Wyniki wyszukiwania - BazTech

1

AIRIS: a real-time face and object detection system for threat monitoring

Urbaniak Ilona Anna, Kosek Wiktoria Maria, Kowalska Alicja Maria

Technical Transactions

|

2026

|

Vol. 123, iss. 1

art. no. e2026007

EN

This study presents AIRIS (Advanced Intelligent Recognition & Interception System), a real-time personal security monitoring platform integrating computer vision and artificial intelligence for mobile threat detection. The system is based on a three-layer architecture comprising adaptive face detection, temporal tracking, and hazardous object recognition using deep learning models. The main contribution lies in system-level integration and engineering validation under realistic deployment constraints. Individual identification combines embedding-based recognition with position-based tracking, while temporal persistence algorithms assess presence duration to identify potential risks. The implementation employs multithreaded processing and graceful degradation mechanisms to ensure reliable real-time operation in a wearable–mobile configuration. Experimental evaluation demonstrates 87% trial-level detection success for hazardous object presentation trials, 91% alert correctness, and processing throughput of 5–10 FPS with 120–180 ms latency.

2

YOLO Object Detectors for Robotics - a Comparative Study

Niżeniec Patryk, Iwanowski Marcin, Gahbler Marcin

Pomiary Automatyka Robotyka

|

2026

|

R. 30, nr 1

117--126

EN

YOLO object detectors recently became a key component of vision systems in many domains. The family of available YOLO models consists of multiple versions, each in various variants. The research reported in this paper aims to validate the applicability of members of this family to detect objects located within the robot workspace. In our experiments, we used our custom dataset and the COCO2017 dataset. To test the robustness of investigated detectors, the images of these datasets were subject to distortions. The results of our experiments, including variations of training/testing configurations and models, may support the choice of the appropriate YOLO version for robotic vision tasks.

PL

Detektory obiektów YOLO stały się ostatnimi czasy kluczowym elementem systemów wizyjnych w wielu dziedzinach. Rodzina dostępnych modeli YOLO składa się z wielu wersji, z których każda występuje w różnych wariantach. Badania opisane w niniejszej pracy mają na celu zweryfikowanie przydatności członków tej rodziny do wykrywania obiektów znajdujących się w przestrzeni roboczej robota. W eksperymentach wykorzystano nasz własny zbiór danych oraz zbiór COCO2017. Aby przetestować odporność badanych detektorów, obrazy z tych zbiorów poddano zniekształceniom. Wyniki eksperymentów, uwzględniające różne konfiguracje treningowe/testowe oraz modele, mogą stanowić wsparcie przy wyborze odpowiedniej wersji YOLO dla zadań związanych z wizją robotyczną.

3

Comparative analysis of effective AI-based 3D multi-object detection and tracking methods for autonomous driving

Dheepika P. S., Umadevi V.

Journal of Automation Mobile Robotics and Intelligent Systems

|

2026

|

Vol. 20, No. 1

113--120

EN

Object detection is a crucial task for autonomous driving, and different autonomous vehicles have varying perceptions. The advancements of object detection paved the way for 3D object detection, which is considered to be the central component of perception systems that predict obstacles, vehicles, pedestrians and other key features of the environmental backgorund. Generally, various sensors and cameras are used in autonomous driving producing accurate perediction of objects. Several algorithms have been employed in object detection, but they have not produced effective outcomes. Thus, the present study implements HDL‐MODT (hybrid deep learning based multi‐object detection and tracking) using a sensor fusion approach. It uses solid‐ state LiDAR, pseudo‐LiDAR and an RGB camera to capture objects and provide effective tracking abilities. Initially, the pre‐processing methods involved noise removal using an A‐Fuzzy (adaptive fuzzy) filter. Contrast enhancement is then performed using the MSO (moth swarm optimization) algorithm, and feature segmentation is done by LGAN (lightweight general adversial networks), where both channel and position attention mechanisms provide precise segmentation. The YOLOv4 approach is deployed for detection of objects such as ground, vehicles, pedstrians and obstacles. Finally, the tracking of objects is performed using IUKF (improved unscented Kalman filter). The simulation of the proposed method is demonstrated by using MATLAB R2020 simulation tool; the performance of the proposed method is also predicted by comparing the results with exisitng algorithms.

