a percentage), which makes it possible to tackle the objectivity problem related to human visual evaluation that is presently based on an ordinal discrete scale. In our opinion, the proposed prototype system could have significant potential in improving the screening process for new PPPs. In fact, it works specifically for new PPPs screening and, despite this, it has an accuracy consistent with the one ordinarily accepted for human visual approaches. Additionally, it provides a higher degree of objectivity and repeatability. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) provides a collaborative infrastructure to communicate smart devices with cloud-edge healthcare applications, medical devices, wearable biosensors, etc. On the other hand, crowd counting as one of computer vision approaches is an emerging topic to detect any objects with static or dynamic mobility in the IoT environments. Smart crowd counting enables pattern recognition for many intelligent applications such as microbiology, surveillance, healthcare systems, crowdedness estimation, and other environmental case studies. According to complicated capturing systems in the IoT environments, crowd counting methods can influence on performance of object detection in the critical case studies using Artificial Intelligence (AI)-based approaches such as machine learning, deep learning, collaborative learning, fuzzy logic and meta-heuristic algorithms. This paper provides a new comprehensive technical analysis for existing AI-based crowd counting approaches in healthcare and medical systems, biotechnology and IoT environments. Meanwhile, it presents a discussion on the existing case studies with respect to analyzing technical aspects and applied algorithms to enhance pattern prediction factors. Finally, some new innovative efforts and challenges are presented for new research upcoming and open issues. [ABSTRACT FROM AUTHOR]

In recent years, developments in the fields of computer vision and artificial intelligence have created new opportunities for studying sports performance. With advancements in computer vision and artificial intelligence, it is now possible to use massive volumes of video data to get deeper insights into sports dynamics, especially in precision-based video sports like table tennis. To develop skills, a thorough examination of player movements is required. With the development of vision-based human posture recognition, computers can function like humans and derive intelligent judgments from outside data. This paper presents a novel method that uses graph convolutional neural networks (GCNNs) to detect and identify improper postures and movements in table tennis players. In addition to conventional methods, the proposed method dissects the human skeleton into finely detailed head, trunk, and leg features. Deep-level features that offer a more comprehensive understanding of athlete movements are extracted after feeding these features into the network. The softmax classifier combines these features to produce the final recognition result. The effectiveness of this approach has been evaluated through extensive experimentation. The GCN model performs remarkably well, with accuracy rates of 86.4% on the NTU-RGB + D dataset and 79.1% on the COCO dataset. This accomplishment is significant because the model consistently yields accurate detection results, even in complex and occlusion-filled scenes. In comparison tests, the proposed model performs better than GraphSAGE, GAT, ChebNet, GIN, and GC-LSTM in identifying relevant body part movements in table tennis players while ignoring irrelevant ones. According to proposed experiments, this enhances the recognition of improper postures in most table tennis actions. [ABSTRACT FROM AUTHOR]

Ambiguous optical illusions have been a paradigmatic object of fascination, research and inspiration in arts, psychology and video games. However, accurate computational models of perception of ambiguous figures have been elusive. In this paper, we design and train a deep neural network model to simulate human perception of the Necker cube, an ambiguous drawing with several alternating possible interpretations. Defining the weights of the neural network connection using a quantum generator of truly random numbers, in agreement with the emerging concepts of quantum artificial intelligence and quantum cognition, we reveal that the actual perceptual state of the Necker cube is a qubit-like superposition of the two fundamental perceptual states predicted by classical theories. Our results finds applications in video games and virtual reality systems employed for training of astronauts and operators of unmanned aerial vehicles. They are also useful for researchers working in the fields of machine learning and vision, psychology of perception and quantum–mechanical models of human mind and decision making. [ABSTRACT FROM AUTHOR]

With the rapid development of object detection technology for unmanned aerial vehicles (UAVs), it is convenient to collect data from UAV aerial photographs. They have a wide range of applications in several fields, such as monitoring, geological exploration, precision agriculture, and disaster early warning. In recent years, many methods based on artificial intelligence have been proposed for UAV object detection, and deep learning is a key area in this field. Significant progress has been achieved in the area of deep-learning-based UAV object detection. Thus, this paper presents a review of recent research on deep-learning-based UAV object detection. This survey provides an overview of the development of UAVs and summarizes the deep-learning-based methods in object detection for UAVs. In addition, the key issues in UAV object detection are analyzed, such as small object detection, object detection under complex backgrounds, object rotation, scale change, and category imbalance problems. Then, some representative solutions based on deep learning for these issues are summarized. Finally, future research directions in the field of UAV object detection are discussed. [ABSTRACT FROM AUTHOR]

