repository
Sequence-based object detection with yolov7
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.advisor | 신동욱 | - |
| dc.contributor.author | 안대훈 | - |
| dc.date.accessioned | 2025-01-25T01:36:01Z | - |
| dc.date.available | 2025-01-25T01:36:01Z | - |
| dc.date.issued | 2023-08 | - |
| dc.identifier.other | 33041 | - |
| dc.identifier.uri | https://dspace.ajou.ac.kr/handle/2018.oak/24496 | - |
| dc.description | 학위논문(석사)--수학과,2023. 8 | - |
| dc.description.tableofcontents | 1. Introduction 1 <br>2. Related Works 2 <br> 2.1 YOLO 2 <br> 2.2 Loss function 2 <br>3. Data 5 <br> 3.1 One-class dataset 5 <br> 3.2 Three-class dataset 6 <br>4. Method 8 <br>5. Experiments 10 <br> 5.1 One-Class Dataset 10 <br> 5.2 Three-Class Dataset 11 <br>6. Conclusion 13 <br>7. References 15 | - |
| dc.language.iso | eng | - |
| dc.publisher | The Graduate School, Ajou University | - |
| dc.rights | 아주대학교 논문은 저작권에 의해 보호받습니다. | - |
| dc.title | Sequence-based object detection with yolov7 | - |
| dc.type | Thesis | - |
| dc.contributor.affiliation | 아주대학교 대학원 | - |
| dc.contributor.alternativeName | Dae Hoon Ahn | - |
| dc.contributor.department | 일반대학원 수학과 | - |
| dc.date.awarded | 2023-08 | - |
| dc.description.degree | Master | - |
| dc.identifier.localId | T000000033041 | - |
| dc.identifier.url | https://dcoll.ajou.ac.kr/dcollection/common/orgView/000000033041 | - |
| dc.subject.keyword | Object detection | - |
| dc.subject.keyword | Sequence-based detection | - |
| dc.subject.keyword | YOLOv7 | - |
| dc.description.alternativeAbstract | In this paper, we propose a novel algorithm called sequence-based object detection to identify accidents in advance and prevent secondary accidents. To evaluate our proposed algorithm, we also propose a novel metric called sequence-based evaluation. We trained model for two datasets, one-class dataset and three-class dataset. For one-class dataset, we used focal loss, and as the results we achieved mAP@0.5 score above o.8 and accuracy 1.0. For three-class dataset, we compared focal loss and quality focal loss, and as the results we achieved mAP@0.5 score above 0.7 and accuracy 1.0. | - |
- Appears in Collections:
- Graduate School of Ajou University > Department of Mathematics > 3. Theses(Master)
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
-
- License
- STATISTICS
- Total Visit :5,011,543
- Total Download :2,095
- Today View :1,726