4

Efficient weapon detection using convolutional and transformer-based Deep Learning Models

Gomulka Kamil

International Journal of Electronics and Telecommunications

|

2026

|

Vol. 72, No. 1

art. no. 31, s. 1--10

EN

Detecting weapons in public spaces remains a significant challenge in computer vision and public safety applications. While deep learning models have achieved great progress in general object detection, there is still a lack of focused studies on class-specific detection tasks, in particular those using new architectures such as transformers. In this work, a comprehensive evaluation of the state-of-the-art deep learning object detection approaches is conducted, including convolution and transformer-based architectures. Therefore, a dedicated large-scale dataset that combines images from multiple public sources is introduced, with a focus on three main weapons categories, enabling a more targeted evaluation. Furthermore, in the paper, the effectiveness of the best-performing architecture is further improved with proposed modifications, including architectural changes and determining a suitable loss function. Finally, the obtained detection approach achieves superior detection results, as evidenced by all performance criteria.

5

Real time object detection for autonomous AUVs using an attention-based fast-RCNN framework

Boudhane Mohcine, Toulni Hamza

International Journal of Applied Mathematics and Computer Science

|

2026

|

Vol. 36, no. 1

67--79

EN

This article considers the problem of fish monitoring in an underwater environment, where many problems might occur, including occlusion, pose changes, and complexity of the scene. Recognizing fish behavior is very important to develop various types of technologies able to provide more precise estimations and monitoring of fish populations in a long term. In this paper, we propose a novel method for underwater fish monitoring (shape modeling and pose estimation). Two main aspects of underwater image processing will be studied: classification and localisation. Additionally, we extract key point features from fish patterns. The fish position and motion are not sufficient features to avoid scene problems. Skeleton extraction could offer us a large range of additional information. It models an object as a set of points of a certain manifold. The 3-dimensional fish pose, along the track of its 3D motion, could depend on curve segments of the underlying manifold. Faster reccurent conventional neural networks (faster R-CNNs) will be used to extract the fish skeleton in different poses. Also, a 3-dimensional trajectory of multiple fish will be derived using a Kalman filter based on the previous feature matching process. The simulation is made for live fish in a fish tank. Experimental results show that our method outperforms relevant models in terms of precision, achieving a minimal accuracy of 94.2%.

6

Comparative analysis of DeepSORT, ByteTrack and StrongSORT algorithms for multi-object tracking in UAV-based video surveillance

Safonyk Andrii, Podvyshennyi Viktor, Naumchuk Oleksandr

Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska

|

2026

|

T. 16, nr 1

116--120

EN

This paper presents a comparative analysis of state-of-the-art multi-object tracking algorithms applied in UAV-based video surveillance systems. The performance results of three advanced tracking methods – DeepSORT, ByteTrack, and StrongSORT – integrated with the YOLOv8 object detector are presented. A mathematical description and experimental simulations were conducted to evaluate the accuracy, stability, and computational performance of the algorithms in dynamic and complex scenes. The obtained results indicate that the StrongSORT + YOLOv8 combination provides the best balance between accuracy and robustness, whereas the ByteTrack method demonstrates high track continuity in high-density environments. The proposed approach can be utilized to enhance the efficiency of UAV-based autonomous monitoring systems.

