Oct 2026· International Journal of Engineering and Manufacturing· 0 citations
TL;DR
A balanced augmented dataset combining two public repositories is constructed, yielding images across ten vehicle classes, and a convex ensemble of three selected models with optimized weights is developed to enhance robustness.
Abstract
The rapid growth of vehicles in Bangladesh has exacerbated traffic congestion, safety concerns, and administrative difficulties, creating an urgent need for Intelligent Transportation Systems (ITS). However, existing global datasets poorly represent Bangladeshi vehicles, and no region-specific detection models are currently available. To address this gap, this research constructs a balanced augmented dataset combining two public repositories, yielding images across ten vehicle classes. A harmonized dataset of manually verified images was split prior to augmentation, expanding the training set to 24,696 samples. Five deep Convolutional Neural Network architectures are then evaluated using transfer learning and extensive augmentation, and a convex ensemble of three selected models with optimized weights is developed to enhance robustness. The single ConvNeXt model achieves 98.980% ± 0.198% accuracy, while the ensemble attains 98.991% ± 0.156% accuracy. Statistical testing confirms the significance of these results; the ensemble effectively reduces misclassifications between visually similar categories. Overall, the proposed system provides a dependable platform for transportation applications in Bangladesh. Future work will address current limitations in static image and category scope through video-based analysis and lightweight deployment strategies.
This paper presents performance analysis of two deep learning architectures for object detection YOLOv2 and YOLOv4-Tiny aimed at identifying the model state for inspecting the braking systems of Series 441 and 444 locomotives. This models were trained and evaluated using a unified dataset comprising images of 3220 Brak...
Marko Perić, A. Miltenović, Emina Petrović et al.· Proceedings· 0 citations
Automatic classification of military aircraft in satellite imagery is a challenging problem with a high risk of error due to the limited pixel area of targets, variations in image resolution and illumination conditions, background complexity, and strong visual similarity among classes. In this study, a deep learning ap...
Unmanned aerial vehicle imagery provides a practical and high-resolution data source for monitoring the spatial condition of urban and peri-urban green zones. However, the reliable detection of damaged, stressed, or declining vegetation areas remains challenging because UAV images often contain complex background patte...
Nodir Rakhimov, Jura Kuvandikov, Maruf Tojiyev et al.· Frontiers in Artificial Inte...· 0 citations
This study presents a comparative and explainable deep learning framework for detecting vehicles and pedestrians in drone-based aerial imagery. The VisDrone dataset was used to address key challenges associated with aerial object detection, including small object size, varying camera angles, crowded scenes, and class i...
Z. Demir, Betul Zehra Celik, Ilkay Yelmen· 2026 11th International Conf...· 0 citations
Real-time automatic detection of fire and smoke is a critical component of modern safety systems in surveillance, industrial, and environmental-protection applications, where conventional sensor-based systems show fundamental limitations. In this paper, a comparative analysis of four deep-learning architectures—DETR, F...
Marko M. Živanović, Vanja Luković, Olga Ristić et al.· Symmetry· 0 citations
A rigorous comparative analysis of deep learning models, specifically U-Net, Mask R-CNN, and YOLOv8-Seg, for real-time traffic sign segmentation is presented, finding that YOLOv8-Seg achieves an optimal trade-off with a mean Average Precision.
Anaxon Muqimova· Techscience uz - Topical Iss...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.