Saved Queries

Accurate identification of picking points remains a critical challenge for automated marigold harvesting, primarily due to complex backgrounds and significant pose variations of the flowers. To overcome this challenge, this study proposes SCS-YOLO-Seg, a novel method based on a lightweight segmentation model. The approach enhances the baseline YOLOv8n-seg architecture by replacing its backbone with StarNet and introducing C2f-Star, a novel lightweight feature extraction module. These modifications achieve substantial model compression, significantly reducing the model size, parameter count, and computational complexity (GFLOPs). Segmentation efficiency is further optimized through a dual-path collaborative architecture (Seg-Marigold head). Following mask extraction, picking points are determined by intersecting the optimized elliptical mask fitting results with the stem skeleton. Experimental results demonstrate that SCS-YOLO-Seg effectively balances model compression with segmentation performance. Compared to YOLOv8n-seg, it maintains high accuracy while significantly reducing resource requirements, achieving a picking point identification accuracy of 93.36% with an average inference time of 28.66 ms per image. This work provides a robust and efficient solution for vision systems in automated marigold harvesting. Full article

(This article belongs to the Section Smart Agriculture)

►▼ Show Figures

Figure 1

18 pages, 2879 KiB

Open AccessArticle

Smartphone-Compatible Colorimetric Detection of CA19-9 Using Melanin Nanoparticles and Deep Learning

by Turgut Karademir, Gizem Kaleli-Can and Başak Esin Köktürk-Güzel

Biosensors 2025, 15(8), 507; https://doi.org/10.3390/bios15080507 (registering DOI) - 5 Aug 2025

Abstract

Paper-based colorimetric biosensors represent a promising class of low-cost diagnostic tools that do not require external instrumentation. However, their broader applicability is limited by the environmental concerns associated with conventional metal-based nanomaterials and the subjectivity of visual interpretation. To address these challenges, this study introduces a proof-of-concept platform—using CA19-9 as a model biomarker—that integrates naturally derived melanin nanoparticles (MNPs) with machine learning-based image analysis to enable environmentally sustainable and analytically robust colorimetric quantification. Upon target binding, MNPs induce a concentration-dependent color transition from yellow to brown. This visual signal was quantified using a machine learning pipeline incorporating automated region segmentation and regression modeling. Sensor areas were segmented using three different algorithms, with the U-Net model achieving the highest accuracy (average IoU: 0.9025 ± 0.0392). Features extracted from segmented regions were used to train seven regression models, among which XGBoost performed best, yielding a Mean Absolute Percentage Error (MAPE) of 17%. Although reduced sensitivity was observed at higher analyte concentrations due to sensor saturation, the model showed strong predictive accuracy at lower concentrations, which are especially challenging for visual interpretation. This approach enables accurate, reproducible, and objective quantification of colorimetric signals, thereby offering a sustainable and scalable alternative for point-of-care diagnostic applications. Full article

(This article belongs to the Special Issue AI-Enabled Biosensor Technologies for Boosting Medical Applications)