PL

W tym artykule przedstawiono analizę porównawczą najnowocześniejszych algorytmów śledzenia wielu obiektów stosowanych w systemach monitoringu wizyjnego opartych na bezzałogowych statkach powietrznych (UAV). Przedstawiono wyniki działania trzech zaawansowa nych metod śledzenia – DeepSORT, ByteTrack i StrongSORT – zintegrowanych z detektorem obiektów YOLOv8. Przeprowadzono opis matematyczny i symulacje eksperymentalne w celu oceny dokładności, stabilności i wydajności obliczeniowej algorytmów w dynamicznych i złożonych scenach. Uzyskane wyniki wskazują, że połączenie StrongSORT + YOLOv8 zapewnia najlepszą równowagę między dokładnością a odpornością, podczas gdy metoda ByteTrack wykazuje wysoką ciągłość śledzenia w środowiskach o dużej gęstości. Proponowane podejście może być wykorzystane do zwiększenia wydajności autonomicznych systemów monitorowania opartych na bezzałogowych statkach powietrznych.

7

Intelligent tool management with an enhanced six-channel you only look once model and structural similarity index measure analysis

Marciniak Kacper, Majewski Paweł, Lampa Piotr, Mrzygłód Mariusz, Reiner Jacek

Advances in Science and Technology. Research Journal

|

2026

|

Vol. 20, no. 1

462--476

EN

Tool storage systems are an integral component of the production chain in modern manufacturing facilities. Automated vertical storage systems are commonly employed to store and manage tools and equipment required for rapid replacement or re-tooling during the production process. In such a scenario, any error made by a warehouse operator can disrupt the inventory system, leading to operational issues or even halting the production line. To address the challenges of storage control and operator error identification, this paper proposes a vision-based system capable of detecting changes within the storage space and determining their directionality. The proposed solution leverages a custom synthetic dataset generation process and a hybrid processing method, combining a 6-channel enhanced YOLOv8 (You Only Look Once) model with Structural Similarity Index Measure (SSIM) analysis. This approach effectively identifies the location and direction of changes (e.g. object removal or addition) and is characterised by robustness to domain shifts and other disturbances, such as variations in illumination or object relocation, which commonly occur during normal operation. The enhanced model utilises a 6-channel input, integrating ”before” and ”after” images while retaining full colour space information - a capability not achievable with the standard YOLO models. Furthermore, the two-stage processing method that incorporates SSIM analysis significantly improves the recall rate of the developed solution. Comprehensive validation on prepared test datasets demonstrated an F1-score of 95.1, with Average Precision (AP50) and Average Recall (AR50) of 88.1 and 79.7, respectively.

8

Aplikacja do rozpoznawania pionowych znaków drogowych

Grochowski Szymon, Kula Sebastian

Studia i Materiały Informatyki Stosowanej

|

2025

|

T. 17, nr 2

38--41

PL

W pracy przedstawiono aplikację do rozpoznawania pionowych znaków drogowych z użyciem modelu sztucznej inteligencji, zaprojektowaną w celu poprawy bezpieczeństwa ruchu drogowego. Model został przetrenowany na przygotowanym zbiorze danych obejmującym zdywersyfikowane obrazy, wzbogacone technikami augmentacji. Aplikacja umożliwia wykrywanie znaków drogowych z kamery internetowej oraz nagrań wideo. Model sztucznej inteligencji wykazuje potencjał do zastosowań w systemach wsparcia kierowców i technologii autonomicznych pojazdów.

EN

This paper presents an application for recognizing vertical traffic signs using an artificial intelligence model, designed to enhance road safety. The model was trained on a prepared dataset comprising diversified images, enriched with augmentation techniques. The application enables the detection of traffic signs from webcam feeds and video recordings. The artificial intelligence model shows potential for use in driver assistance systems and autonomous vehicle technologies.

