TY - GEN AU - Juan Terven AU - Diana-Margarita Córdova-Esparza AU - Julio-Alejandro Romero-González TI - A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS PY - 2023/// CY - [Place of publication not identified] PB - Multidisciplinary Digital Publishing Institute KW - YOLO KW - real-time object detection KW - YOLOv8 KW - YOLO-NAS KW - network architecture evolution KW - training methods KW - B. Sc. Artificial Intelligence KW - UMUN open access collection KW - computer vision KW - Journal articles N1 - Publication type: Journal article; Linked open-access copy: published version; Open access; no subscription required for the linked open-access version N2 - YOLO has become a central real-time object detection system for robotics, driverless cars, and video monitoring applications. We present a comprehensive analysis of YOLO’s evolution, examining the innovations and contributions in each iteration from the original YOLO up to YOLOv8, YOLO-NAS, and YOLO with transformers. We start by describing the standard metrics and postprocessing; then, we discuss the major changes in network architecture and training tricks for each model. Finally, we summarize the essential lessons from YOLO’s development and provide a perspective on its future, highlighting potential research directions to enhance real-time object detection systems UR - https://doi.org/10.3390/make5040083 ER -