►▼ Show Figures

Figure 1

23 pages, 2640 KiB

Open AccessArticle

DenseNet-Based Classification of EEG Abnormalities Using Spectrograms

by Lan Wei and Catherine Mooney

Algorithms 2025, 18(8), 486; https://doi.org/10.3390/a18080486 - 5 Aug 2025

Abstract

Electroencephalogram (EEG) analysis is essential for diagnosing neurological disorders but typically requires expert interpretation and significant time. Purpose: This study aims to automate the classification of normal and abnormal EEG recordings to support clinical diagnosis and reduce manual workload. Automating the initial screening of EEGs can help clinicians quickly identify potential neurological abnormalities, enabling timely intervention and guiding further diagnostic and treatment strategies. Methodology: We utilized the Temple University Hospital EEG dataset to develop a DenseNet-based deep learning model. To enable a fair comparison of different EEG representations, we used three input types: signal images, spectrograms, and scalograms. To reduce dimensionality and simplify computation, we focused on two channels: T5 and O1. For interpretability, we applied Local Interpretable Model-agnostic Explanations (LIME) and Gradient-weighted Class Activation Mapping (Grad-CAM) to visualize the EEG regions influencing the model’s predictions. Key Findings: Among the input types, spectrogram-based representations achieved the highest classification accuracy, indicating that time-frequency features are especially effective for this task. The model demonstrated strong performance overall, and the integration of LIME and Grad-CAM provided transparent explanations of its decisions, enhancing interpretability. This approach offers a practical and interpretable solution for automated EEG screening, contributing to more efficient clinical workflows and better understanding of complex neurological conditions. Full article

(This article belongs to the Special Issue AI-Assisted Medical Diagnostics)

►▼ Show Figures

Figure 1

28 pages, 2057 KiB

Open AccessArticle

Design and Fabrication of a Cost-Effective, Remote-Controlled, Variable-Rate Sprayer Mounted on an Autonomous Tractor, Specifically Integrating Multiple Advanced Technologies for Application in Sugarcane Fields

by Pongpith Tuenpusa, Kiattisak Sangpradit, Mano Suwannakam, Jaturong Langkapin, Alongklod Tanomtong and Grianggai Samseemoung

AgriEngineering 2025, 7(8), 249; https://doi.org/10.3390/agriengineering7080249 - 5 Aug 2025

Abstract

The integration of a real-time image processing system using multiple webcams with a variable rate spraying system mounted on the back of an unmanned tractor presents an effective solution to the labor shortage in agriculture. This research aims to design and fabricate a low-cost, variable-rate, remote-controlled sprayer specifically for use in sugarcane fields. The primary method involves the modification of a 15-horsepower tractor, which will be equipped with a remote-control system to manage both the driving and steering functions. A foldable remote-controlled spraying arm is installed at the rear of the unmanned tractor. The system operates by using a webcam mounted on the spraying arm to capture high-angle images above the sugarcane canopy. These images are recorded and processed, and the data is relayed to the spraying control system. As a result, chemicals can be sprayed on the sugarcane accurately and efficiently based on the insights gained from image processing. Tests were conducted at various nozzle heights of 0.25 m, 0.5 m, and 0.75 m. The average system efficiency was found to be 85.30% at a pressure of 1 bar, with a chemical spraying rate of 36 L per hour and a working capacity of 0.975 hectares per hour. The energy consumption recorded was 0.161 kWh, while fuel consumption was measured at 6.807 L per hour. In conclusion, the development of the remote-controlled variable rate sprayer mounted on an unmanned tractor enables immediate and precise chemical application through remote control. This results in high-precision spraying and uniform distribution, ultimately leading to cost savings, particularly by allowing for adjustments in nozzle height from a minimum of 0.25 m to a maximum of 0.75 m from the target. Full article

(This article belongs to the Special Issue Implementation of Artificial Intelligence in Agriculture)

15 pages, 4422 KiB

Open AccessArticle

Advanced Deep Learning Methods to Generate and Discriminate Fake Images of Egyptian Monuments

by Daniyah Alaswad and Mohamed A. Zohdy

Appl. Sci. 2025, 15(15), 8670; https://doi.org/10.3390/app15158670 (registering DOI) - 5 Aug 2025