9

Hoofed animal detection in UAV thermal images using Balanced Random Forest and CNN features

Włodarczyk Dorota, Jóźków Grzegorz

Reports on Geodesy and Geoinformatics

|

2025

|

Vol. 120

1--13

PL

Wildlife monitoring is vital to conservation efforts and the prevention of animal-related negative impacts on human activities and ecosystems. The use of Unmanned Aerial Vehicles (UAVs) enables data collection with no harm to wildlife and in difficult field conditions. This study proposes a method of detecting hoofed animals in UAV-acquired thermal images, addressing the challenges of low-resolution thermal imaging and the presence of other heated objects hindering simple temperature analysis and image segmentation. The proposed method uses machine learning algorithms and is designed to work with a limited size of training dataset. The method consists of an initial segmentation step that detects potential animals based on thermal and geometrical signatures, followed by classification using a Balanced Random Forest (BRF) algorithm. One of the key aspects of the proposed method is the use of geometric and thermal features along with multi-scale Convolutional Neural Network (CNN) extracted feature representations in BRF. The benefit of the BRF is its speed, little requirement regarding the amount of training data, and its capacity to work with an imbalanced number of objects in different classes. The dataset was collected during two UAV flights over a fenced enclosure with wild hoofed animals. The proposed approach showed high efficiency, achieving an overall accuracy of 90%. These results confirm the feasibility of UAV-based animal detection based solely on thermal images collected during the day and showing many other heated objects. The method provides a solution for wildlife monitoring, with potential adaptability to different species and further applications.

10

Dangerous items’ detection in surveillance camera images using Faster R ‑CNN

Omiotek Zbigniew

Przegląd Elektrotechniczny

|

2025

|

R. 101, nr 5

156--168

EN

The Faster R -CNN with different backbone networks was used to detect dangerous objects in the study. The best results were obtained for the ResNet152 backbone. The mAP value was 85%, while the AP level ranged from 80% to 91%, depending on the item detected. An average real -time detection speed was between 11 and 13 FPS. Both the accuracy and speed of the model allow it to be recommended for use in public security monitoring systems aimed at detecting potentially dangerous objects.

PL

W badaniach, do wykrywania niebezpiecznych obiektów wykorzystano sieć Faster R -CNN z różnymi sieciami szkieletowymi. Naj lepsze wyniki uzyskano dla sieci szkieletowej ResNet152. Wartość mAP wyniosła 85%, natomiast poziom AP wahał się od 80% do 91%, w za leżności od wykrywanego obiektu. Średnia prędkość wykrywania w czasie rzeczywistym wynosiła od 11 do 13 FPS. Zarówno dokładność, jak i szybkość modelu pozwalają rekomendować go do wykorzystania w systemach monitorowania bezpieczeństwa publicznego, mających na celu wykrywanie potencjalnie niebezpiecznych obiektów.

11

Automatyczne rozpoznawanie powalonych drzew na drogach

Balcerek Julian, Pawłowski Paweł, Stankiewicz Tymon, Vykysaly Eryk

Przegląd Elektrotechniczny

|

2025

|

R. 101, nr 11

153--159

PL

W niniejszym artykule zaprezentowano system do automatycznego rozpoznawania powalonych drzew na drogach z perspektywy pojazdu. System dokonuje analizy obrazów za pomocą sztucznych sieci neuronowych. Do przeprowadzenia testów skuteczności rozpoznawania przygotowano bazę obrazów, z uwzględnieniem przyjętych kryteriów doboru, klatek referencyjnych, różnych rodzajów anotacji i augmentacji danych. Dla sieci wytrenowanych na większych obszarach zaznaczeń obiektów osiągnięto ponad 90-procentową dokładność rozpoznawania.

EN

This article presents a system for automatic recognition of fallen trees on roads from a vehicle perspective. The system uses artificial neural networks for image analysis. A database of images was prepared to carry out the recognition tests, taking into account the adopted selection criteria, reference frames, various types of data annotation and augmentation. For networks trained on larger areas of object selection, over 90% recognition accuracy was achieved.