Introduction: Oral squamous cell carcinoma (OSCC) presents a significant global health challenge. The integration of artificial intelligence (AI) and computer vision holds promise for the early detection of OSCC through the analysis of digitized oral photographs. This literature review explores the landscape of AIdriven OSCC automatic detection, assessing both the performance and limitations of the current state of the art. Materials and Methods: An electronic search using several data base was conducted, and a systematic review performed in accordance with PRISMA guidelines (CRD42023441416). Results: Several studies have demonstrated remarkable results for this task, consistently achieving sensitivity rates exceeding 85% and accuracy rates surpassing 90%, often encompassing around 1000 images. The review scrutinizes these studies, shedding light on their methodologies, including the use of recent machine learning and pattern recognition approaches coupled with different supervision strategies. However, comparing the results from different papers is challenging due to variations in the datasets used. Discussion: Considering these findings, this review underscores the urgent need for more robust and reliable datasets in the field of OSCC detection. Furthermore, it highlights the potential of advanced techniques such as multi-task learning, attention mechanisms, and ensemble learning as crucial tools in enhancing the accuracy and sensitivity of OSCC detection through oral photographs. Conclusion: These insights collectively emphasize the transformative impact of AI-driven approaches on early OSCC diagnosis, with the potential to significantly improve patient outcomes and healthcare practices. [ABSTRACT FROM AUTHOR]

Frozen sections are a useful pathologic tool, but variable image quality may impede the use of artificial intelligence and machine learning in their interpretation. We aimed to identify the current research on machine learning models trained or tested on frozen section images. We searched PubMed and Web of Science for articles presenting new machine learning models published in any year. Eighteen papers met all inclusion criteria. All papers presented at least one novel model trained or tested on frozen section images. Overall, convolutional neural networks tended to have the best performance. When physicians were able to view the output of the model, they tended to perform better than either the model or physicians alone at the tested task. Models trained on frozen sections performed well when tested on other slide preparations, but models trained on only formalin‐fixed tissue performed significantly worse across other modalities. This suggests not only that machine learning can be applied to frozen section image processing, but also use of frozen section images may increase model generalizability. Additionally, expert physicians working in concert with artificial intelligence may be the future of frozen section histopathology. [ABSTRACT FROM AUTHOR]

Computer Vision (CV) has become an essential field in Artificial Intelligence applications. Object detection and recognition (ODR) is one of the fundamental tasks of computer vision implementations. However, developing an efficient ODR model is still a significant problem. The model's execution time and speed are the most critical features during the inference or detection and recognition process, which need to be improved using the latest object detection architectures. In this paper, the handwritten detection and recognition (HDR) model is developed based on previously known algorithms with their efficiency, such as Faster R-CNN and YOLOv4 in the first hand. On the other hand, two new models capable of detecting and recognizing handwritten digits using the latest ODR algorithm are proposed, one based on the latest YOLO family architecture (YOLOv5-HDR) with high speed and accuracy and the other using the transformers architecture (DETR). To the best of our knowledge, this is the first study to achieve a details comparison between YOLOv5 and transformers-based models in handwritten digit detection. Finally, the detailed performance analysis achieved by the paper proves that the YOLOv4-based model achieved the testing inference 13% faster than Faster R-CNN. However, the proposed YOLOv5-based model outperformed the YOLOv4 and the transformers-based one as it increased the testing execution time 25% faster than the YOLOv4, three times faster than the DETR model. A further adversarial attack test has been conducted to ensure the robust performance of the proposed model. Furthermore, numerical experiment results and their analyses demonstrate the robustness and effectiveness of the proposed YOLOv5-based model being the most stable for handwritten digit detection and recognition tasks. [ABSTRACT FROM AUTHOR]