Abstract

Artificial intelligence technologies, particularly machine learning and computer vision, are being increasingly utilized to preserve, restore, and create immersive virtual experiences with cultural artifacts and sites, thus aiding in conserving cultural heritage and making it accessible to a global audience. This paper examines the performance of Generative Adversarial Networks (GAN), especially Style-Based Generator Architecture (StyleGAN), as a deep learning approach for producing realistic images of Egyptian monuments. We used Sigmoid loss for Language–Image Pre-training (SigLIP) as a unique image–text alignment system to guide monument generation through semantic elements. We also studied truncation methods to regulate the generated image noise and identify the most effective parameter settings based on architectural representation versus diverse output creation. An improved discriminator design that combined noise addition with squeeze-and-excitation blocks and a modified MinibatchStdLayer produced 27.5% better Fréchet Inception Distance performance than the original discriminator models. Moreover, differential evolution for latent-space optimization reduced alignment mistakes during specific monument construction tasks by about 15%. We checked a wide range of truncation values from 0.1 to 1.0 and found that somewhere between 0.4 and 0.7 was the best range because it allowed for good accuracy while retaining many different architectural elements. Our findings indicate that specific model optimization strategies produce superior outcomes by creating better-quality and historically correct representations of diverse Egyptian monuments. Thus, the developed technology may be instrumental in generating educational and archaeological visualization assets while adding virtual tourism capabilities. Full article

(This article belongs to the Special Issue Novel Applications of Machine Learning and Bayesian Optimization)

►▼ Show Figures

Figure 1

27 pages, 37457 KiB

Open AccessArticle

Multi-Sensor Flood Mapping in Urban and Agricultural Landscapes of the Netherlands Using SAR and Optical Data with Random Forest Classifier

by Omer Gokberk Narin, Aliihsan Sekertekin, Caglar Bayik, Filiz Bektas Balcik, Mahmut Arıkan, Fusun Balik Sanli and Saygin Abdikan

Remote Sens. 2025, 17(15), 2712; https://doi.org/10.3390/rs17152712 - 5 Aug 2025

Abstract

Floods stand as one of the most harmful natural disasters, which have become more dangerous because of climate change effects on urban structures and agricultural fields. This research presents a comprehensive flood mapping approach that combines multi-sensor satellite data with a machine learning method to evaluate the July 2021 flood in the Netherlands. The research developed 25 different feature scenarios through the combination of Sentinel-1, Landsat-8, and Radarsat-2 imagery data by using backscattering coefficients together with optical Normalized Difference Water Index (NDWI) and Hue, Saturation, and Value (HSV) images and Synthetic Aperture Radar (SAR)-derived Grey Level Co-occurrence Matrix (GLCM) texture features. The Random Forest (RF) classifier was optimized before its application based on two different flood-prone regions, which included Zutphen’s urban area and Heijen’s agricultural land. Results demonstrated that the multi-sensor fusion scenarios (S18, S20, and S25) achieved the highest classification performance, with overall accuracy reaching 96.4% (Kappa = 0.906–0.949) in Zutphen and 87.5% (Kappa = 0.754–0.833) in Heijen. For the flood class F1 scores of all scenarios, they varied from 0.742 to 0.969 in Zutphen and from 0.626 to 0.969 in Heijen. Eventually, the addition of SAR texture metrics enhanced flood boundary identification throughout both urban and agricultural settings. Radarsat-2 provided limited benefits to the overall results, since Sentinel-1 and Landsat-8 data proved more effective despite being freely available. This study demonstrates that using SAR and optical features together with texture information creates a powerful and expandable flood mapping system, and RF classification performs well in diverse landscape settings. Full article

(This article belongs to the Special Issue Remote Sensing Applications in Flood Forecasting and Monitoring)

24 pages, 4967 KiB

Open AccessArticle

CatBoost-Optimized Hyperspectral Modeling for Accurate Prediction of Wood Dyeing Formulations