12

Basketball Player Target Trackingbased on Improved YOLOv5 and Multi Feature Fusion

Sun Jinjun, Liu Ronghua

Machine Graphics and Vision

|

2025

|

Vol. 34, No. 1

3--24

EN

Multi-target tracking has important applications in many fields including logistics and transportation, security systems and assisted driving. With the development of science and technology, multi-target tracking has also become a research hotspot in the field of sports. In this study, a multi-attention module is added to compute the target feature information of different dimensions for the leakage problem of the traditional fifth-generation single-view detection algorithm. The study adopts two-stage target detection method to speed up the detection rate, and at the same time, recursive filtering is utilized to predict the position of the athlete in the next frame of the video. The results indicated that the improved fifth generation monovision detection algorithm possessed better results for target tracking of basketball players. The running time was reduced by 21.26% compared with the traditional fifth-generation monovision detection algorithm, and the average number of images that could be processed per second was 49. The accuracy rate was as high as 98.65%, and the average homing rate was 97.21%.During the tracking process of 60 frames of basketball sports video, the computational delay was always maintained within 40 ms. It can be demonstrated that by deeply optimizing the detection algorithm, the ability to identify and locate basketball players can be significantly improved, which provides a solid data support for the analysis of players’ behaviors and tactical layout in basketball games.

13

Digiteye: a Transparent Soft Tactile Sensor for Robust Multi-Modal Perception

Bui Son Tien, Le Duy Ngoc, Nguyen Tu Ahn, Nguyen Son Hong, Tran Son Ahn, Tran Luc Phi, Pham Thong Huy

Journal of Machine Engineering

|

2025

|

Vol. 25, No. 4

91--105

EN

Tactile sensing remains fundamental for enabling dexterous robotic manipulation and safe human–robot interaction. Existing visuotactile sensors often compromise either deformation depth or optical transparency, limiting their ability to capture both contact forces and external scene information. This paper presents DigitEye, a transparent soft tactile sensor with a hollow box-shaped silicone rubber skin that deforms at the centimeter scale while preserving high optical clarity. A one-shot molding process with inner-frame grooves ensures robust adhesion and modular replacement of the soft skin, while dark-blue markers embedded through CNC-machined molds enable reliable tracking under varied conditions. To validate the design, we constructed two benchmark datasets: a force-sensing dataset linking images to indentation depth and ground-truth force, and an object detection dataset of fruits under varying distances and lighting. Experimental evaluations demonstrate reliable force estimation across multiple contact geometries, together with YOLO-based recognition, achieving a precision of 0.95, a recall of 0.87, and an mAP@0.5 of 0.689. These results highlight DigitEye as a practical platform for transparent visuotactile sensing, supporting both fine-grained contact perception and safer robotic operation in unstructured environments.

14

Adaptive separation fusion: a novel downsampling approach in CNNS

Ji Xia, Chang Jinglong, Ji Yapeng

Journal of Artificial Intelligence and Soft Computing Research

|

2025

|

Vol. 15, No. 2

197--210

EN

Almost all computer vision tasks rely on convolutional neural networks and transformers, both of which require extensive computations. With the increasingly large size of images, it becomes challenging to input these images directly. Therefore, in typical cases, we downsample the images to a reasonable size before proceeding with subsequent tasks. However, the downsampling process inevitably discards some fine-grained information, leading to network performance degradation. Existing methods, such as strided convolution and various pooling techniques, struggle to address this issue effectively. To overcome this limitation, we propose a generalized downsampling module, Adaptive Separation Fusion Downsampling (ASFD). ASFD adaptively captures intra- and inter-region attentional relationships and preserves feature representations lost during downsampling through fusion. We validate ASFD on representative computer vision tasks, including object detection and image classification. Specifically, we incorporated ASFD into the YOLOv7 object detection model and several classification models. Experiments demonstrate that the modified YOLOv7 architecture surpasses state-of-the-art models in object detection, particularly excelling in small object detection. Additionally, our method outperforms commonly used downsampling techniques in classification tasks. Furthermore, ASFD functions as a plug-and-play module compatible with various network architectures.