Anomaly detection in video surveillance is a highly developed subject that is attracting increased attention from the research community. There is great demand for intelligent systems with the capacity to automatically detect anomalous events in streaming videos. Due to this, a wide variety of approaches have been proposed to build an effective model that would ensure public security. There has been a variety of surveys of anomaly detection, such as of network anomaly detection, financial fraud detection, human behavioral analysis, and many more. Deep learning has been successfully applied to many aspects of computer vision. In particular, the strong growth of generative models means that these are the main techniques used in the proposed methods. This paper aims to provide a comprehensive review of the deep learning-based techniques used in the field of video anomaly detection. Specifically, deep learning-based approaches have been categorized into different methods by their objectives and learning metrics. Additionally, preprocessing and feature engineering techniques are discussed thoroughly for the vision-based domain. This paper also describes the benchmark databases used in training and detecting abnormal human behavior. Finally, the common challenges in video surveillance are discussed, to offer some possible solutions and directions for future research. [ABSTRACT FROM AUTHOR]

Increasing computational power and improving deep learning methods have made computer vision technologies pervasively common in urban environments. Their applications in policing, traffic management, and documenting public spaces are increasingly common (Ridgeway 2018, Coifman et al. 1998, Sun et al. 2020). Despite the often-discussed biases in the algorithms' training and unequally borne benefits (Khosla et al. 2012), almost all applications similarly reduce urban experiences to simplistic, reductive, and mechanistic measures. There is a lack of context, depth, and specificity in these practices that enables semantic knowledge or analysis within urban contexts, especially within the context of using and occupying urban space. This paper will critique existing uses of artificial intelligence and computer vision in urban practices to propose a new framework for understanding people, action, and public space. This paper revisits Geertz's (1973) use of thick descriptions in generating interpretive theories of culture and activity and uses this lens to establish a framework to approach evaluating the varied uses of computer vision technologies that weigh meaning. By discussing cases of implemented examples of urban computer vision—from LinkNYC and Numina's urban measurements to the Detroit Police's use of DataWorks Plus's facial recognition technology—it proposes a framework for evaluating the thickness of the algorithm's conclusions against the computational method's complexity required to produce that outcome. Further, we discuss how the framework's positioning may differ (and conflict) between different users of the technology, from engineer to urban planner and policymaker, to citizen. This paper also discusses how the current use and training of deep learning algorithms and how this process limits semantic learning and proposes three potential methodologies toward gaining a more contextually specific, urban-semantic, description of urban space relevant to urbanists. This paper contributes to the critical conversations regarding the proliferation of artificial intelligence by challenging the current applications of these technologies in the urban environment by highlighting their failures within this context while also proposing an evolution of these algorithms that may ultimately make them sensitive and useful within this spatial and cultural milieu. [ABSTRACT FROM AUTHOR]

Focused on city-scale automation, and using self-driving cars (SDCs) as a case study, this article reflects on the role of AI—and in particular, computer vision systems used for mapping and navigation—as a catalyst for urban transformation. Urban research commonly presents AI and cities as having a one-way cause-and-effect relationship, giving undue weight to AI's impact on cities and overlooking the role of cities in shaping AI. Working at the intersection of data science and social research, this paper aims to counter this trend by exploring the reverse perspective: how do cities affect the development, and expose the present limits, of SDCs? The contribution of this paper is threefold. First, by comparing urban and nonurban environments and thoroughly examining the relationship between computer vision and city-specific sociality and form, it defines machine autonomy/automation as a function of the sociotechnical milieu in which an AI system operates. Second, and related, the paper problematizes the notion of SDCs as autonomous technologies and the role it plays in envisioning contending policy arrangements and technical solutions for achieving full driving automation. Finally, the article offers insight into a materialist and spatialized understanding of AI—namely, not as an abstract quality susceptible to replication within discrete machines, but rather as a distributed property emerging through embodied interactions among a multiplicity of agents (human, non-human, and technological) within/with their environments. [ABSTRACT FROM AUTHOR]

With the improvement of industrial automation and technological progress, the number of robots continues to increase, application scenarios are becoming more and more complex, and the requirements for automation and intelligence of robots are also increasing. Due to the development of computer technology and artificial intelligence based on machine vision technical robots has received great attention inthe field of research and production. With the growth of demand, rapid and accurate identification and positioning of objects in any posture in complex spatial environments have become a research hotspot. Based on the image feature processing technology, this paper studies the autonomous target recognition and grasping of industrial robots, establishes the coordinate system of the vision system, derives the projection matrix, and builds a parallel binocular stereo vision system. The method adopted in this paper is that the claw at the end of the robot grips the object to move to different poses, which is used as the theoretical pose of the object, and the grasping result of the visual system is used as the actual pose. The two are compared to solve the grasping errors, a total of 8 comparison experiments were made, and these experimental data were collected and decomposed to draw conclusions. Experiments show that the attitude errors in the X, Y, and Z directions are 1.08°, 1.01°, and 0.92°, respectively. Compared with the previous image positioning errors, it can be found that the errors in the actual robot positioning process are too large, which is mainly caused by the uncalibrated robot; the method used can accurately, quickly, and stably realize the recognition and positioning of the target and meet the needs of the robot for real-time grasping. [ABSTRACT FROM AUTHOR]