by Xuemei Guan, Rongkai Xue, Zhongsheng He, Shibin Chen and Xiangya Chen

Forests 2025, 16(8), 1279; https://doi.org/10.3390/f16081279 - 5 Aug 2025

Abstract

This study proposes a CatBoost-enhanced hyperspectral modeling approach for accurate prediction of wood dyeing formulations. Using Pinus sylvestris var. mongolica veneer as the substrate, 306 samples with gradient dye concentrations were prepared, and their reflectance spectra (400–700 nm) were acquired. After noise reduction and sensitive band selection (400–450 nm, 550–600 nm, and 600–650 nm), spectral descriptors were extracted as model inputs. The CatBoost algorithm, optimized via k-fold cross-validation and grid search, outperformed XGBoost, random forest, and SVR in prediction accuracy, achieving MSE = 0.00271 and MAE = 0.0349. Scanning electron microscopy (SEM) revealed the correlation between dye particle distribution and spectral response, validating the model’s physical basis. This approach enables intelligent dye formulation control in industrial wood processing, reducing color deviation (ΔE < 1.75) and dye waste by approximately 25%. Full article

(This article belongs to the Section Wood Science and Forest Products)

►▼ Show Figures

Figure 1

18 pages, 2839 KiB

Open AccessArticle

Detection of Maize Pathogenic Fungal Spores Based on Deep Learning

by Yijie Ren, Ying Xu, Huilin Tian, Qian Zhang, Mingxiu Yang, Rongsheng Zhu, Dawei Xin, Qingshan Chen, Qiaorong Wei and Shuang Song

Agriculture 2025, 15(15), 1689; https://doi.org/10.3390/agriculture15151689 - 5 Aug 2025

Abstract

Timely detection of pathogen spores is fundamental to ensuring early intervention and reducing the spread of corn diseases, like northern corn leaf blight, corn head smut, and corn rust. Traditional spore detection methods struggle to identify spore-level targets within complex backgrounds. To improve the recognition accuracy of various maize disease spores, this study introduced the YOLOv8s-SPM model by incorporating the space-to-depth and convolution (SPD-Conv) layers, the Partial Self-Attention (PSA) mechanism, and Minimum Point Distance Intersection over Union (MPDIoU) loss function. First, we combined SPD-Conv layers into the Backbone of the YOLOv8s to enhance recognition performance on small targets and low-resolution images. To improve computational efficiency, the PSA mechanism was incorporated within the Neck layer of the network. Finally, MPDIoU loss function was applied to refine the localization performance of bounding boxes. The results revealed that the YOLOv8s-SPM model achieved 98.9% accuracy on the mixed spore dataset. Relative to the baseline YOLOv8s, the YOLOv8s-SPM model yielded a 1.4% gain in accuracy. The improved model significantly improved spore detection accuracy and demonstrated superior performance in recognizing diverse spore types under complex background conditions. It met the demands for high-precision spore detection and filled a gap in intelligent spore recognition for maize, offering an effective starting point and practical path for future research in this field. Full article

(This article belongs to the Section Crop Protection, Diseases, Pests and Weeds)

►▼ Show Figures

Figure 1

17 pages, 2283 KiB

Open AccessArticle

A Remote Strawberry Health Monitoring System Performed with Multiple Sensors Approach

by Xiao Du, Jun Steed Huang, Qian Shi, Tongge Li, Yanfei Wang, Haodong Liu, Zhaoyuan Zhang, Ni Yu and Ning Yang

Agriculture 2025, 15(15), 1690; https://doi.org/10.3390/agriculture15151690 - 5 Aug 2025

Abstract

Temperature is a key physiological indicator of plant health, influenced by factors including water status, disease and developmental stage. Monitoring changes in multiple factors is helpful for early diagnosis of plant growth. However, there are a variety of complex light interference phenomena in the greenhouse, so traditional detection methods cannot meet effective online monitoring of strawberry health status without manual intervention. Therefore, this paper proposes a leaf soft-sensing method based on a thermal infrared imaging sensor and adaptive image screening Internet of Things system, with additional sensors to realize indirect and rapid monitoring of the health status of a large range of strawberries. Firstly, a fuzzy comprehensive evaluation model is established by analyzing the environmental interference terms from the other sensors. Secondly, through the relationship between plant physiological metabolism and canopy temperature, a growth model is established to predict the growth period of strawberries based on canopy temperature. Finally, by deploying environmental sensors and solar height sensors, the image acquisition node is activated when the environmental interference is less than the specified value and the acquisition is completed. The results showed that the accuracy of this multiple sensors system was 86.9%, which is 30% higher than the traditional model and 4.28% higher than the latest advanced model. It makes it possible to quickly and accurately assess the health status of plants by a single factor without in-person manual intervention, and provides an important indication of the early, undetectable state of strawberry disease, based on remote operation. Full article