15

Applying AI-assisted image processing to detect and measure CO2 microbubbles for carbon storage

Le Dang Nguyen Hai, Le Nam Nguyen Hai

Inżynieria Mineralna

|

2025

|

Vol. 2, no. 1

755--761

EN

To address the challenges in the CO2 injection process, CO2 microbubble dispersion has been proposed as an alternative to traditional methods, such as miscible injection and water-alternating-gas (WAG) injection. This study presents an AI-assisted model for detecting CO2 microbubbles, powered by the YOLOv8 algorithm, renowned for its high-accuracy predictions. Conventional image processing techniques often struggle with detecting microbubbles, particularly in cases involving overlapping bubbles, variations in size, and low-contrast images, which can lead to inaccuracies in bubble identification and measurement. In contrast, YOLOv8’s advanced detection capabilities offer a more robust solution by precisely localizing and classifying microbubbles, even in challenging scenarios. The model’s performance was rigorously evaluated, demonstrating its effectiveness as a valuable tool for microbubble analysis. The detection images processed using YOLOv8 illustrate its ability to accurately detect and classify bubbles of varying sizes, generating precise bounding boxes around each identified bubble. This combination of data visualization and advanced detection techniques underscores the efficacy of YOLOv8 in microbubble analysis, enabling accurate measurement and detailed characterization of bubble size distributions—an essential factor in optimizing chemical engineering processes.

16

Fine-grained detection and segmentation of civilian aircraft in satellite imagery using YOLOv8

Panneerselvam Ramesh Kumar, Bandi Sarada, Doddapaneni Sree Datta Siva Charan

Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska

|

2025

|

T. 15, nr 2

5--12

EN

Detectionand segmentation of civilian aircraft from satellite imagery has significant importance in applications for air traffic management, surveillance, and defense. Yet, its visual confusions and lack of unification in recognition make it hard. This paper presents that by developing an efficient YOLOv8-based model for aircraft detection, classification, and segmentation within the FAIR1M-2.0 dataset. This proposed methodology involves dataset preprocessing and compatibility adjustments where the backbone used is CSPDarknet53 combining with the C2f module, which provides an efficient multi-scale representation, this happens to be the most critical requirement in distinguishing between among 11 unique categories of aircraft. Including the SAM model helps improve localization precision by achieving more accurate pixel-level segmentation. The present work effectively carried out an accurateclassification and described civilian aircraft, containing the enhanced detection and quantification capability appropriate for complex satellite-oriented aircraft analysis. These reasons make the work satisfy the fundamental requirement for very accurateidentification and evaluation of aerial images.The approach improves the accuracy and precision of aircraft classification over delicate satellite images, and thus is useful in operations for real-time surveillance and monitoring. Fine-grained classification and segmentation would then be able to effectively capture slight differences between aircraft types, which are now vital to the reliable management of airspaces. This work, therefore sets a good foundation for future development and advancement of high-resolution aerial analysis in diverse operational settings.

PL

Wykrywanie i segmentacja cywilnych samolotów na podstawie obrazów satelitarnych mają kluczowe znaczenie w zarządzaniu ruchem lotniczym, nadzorze oraz obronności. Ze względu na wizualne podobieństwa między różnymi typami samolotów oraz brak standaryzacji w rozpoznawaniu, jest to zadanie trudne. Niniejszy artykuł przedstawia efektywny model oparty na YOLOv8 do wykrywania, klasyfikacji i segmentacji samolotów w zbiorze danych FAIR1M-2.0. Zaproponowana metodologia obejmuje wstępne przetwarzanie danych i dostosowanie do zgodności, w którym wykorzystano CSPDarknet53 jako bazę, połączoną z modułem C2f, co zapewnia efektywną reprezentację wieloskalową–jest to kluczowy element przy rozróżnianiu 11 unikalnych kategorii samolotów. Włączenie modelu SAM poprawia precyzję lokalizacji, pozwalając na dokładniejszą segmentację na poziomie pikseli. Prezentowane badania pozwoliły na dokładną klasyfikację i opisanie cywilnych samolotów, zapewniając ulepszone możliwości wykrywania i analizowania obiektów na obrazach satelitarnych. Takie podejście znacznie zwiększa dokładność i precyzję klasyfikacji samolotów, co czyni je przydatnym w operacjach nadzoru i monitorowania w czasie rzeczywistym. Precyzyjna klasyfikacja i segmentacja umożliwia skuteczne rozróżnianie subtelnych różnic między typami samolotów, co jest istotne dla niezawodnego zarządzania przestrzenią powietrzną. Niniejsza praca stanowi solidną podstawę dlaprzyszłych badań nad analizą obrazów lotniczych w wysokiej rozdzielczości w różnych kontekstach operacyjnych.

