This paper provides a comprehensive review of the evolution of the YOLO (You Only Look Once) object detection algorithm, focusing on YOLOv5, YOLOv8, and YOLOv10. These versions have been developed to improve performance, efficiency, and suitability for edge deployment. YOLOv5 introduced significant innovations such as the CSPDarknet backbone and Mosaic Augmentation, balancing speed and accuracy. YOLOv8 built upon this foundation with enhanced feature extraction and anchor-free detection, improving versatility and performance. YOLOv10 represents a leap forward with NMS-free training, spatial-channel decoupled downsampling, and large-kernel convolutions, achieving state-of-the-art performance with reduced computational overhead. The three variants stand out due to their optimal balance of speed, accuracy, and efficiency, making them especially suitable for resource-constrained environments. YOLOv5, introduced in 2020, marked a significant leap in performance and ease of use, establishing itself as a go-to solution for many edge computing applications. YOLOv8, released in 2023, built upon YOLOv5's success, offering improved accuracy and a unified framework for various computer vision tasks. YOLOv10, the latest iteration, pushes the boundaries further with innovative approaches to reduce computational overhead while maintaining high accuracy. These three YOLO variants have become prevalent in constrained edge deployment for several key reasons: optimized performance, scalability, ease of deployment, continuous improvement, and community support. YOLOv5 offers a range of model sizes (n, s, m, l, x) for different computational needs, while YOLOv8 provides a unified framework for various computer vision tasks. YOLOv10 introduces NMS-free training and other advanced techniques, making it particularly efficient for edge devices with limited computational resources. The paper highlights the key advancements of each version, compares their performance metrics, and discusses why they are particularly well-suited for edge deployment in various real-world applications. YOLOv5, YOLOv8, and YOLOv10 represent significant improvements in accuracy, efficiency, and real-time performance, making them leading choices for real-time object detection in edge computing scenarios.This paper provides a comprehensive review of the evolution of the YOLO (You Only Look Once) object detection algorithm, focusing on YOLOv5, YOLOv8, and YOLOv10. These versions have been developed to improve performance, efficiency, and suitability for edge deployment. YOLOv5 introduced significant innovations such as the CSPDarknet backbone and Mosaic Augmentation, balancing speed and accuracy. YOLOv8 built upon this foundation with enhanced feature extraction and anchor-free detection, improving versatility and performance. YOLOv10 represents a leap forward with NMS-free training, spatial-channel decoupled downsampling, and large-kernel convolutions, achieving state-of-the-art performance with reduced computational overhead. The three variants stand out due to their optimal balance of speed, accuracy, and efficiency, making them especially suitable for resource-constrained environments. YOLOv5, introduced in 2020, marked a significant leap in performance and ease of use, establishing itself as a go-to solution for many edge computing applications. YOLOv8, released in 2023, built upon YOLOv5's success, offering improved accuracy and a unified framework for various computer vision tasks. YOLOv10, the latest iteration, pushes the boundaries further with innovative approaches to reduce computational overhead while maintaining high accuracy. These three YOLO variants have become prevalent in constrained edge deployment for several key reasons: optimized performance, scalability, ease of deployment, continuous improvement, and community support. YOLOv5 offers a range of model sizes (n, s, m, l, x) for different computational needs, while YOLOv8 provides a unified framework for various computer vision tasks. YOLOv10 introduces NMS-free training and other advanced techniques, making it particularly efficient for edge devices with limited computational resources. The paper highlights the key advancements of each version, compares their performance metrics, and discusses why they are particularly well-suited for edge deployment in various real-world applications. YOLOv5, YOLOv8, and YOLOv10 represent significant improvements in accuracy, efficiency, and real-time performance, making them leading choices for real-time object detection in edge computing scenarios.