(This article belongs to the Section Artificial Intelligence and Digital Agriculture)

►▼ Show Figures

Figure 1

27 pages, 11710 KiB

Open AccessArticle

Assessing ResNeXt and RegNet Models for Diabetic Retinopathy Classification: A Comprehensive Comparative Study

by Samara Acosta-Jiménez, Valeria Maeda-Gutiérrez, Carlos E. Galván-Tejada, Miguel M. Mendoza-Mendoza, Luis C. Reveles-Gómez, José M. Celaya-Padilla, Jorge I. Galván-Tejada and Antonio García-Domínguez

Diagnostics 2025, 15(15), 1966; https://doi.org/10.3390/diagnostics15151966 - 5 Aug 2025

Abstract

Background/Objectives: Diabetic retinopathy is a leading cause of vision impairment worldwide, and the development of reliable automated classification systems is crucial for early diagnosis and clinical decision-making. This study presents a comprehensive comparative evaluation of two state-of-the-art deep learning families for the task of classifying diabetic retinopathy using retinal fundus images. Methods: The models were trained and tested in both binary and multi-class settings. The experimental design involved partitioning the data into training (70%), validation (20%), and testing (10%) sets. Model performance was assessed using standard metrics, including precision, sensitivity, specificity, F1-score, and the area under the receiver operating characteristic curve. Results: In binary classification, the ResNeXt101-64x4d model and RegNetY32GT model demonstrated outstanding performance, each achieving high sensitivity and precision. For multi-class classification, ResNeXt101-32x8d exhibited strong performance in early stages, while RegNetY16GT showed better balance across all stages, particularly in advanced diabetic retinopathy cases. To enhance transparency, SHapley Additive exPlanations were employed to visualize the pixel-level contributions for each model’s predictions. Conclusions: The findings suggest that while ResNeXt models are effective in detecting early signs, RegNet models offer more consistent performance in distinguishing between multiple stages of diabetic retinopathy severity. This dual approach combining quantitative evaluation and model interpretability supports the development of more robust and clinically trustworthy decision support systems for diabetic retinopathy screening. Full article

(This article belongs to the Special Issue Artificial Intelligence and Deep Learning in Clinical Classification and Prediction)

►▼ Show Figures

Figure 1

17 pages, 4105 KiB

Open AccessArticle

Evaluation of the Effect of X-Ray Therapy on Glioma Rat Model Using Chemical Exchange Saturation Transfer and Diffusion-Weighted Imaging

by Kazuki Onishi, Koji Itagaki, Sachie Kusaka, Tensei Nakano, Junpei Ueda and Shigeyoshi Saito