Purpose: Problem-solving" is the most crucial key insight of scientific research. This study focuses on constructing the "problem-solving" knowledge graph of scientific domains by extracting four entity relation types: problem-solving, problem hierarchy, solution hierarchy and association. Design/methodology/approach: This paper presents a low-cost method for identifying these relationships in scientific papers based on word analogy. The problem-solving and hierarchical relations are represented as offset vectors of the head and tail entities and then classified by referencing a small set of predefined entity relations. Findings: This paper presents an experiment with artificial intelligence papers from the Web of Science and achieved good performance. The F1 scores of entity relation types problem hierarchy, problem-solving and solution hierarchy, which were 0.823, 0.815 and 0.748, respectively. This paper used computer vision as an example to demonstrate the application of the extracted relations in constructing domain knowledge graphs and revealing historical research trends. Originality/value: This paper uses an approach that is highly efficient and has a good generalization ability. Instead of relying on a large-scale manually annotated corpus, it only requires a small set of entity relations that can be easily extracted from external knowledge resources. [ABSTRACT FROM AUTHOR]

Deep learning, which is a subfield of machine learning, has opened a new era for the development of neural networks. The auto-encoder is a key component of deep structure, which can be used to realize transfer learning and plays an important role in both unsupervised learning and non-linear feature extraction. By highlighting the contributions and challenges of recent research papers, this work aims to review state-of-the-art auto-encoder algorithms. Firstly, we introduce the basic auto-encoder as well as its basic concept and structure. Secondly, we present a comprehensive summarization of different variants of the auto-encoder. Thirdly, we analyze and study auto-encoders from three different perspectives. We also discuss the relationships between auto-encoders, shallow models and other deep learning models. The auto-encoder and its variants have successfully been applied in a wide range of fields, such as pattern recognition, computer vision, data generation, recommender systems, etc. Then, we focus on the available toolkits for auto-encoders. Finally, this paper summarizes the future trends and challenges in designing and training auto-encoders. We hope that this survey will provide a good reference when using and designing AE models. [ABSTRACT FROM AUTHOR]

Breast cancer conservative treatment (BCCT) is a form of treatment commonly used for patients with early breast cancer. This procedure consists of removing the cancer and a small margin of surrounding tissue, while leaving the healthy tissue intact. In recent years, this procedure has become increasingly common due to identical survival rates and better cosmetic outcomes than other alternatives. Although significant research has been conducted on BCCT, there is no gold-standard for evaluating the aesthetic results of the treatment. Recent works have proposed the automatic classification of cosmetic results based on breast features extracted from digital photographs. The computation of most of these features requires the representation of the breast contour, which becomes key to the aesthetic evaluation of BCCT. State-of-the-art methods use conventional image processing tools that automatically detect breast contours based on the shortest path applied to the Sobel filter result in a 2D digital photograph of the patient. However, because the Sobel filter is a general edge detector, it treats edges indistinguishably, i.e., it detects too many edges that are not relevant to breast contour detection and too few weak breast contours. In this paper, we propose an improvement to this method that replaces the Sobel filter with a novel neural network solution to improve breast contour detection based on the shortest path. The proposed solution learns effective representations for the edges between the breasts and the torso wall. We obtain state of the art results on a dataset that was used for developing previous models. Furthermore, we tested these models on a new dataset that contains more variable photographs and show that this new approach shows better generalization capabilities as the previously developed deep models do not perform so well when faced with a different dataset for testing. The main contribution of this paper is to further improve the capabilities of models that perform the objective classification of BCCT aesthetic results automatically by improving upon the current standard technique for detecting breast contours in digital photographs. To that end, the models introduced are simple to train and test on new datasets which makes this approach easily reproducible. [ABSTRACT FROM AUTHOR]