17

Ore image target detection based on improved YOLOv5 network

Cai Gaipin, Luo Hui, Huang Jinruo, Yi Guotao

Gospodarka Surowcami Mineralnymi

|

2025

|

Vol. 41, iss. 2

177--196

EN

The existing target detection algorithms detect the ore on the conveyor belt after the crushing process with low precision and slow detection speed. This leads to challenges in achieving a balance between precision and speed, to enhance the detection precision and speed of ore, and in view of the problems of leakage, misdetection, and insufficient feature extraction of YOLOv5 in the task of ore image detection; this study presents a target detection approach relying on the CA attention mechanism (Coordinate attention for efficient mobile network design), the SIoU loss function and the target detection algorithm YOLOv5 combination of ore image particle target detection method. Integrating the CA attention mechanism into the YOLOv5 backbone feature network enhances the feature learning and extraction of ore images, thereby improving the precision of the detection model; the SIoU loss function is refined to boost the recognition precision of the network on ore images and address the shortcomings of the original loss function that fails to take angular loss, distance loss, and shape loss into account, thereby further improving the precision and speed of ore image detection. The experimental findings demonstrate that the AP value, value, and precision rate are improved compared with the pre-improved algorithm. The CA-YOLOv5 method is verified to be fast, effective, and advanced and provides a foundation for real-time target detection of ores on conveyor belts in subsequent intelligent mine production.

PL

Istniejące algorytmy wykrywania celu wykrywają rudę na taśmie przenośnika po procesie kruszenia z niską precyzją i niską szybkością wykrywania. Prowadzi to do wyzwań związanych z osiągnięciem równowagi między precyzją i szybkością, w celu zwiększenia precyzji i szybkości wykrywania rudy, a także ze względu na problemy z wyciekami, błędnym wykrywaniem i niewystarczającą ekstrakcją cech YOLOv5 w zadaniu wykrywania obrazu rudy; niniejsze badanie przedstawia podejście do wykrywania celu polegające na mechanizmie uwagi CA (Coordinate attention for efficient mobile network design), funkcji straty SIoU i kombinacji algorytmu wykrywania celu YOLOv5 w połączeniu z metodą wykrywania celu cząstek obrazu rudy. Zintegrowanie mechanizmu uwagi CA z siecią funkcji szkieletowych YOLOv5 usprawnia uczenie się funkcji i ekstrakcję obrazów rudy, tym samym zwiększając precyzję modelu wykrywania; funkcja straty SIoU została udoskonalona w celu zwiększenia precyzji rozpoznawania sieci na obrazach rudy i usunięcia niedociągnięć oryginalnej funkcji straty, która nie uwzględnia strat kątowych, strat odległości i strat kształtu, co jeszcze bardziej poprawia precyzję i szybkość wykrywania obrazów rudy. Wyniki eksperymentów pokazują, że wartość AP, wartość i wskaźnik precyzji są lepsze w porównaniu z wcześniej ulepszonym algorytmem. Metoda CA-YOLOv5 została zweryfikowana jako szybka, skuteczna i zaawansowana oraz stanowi podstawę do wykrywania celów rud na taśmach przenośnikowych w czasie rzeczywistym w późniejszej inteligentnej produkcji kopalnianej.