Cancers 2025, 17(15), 2578; https://doi.org/10.3390/cancers17152578 - 5 Aug 2025

Abstract

Background/Objectives: This study aimed to examine the changes in brain metabolites and water molecule diffusion using chemical exchange saturation transfer (CEST) imaging and diffusion-weighted imaging (DWI) after 15 Gy of X-ray irradiation in a rat model of glioma. Methods: The glioma-derived cell line, C6, was implanted into the striatum of the right brain of 7-week-old male Wistar rats. CEST imaging and DWI were performed on days 8, 10, and 17 after implantation using a 7T-magnetic resonance imaging. X-ray irradiation (15 Gy) was performed on day 9. Magnetization transfer ratio (MTR) and apparent diffusion coefficient (ADC) values were calculated for CEST and DWI, respectively. Results: On day 17, the MTR values at 1.2 ppm, 1.5 ppm, 1.8 ppm, 2.1 ppm, and 2.4 ppm in the irradiated group decreased significantly compared with those of the control group. The standard deviation for the ADC values on a pixel-by-pixel basis increased from day 8 to day 17 (0.6 ± 0.06 → 0.8 ± 0.17 (×10⁻³ mm²/s)) in the control group, whereas it remained nearly unchanged (0.6 ± 0.06 → 0.8 ± 0.11 (×10⁻³ mm²/s)) in the irradiated group. Conclusions: This study revealed the effects of 15 Gy X-ray irradiation in a rat model of glioma using CEST imaging and DWI. Full article

(This article belongs to the Special Issue Intraoperative Visualization Techniques and Advanced Imaging in Brain Tumors)

►▼ Show Figures

Figure 1

32 pages, 22267 KiB

Open AccessArticle

HAF-YOLO: Dynamic Feature Aggregation Network for Object Detection in Remote-Sensing Images

by Pengfei Zhang, Jian Liu, Jianqiang Zhang, Yiping Liu and Jiahao Shi

Remote Sens. 2025, 17(15), 2708; https://doi.org/10.3390/rs17152708 - 5 Aug 2025

Abstract

The growing use of remote-sensing technologies has placed greater demands on object-detection algorithms, which still face challenges. This study proposes a hierarchical adaptive feature aggregation network (HAF-YOLO) to improve detection precision in remote-sensing images. It addresses issues such as small object size, complex backgrounds, scale variation, and dense object distributions by incorporating three core modules: dynamic-cooperative multimodal fusion architecture (DyCoMF-Arch), multiscale wavelet-enhanced aggregation network (MWA-Net), and spatial-deformable dynamic enhancement module (SDDE-Module). DyCoMF-Arch builds a hierarchical feature pyramid using multistage spatial compression and expansion, with dynamic weight allocation to extract salient features. MWA-Net applies wavelet-transform-based convolution to decompose features, preserving high-frequency detail and enhancing representation of small-scale objects. SDDE-Module integrates spatial coordinate encoding and multidirectional convolution to reduce localization interference and overcome fixed sampling limitations for geometric deformations. Experiments on the NWPU VHR-10 and DIOR datasets show that HAF-YOLO achieved mAP50 scores of 85.0% and 78.1%, improving on YOLOv8 by 4.8% and 3.1%, respectively. HAF-YOLO also maintained a low computational cost of 11.8 GFLOPs, outperforming other YOLO models. Ablation studies validated the effectiveness of each module and their combined optimization. This study presents a novel approach for remote-sensing object detection, with theoretical and practical value. Full article

(This article belongs to the Special Issue New Insights in Remote Sensing Image Interpretation with Deep Learning)

►▼ Show Figures

Figure 1

19 pages, 1495 KiB

Open AccessReview

Computer Vision for Low-Level Nuclear Waste Sorting: A Review

by Tianshuo Li, Danielle E. Winckler and Zhong Li

Environments 2025, 12(8), 270; https://doi.org/10.3390/environments12080270 - 5 Aug 2025

Abstract

Nuclear power is a low-emission and economically competitive energy source, yet the effective disposal and management of its associated radioactive waste can be challenging. Radioactive waste can be categorised as high-level waste (HLW), intermediate-level waste (ILW), and low-level waste (LLW). LLW primarily comprises materials contaminated during routine clean-up, such as mop heads, paper towels, and floor sweepings. While LLW is less radioactive compared to HLW and ILW, the management of LLW poses significant challenges due to the large volume that requires processing and disposal. The volume of LLW can be significantly reduced through sorting, which is typically performed manually in a labour-intensive way. Smart management techniques, such as computer vision (CV) and machine learning (ML), have great potential to help reduce the workload and human errors during LLW sorting. This paper provides a comprehensive review of previous research related to LLW sorting and a summative review of existing applications of CV in solid waste management. It also discusses state-of-the-art CV and ML algorithms and their potential for automating LLW sorting. This review lays a foundation for and helps facilitate the applications of CV and ML techniques in LLW sorting, paving the way for automated LLW sorting and sustainable LLW management. Full article