In the realm of intelligent sensor systems, the dependence on Artificial Intelligence (AI) applications has heightened the importance of interpretability. This is particularly critical for opaque models such as Deep Neural Networks (DNN), as understanding their decisions is essential, not only for ethical and regulatory compliance, but also for fostering trust in AI-driven outcomes. This paper introduces the novel concept of a Computer Vision Interpretability Index (CVII). The CVII framework is designed to emulate human cognitive processes, specifically in tasks related to vision. It addresses the intricate challenge of quantifying interpretability, a task that is inherently subjective and varies across domains. The CVII is rigorously evaluated using a range of computer vision models applied to the COCO (Common Objects in Context) dataset, a widely recognized benchmark in the field. The findings established a robust correlation between image interpretability, model selection, and CVII scores. This research makes a substantial contribution to enhancing interpretability for human comprehension, as well as within intelligent sensor applications. By promoting transparency and reliability in AI-driven decision-making, the CVII framework empowers its stakeholders to effectively harness the full potential of AI technologies. [ABSTRACT FROM AUTHOR]

The presented paper investigates the problem of endoscopic bleeding detection in endoscopic videos in the form of a binary image classification task. A set of definitions of high-level visual features of endoscopic bleeding is introduced, which incorporates domain knowledge from the field. The high-level features are coupled with respective feature descriptors, enabling automatic capture of the features using image processing methods. Each of the proposed feature descriptors outputs a feature activation map in the form of a grayscale image. Acquired feature maps can be appended in a straightforward way to the original color channels of the input image and passed to the input of a convolutional neural network during the training and inference steps. An experimental evaluation is conducted to compare the classification ROC AUC of feature-extended convolutional neural network models with baseline models using regular color image inputs. The advantage of feature-extended models is demonstrated for the Resnet and VGG convolutional neural network architectures. [ABSTRACT FROM AUTHOR]

The production of food generated by agriculture has been essential for civilizations throughout time. Tillage of fields has been supported by great technological advances in several areas of knowledge, which have increased the amount of food produced at lower costs. The use of technology applied to modern agriculture has generated a research area called precision agriculture, which has providing crops with resources in an exact amount at a precise moment as one of its most relevant objectives The data analysis process in precision agriculture systems begins with the filtering of the information available, which can come from sources such as images, videos, and spreadsheets. When the information source is digital images, the process is known as segmentation, which consists of assigning a category or label to each pixel of the analyzed image. In recent years, different algorithms of segmentation have been developed that make use of different pixel characteristics, such as color, texture, neighborhood, and superpixels. In this paper, a method to segment images of leaves and fruits of tomato plants is presented, which is carried out in two stages. The first stage is based on the dominance of one of the color channels over the other two, using the R G B color model. In the case of the segmentation of the leaves, the green channel dominance is used, whereas the dominance of red channel is used for the fruits. In the second stage, the false positives generated during the previous stage are eliminated by using thresholds calculated for each pixel that meets the condition of the first stage. The results are measured by applying performance metrics: Accuracy, Precision, Recall, F1-Score, and Intersection over Union. The results for segmentation of the fruit and leaves of the tomato plants with the highest metrics is Accuracy with 98.34% for fruits and Recall with 95.08% for leaves. [ABSTRACT FROM AUTHOR]

Over the last decades, the field of medicine has witnessed significant progress in artificial intelligence (AI), the Internet of Medical Things (IoMT), and deep learning (DL) systems. Otorhinolaryngology, and imaging in its various subspecialties, has not remained untouched by this transformative trend. As the medical landscape evolves, the integration of these technologies becomes imperative in augmenting patient care, fostering innovation, and actively participating in the ever-evolving synergy between computer vision techniques in otorhinolaryngology and AI. To that end, we conducted a thorough search on MEDLINE for papers published until June 2023, utilizing the keywords 'otorhinolaryngology', 'imaging', 'computer vision', 'artificial intelligence', and 'deep learning', and at the same time conducted manual searching in the references section of the articles included in our manuscript. Our search culminated in the retrieval of 121 related articles, which were subsequently subdivided into the following categories: imaging in head and neck, otology, and rhinology. Our objective is to provide a comprehensive introduction to this burgeoning field, tailored for both experienced specialists and aspiring residents in the domain of deep learning algorithms in imaging techniques in otorhinolaryngology. [ABSTRACT FROM AUTHOR]