18

Overlapping Box Suppression and Merging Algorithms for Window-Based Object Detection

Kos Aleksandra

Foundations of Computing and Decision Sciences

|

2025

|

Vol. 50, No. 3

403--23

EN

In this manuscript, we extend the Overlapping Box Suppression (OBS) algorithm, a novel approach designed to enhance window-based object detection systems by reducing false-positive detections. While window-based methods are commonly used for small object detection, they often face challenges due to partially visible objects and intersecting detection windows. To address this, the proposed OBS algorithm uses the detection window coordinates to effectively filter out redundant partial detections, improving detection quality. Additionally, we introduce a novel Overlapping Box Merging (OBM) algorithm, which further refines detection results by combining partial detections into a single, more accurate detection. Together, OBS and OBM offer a robust solution for handling overlapping and fragmented detections. We evaluate this combined global filtering block on sequences from the SeaDronesSee dataset, demonstrating superior performance across multiple object detection metrics compared to traditional NMS-based filtering methods.

19

Czujniki pojemnościowe nowej generacji

Dozór Techniczny

|

2025

|

z. 4

28--28

PL

Czujniki pojemnościowe Turck serii BC/UC w stopniu ochrony IP67 łączą w sobie konwencjonalną pracę z cyfrową inteligencją i dodatkowymi danymi do monitorowania stanu.

20

Hybrydowy klasyfikator treści CSAM w materiale fotograficznym

Stefańczyk Maciej, Dudek Wojciech

Cybersecurity and Law

|

2025

|

Vol. 13 (1) - numer specjalny

87--94

PL

Poczucie anonimowości, połączone z łatwością publikowania treści w internecie, sprzyja pojawianiu się w sieci coraz większej ilości materiałów nielegalnych. Jedną z kategorii takich treści są materiały przedstawiające wykorzystywanie seksualne dzieci (Child Sexual Abuse Material – CSAM), treści erotyczne z ich udziałem czy też w ich obecności. Obecnie możliwości reakcji na tego typu treści (m.in. blokowanie domen) mają pojedyncze ośrodki na poziomie krajowym. Ze względu na charakter przeglądanych treści zadanie to jest bardzo obciążające psychicznie, a każda metoda prowadząca do zmniejszenia ekspozycji pracowników na tego typu obrazy jest na wagę złota. Z tego względu narodziła się idea projektu APAKT2 (Automatyczne Przeszukiwanie, Analiza i Klasyfikacja Treści), który w sposób automatyczny analizuje przekazane dane i priorytetyzuje je tak, aby analityk możliwie szybko mógł ocenić, czy dana domena powinna zostać zablokowana czy nie. W niniejszym artykule przedstawione zostały prace (i związane z nimi specyficzne trudności) nad stworzenie klasyfikatora treści w materiale fotograficznym. W ich wyniku powstał hybrydowy klasyfikator, łączący współczesne osiągnięcia z dziedziny sztucznej inteligencji w rozpoznawaniu obrazów z klasycznymi metodami wspomagania decyzji.

EN

A sense of anonymity, combined with the ease of publishing content on the Internet, has fostered the appearance of an increasing amount of illegal material online. One category of such content is Child Sexual Abuse Material (CSAM), erotic content with or in the presence of children. Currently, the ability to respond to this type of content (including domain blocking) is available to individual units at the national level. Due to the nature of the content, this task is mentally taxing, and any method leading to a reduction in employees' exposure to such images is at a premium. For this reason, the idea of the APAKT (Automated Content Search, Analysis and Classification) project was born, which automatically analyzes the submitted data and prioritizes it so that the analyst can assess as quickly as possible whether a domain should be blocked or not. This article presents the work (and related specific difficulties) on the creation of a content classifier in photographic material. As a result, a hybrid classifier was created, combining modern developments in artificial intelligence in image recognition with classical decision support methods.