►▼ Show Figures

Figure 1

31 pages, 1811 KiB

Open AccessArticle

Fractal-Inspired Region-Weighted Optimization and Enhanced MobileNet for Medical Image Classification

by Yichuan Shao, Jiapeng Yang, Wen Zhou, Haijing Sun and Qian Gao

Fractal Fract. 2025, 9(8), 511; https://doi.org/10.3390/fractalfract9080511 - 5 Aug 2025

Abstract

In the field of deep learning, the design of optimization algorithms and neural network structures is crucial for improving model performance. Recent advances in medical image analysis have revealed that many pathological features exhibit fractal-like characteristics in their spatial distribution and morphological patterns. This observation has opened new possibilities for developing fractal-inspired deep learning approaches. In this study, we propose the following: (1) a novel Region-Module Adam (RMA) optimizer that incorporates fractal-inspired region-weighting to prioritize areas with higher fractal dimensionality, and (2) an ECA-Enhanced Shuffle MobileNet (ESM) architecture designed to capture multi-scale fractal patterns through its enhanced feature extraction modules. Our experiments demonstrate that this fractal-informed approach significantly improves classification accuracy compared to conventional methods. On gastrointestinal image datasets, the RMA algorithm achieved accuracies of 83.60%, 81.60%, and 87.30% with MobileNetV2, ShuffleNetV2, and ESM networks, respectively. For glaucoma fundus images, the corresponding accuracies reached 84.90%, 83.60%, and 92.73%. These results suggest that explicitly considering fractal properties in medical image analysis can lead to more effective diagnostic tools. Full article

(This article belongs to the Special Issue Fractal and Multifractal Analysis in Environmental, Medical and Technical Fields: Pattern Recognition, Analysis and Processing of Images)

33 pages, 4254 KiB

Open AccessArticle

A Method of Simplified Synthetic Objects Creation for Detection of Underwater Objects from Remote Sensing Data Using YOLO Networks

by Daniel Klukowski, Jacek Lubczonek and Pawel Adamski

Remote Sens. 2025, 17(15), 2707; https://doi.org/10.3390/rs17152707 - 5 Aug 2025

Abstract

The number of CNN application areas is growing, which leads to the need for training data. The research conducted in this work aimed to obtain effective detection models trained only using simplified synthetic objects (SSOs). The research was conducted on inland shallow water areas, while images of bottom objects were obtained using a UAV platform. The work consisted in preparing SSOs, thanks to which composite images were created. On such training data, 120 models based on the YOLO (You Only Look Once) network were obtained. The study confirmed the effectiveness of models created using YOLOv3, YOLOv5, YOLOv8, YOLOv9, and YOLOv10. A comparison was made between versions of YOLO. The influence of the amount of training data, SSO type, and augmentation parameters used in the training process was analyzed. The main parameter of model performance was the F1-score. The calculated statistics of individual models indicate that the most effective networks use partial augmentation, trained on sets consisting of 2000 SSOs. On the other hand, the increased transparency of SSOs resulted in increasing the diversity of training data and improving the performance of models. This research is developmental, and further research should improve the processes of obtaining detection models using deep networks. Full article

(This article belongs to the Special Issue Coastal Environment Monitoring Based on Remote Sensing and Artificial Intelligence)

►▼ Show Figures

Figure 1

Show export options Show export options

Select all

Export citation of selected articles as:

Error

Oops... you haven't selected anything for export.

Displaying article 1-50 on page 1 of 2000.

Go to page 1 2 3 4 5

Search Results (119,623)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI