Many previous studies have explored the integration of a specific You Only Look Once (YOLO) model with real-time trackers like Deep Simple Online and Realtime Tracker (DeepSORT) and Strong Simple Online and Realtime Tracker (StrongSORT). However, few have conducted a comprehensive and in-depth analysis of integrating the family of YOLO models with these real-time trackers to study the performance of the resulting pipeline and draw critical conclusions. This work aims to fill this gap, with the primary objective of investigating the effectiveness of integrating the YOLO series, in light-sized versions, with the real-time DeepSORT and StrongSORT tracking algorithms for real-time object tracking in a computationally limited environment. This work will systematically compare various lightweight YOLO versions, from YOLO version 3 (YOLOv3) to YOLO version 10 (YOLOv10), combined with both tracking algorithms. It will evaluate their performance using detailed metrics across diverse and challenging real-world datasets: the Multiple Object Tracking 2017 (MOT17) and Multiple Object Tracking 2020 (MOT20) datasets. The goal of this work is to assess the robustness and accuracy of these light models in multiple complex real-world environments in scenarios with limited computational resources. Our findings reveal that YOLO version 5 (YOLOv5), when combined with either tracker (DeepSORT or StrongSORT), offers not only a solid baseline in terms of the model’s size (enabling real-time performance on edge devices) but also competitive overall performance (in terms of Multiple Object Tracking Accuracy (MOTA) and Multiple Object Tracking Precision (MOTP)). The results suggest a strong correlation between the choice regarding the YOLO version and the tracker’s overall performance.

Camera and LiDAR data fusion has been a popular research area, especially in the field of autonomous vehicles. This study evaluates the efficiency and accuracy of different depth point extraction methods, including Point-by-Point (PbyP), Complete Region Depth Extraction (CoRDE), Central Region Depth Extraction (CeRDE), and Grid Central Region Depth Extraction (GCRDE), across object categories such as person, bicycle, car, bus, and truck, and occlusion levels ranging from 0 to 3. The approaches are assessed based on extraction time, accuracy, and root mean squared error (RMSE). Bounding box-based methods, such as PbyP and CoRDE, consistently show slower extraction times compared to segmentation mask methods, with CeRDE being the most efficient in terms of computational speed. However, segmentation mask methods, particularly CeRDE and GCRDE, offer superior accuracy, especially for complex objects like trucks and cars, where bounding box methods struggle, particularly at higher occlusion levels. In terms of RMSE, segmentation mask methods consistently outperform bounding box methods, providing more precise depth estimations, particularly for larger and more occluded objects. Overall, segmentation mask methods are preferred for applications where accuracy is critical, despite their slower processing speed, while bounding box methods are suitable for real-time applications requiring faster depth extraction. GeRDE offers a balance between speed and accuracy, making it ideal for tasks needing both efficiency and precision.

Traffic sign recognition is critical for intelligent transportation systems and autonomous driving. Conventional convolutional neural networks (CNNs) typically utilize the ReLU activation function for its computational efficiency; however, alternative activation functions can improve computing effectiveness capacity in recognition tasks. In this study, we propose a CNNs model enhanced with the Gaussian Error Linear Unit (GELU) activation function. We evaluate its performance on benchmark datasets and compare it against both ReLU and Leaky ReLU baseline. Experimental results show that the proposed GELU-activated CNNs achieves a recognition accuracy of 99.75% and provides small but consistent improvements over ReLU and Leaky ReLU models, particularly under challenging conditions such as occlusion and low lighting. These findings highlight GELU’s potential to enhance the robustness and reliability of traffic sign recognition in Electric Vehicles for autonomous driving applications.

Multi object tracking (MOT) is a crucial task in video analysis but is often hindered by frequent identity (ID) switches, particularly in crowded or occluded scenarios. This study explores the integration of a vision-language model, into two tracking by detection frameworks DeepSORT and StrongSORT to enhance appearance-based re-identification. YOLOv8x is employed as the base detector due to its robust localization performance, while CLIP’s visual features replace the default appearance encoders, providing more discriminative and semantically rich embeddings. We evaluated the CLIP enhanced DeepSORT and StrongSORT on sequences from two challenging real world benchmarks: MOT15 and MOT16. Furthermore, we analyze the generalizability of YOLOv8x when trained on the MOT20 benchmark and applied to the chosen trackers on MOT15 and MOT16. Our findings show that both CLIP enhanced trackers substantially reduce ID switches and improve ID-based tracking metrics, with CLIP StrongSORT achieving the most consistent gains. In addition, YOLOv8x demonstrates strong generalization capabilities for unseen datasets. These results highlight the effectiveness of incorporating vision language models into MOT frameworks, particularly under visually challenging conditions.