원문정보
초록
영어
Object detection is an important field of computer vision and is applied to applications such as security, autonomous driving, and face recognition. Recently, as the application of artificial intelligence technology including deep learning has been applied in various fields, it has become a more powerful tool that can learn meaningful high-level, deeper features, solving difficult problems that have not been solved. Therefore, deep learning techniques are also being studied in the field of object detection, and algorithms with excellent performance are being introduced. In this paper, a deep learning-based object detection algorithm used to detect multiple objects in an image is investigated, and future development directions are presented.
목차
1. INTRODUCTION
2. OBJECT DETECTION METHOD
2.1 R-CNN
2.2 Fast R-CNN
2.3 Faster R-CNN
2.4 Mask R-CNN
2.5 YOLO
2.6 SSD
2.7 RefineDet
2.8 Relation Networks for Object Detection
2.9 CenterNet
2.10 EfficientDet
3. Research direction of object detection
3.1 Combined one-stage detector and two-stage detector in object detection networks
3.2 Efficient post-processing method
3.3 Multi-domain object detection
3.4 Unsupervised object detection
3.5 Multi-source information support
3.6 Object detection system for portable terminals
3.7 GAN-based object detection system
4. Conclusion
5. ACKNOWLEDGEMENT
REFERENCES