원문정보
초록
영어
With the development of computer vision technology utilizing GPUs, objects in video images are being detected in real-time and utilized in various fields. The emergence of CNN technology for detecting objects in video images has made significant progress in object detection research. CNNs have evolved through R-CNN, Fast R-CNN, Faster R-CNN, Mask R-CNN, etc., improving the accuracy and performance of object detection. While CNN-based technology accurately detects objects, detection time is lengthy, making real-time detection challenging. However, the YOLO technology, which enables real-time detection with a fast detection speed, was first proposed, and the accuracy has been greatly improved with the recent development of YOLOv9. Additionally, YOLO technology can operate on low-end boards such as Raspberry Pi or Jetson Nano, so it is used in various fields. Recently, YOLO technology can be used not only for image processing but also for security monitoring services, vehicle access control, and crack detection on roads through CCTV.
목차
1. INTRODUCTION
2. RELATED WORK
2.1. Object Detection Techniques Using Deep Learning Techniques
2.2. Image Recognition Technology Detection Types and Detector Classification
3. CNN-BASED OBJECT DETECTION TECHNIQUES
3.1. LeNet-5
3.2. R-CNN (Region-based CNN)
3.3. Fast R-CNN
3.4. Mask R-CNN
4. REAL-TIME OBJECT DETECTION TECHNIQUES
4.1. YOLOv1
4.2. YOLOv2
4.3. YOLOv3
4.4. YOLOv4
4.5. YOLOv5
4.6. YOLOv7
4.7. YOLOv6
4.8. YOLOv8
4.9. YOLOv9
5. CONCLUSION
REFERENCES