Abstract
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.
Keywords
Computer scienceArchitectureArtificial intelligenceObject detectionRoboticsSystems engineeringHuman–computer interactionEngineeringRobotGeography
Affiliated Institutions
Related Publications
Object Detection With Deep Learning: A Review
Due to object detection's close relationship with video analysis and image understanding, it has attracted much research attention in recent years. Traditional object detection ...
YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors
Real-time object detection is one of the most important research topics in computer vision. As new approaches regarding architecture optimization and training optimization are c...
A ConvNet for the 2020s
The "Roaring 20s" of visual recognition began with the introduction of Vision Transformers (ViTs), which quickly superseded ConvNets as the state-of-the-art image classification...
FCOS: Fully Convolutional One-Stage Object Detection
We propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to semantic segmentation. Almost all stat...
ORB: An efficient alternative to SIFT or SURF
Feature matching is at the base of many computer vision problems, such as object recognition or structure from motion. Current methods rely on costly descriptors for detection a...
Publication Info
- Year
- 2023
- Type
- review
- Volume
- 5
- Issue
- 4
- Pages
- 1680-1716
- Citations
- 1932
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
1932
OpenAlex
86
Influential
1950
CrossRef
Cite This
Juan Terven,
Diana‐Margarita Córdova‐Esparza,
Julio-Alejandro Romero-González
(2023).
A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS.
Machine Learning and Knowledge Extraction
, 5
(4)
, 1680-1716.
https://doi.org/10.3390/make5040083
Identifiers
- DOI
- 10.3390/make5040083
- arXiv
- 2304.00501