The Application of Improved YOLO V3 in Multi-Scale Target Detection
文献类型：期刊论文
| 作者 | Luo HB(罗海波)1,2,4,5 ; Hui B(惠斌)1,2,4,5; Chang Z(常铮)1,2,4,5; Ju MR(鞠默然)1,2,3,4,5; Wang ZB(王仲博)1,2,3,4,5
|
| 刊名 | APPLIED SCIENCES-BASEL
 |
| 出版日期 | 2019 |
| 卷号 | 9期号:18页码:1-14 |
| 关键词 | target detection YOLO V3 anchor box computer vision deep learning |
| ISSN号 | 2076-3417 |
| 产权排序 | 1 |
| 英文摘要 | Target detection is one of the most important research directions in computer vision. Recently, a variety of target detection algorithms have been proposed. Since the targets have varying sizes in a scene, it is essential to be able to detect the targets at different scales. To improve the detection performance of targets with different sizes, a multi-scale target detection algorithm was proposed involving improved YOLO (You Only Look Once) V3. The main contributions of our work include: (1) a mathematical derivation method based on Intersection over Union (IOU) was proposed to select the number and the aspect ratio dimensions of the candidate anchor boxes for each scale of the improved YOLO V3; (2) To further improve the detection performance of the network, the detection scales of YOLO V3 have been extended from 3 to 4 and the feature fusion target detection layer downsampled by 4x is established to detect the small targets; (3) To avoid gradient fading and enhance the reuse of the features, the six convolutional layers in front of the output detection layer are transformed into two residual units. The experimental results upon PASCAL VOC dataset and KITTI dataset show that the proposed method has obtained better performance than other state-of-the-art target detection algorithms. |
| 语种 | 英语 |
| WOS记录号 | WOS:000489115200135 |
| 源URL | [http://ir.sia.cn/handle/173321/25771]  |
| 专题 | 沈阳自动化研究所_光电信息技术研究室 |
| 作者单位 | 1.The Key Lab of Image Understanding and Computer Vision, Shenyang 110016, China 2.Key Laboratory of Opto-Electronic Information Processing, Chinese Academy of Science, Shenyang 110016, China 3.University of Chinese Academy of Sciences, Beijing 100049, China 4.Institutes for Robotics and IntelligentManufacturing, Chinese Academy of Sciences, Shenyang 110169, China 5.Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China |
| 推荐引用方式 GB/T 7714 | Luo HB,Hui B,Chang Z,et al. The Application of Improved YOLO V3 in Multi-Scale Target Detection[J]. APPLIED SCIENCES-BASEL,2019,9(18):1-14. |
| APA | Luo HB,Hui B,Chang Z,Ju MR,&Wang ZB.(2019).The Application of Improved YOLO V3 in Multi-Scale Target Detection.APPLIED SCIENCES-BASEL,9(18),1-14. |
| MLA | Luo HB,et al."The Application of Improved YOLO V3 in Multi-Scale Target Detection".APPLIED SCIENCES-BASEL 9.18(2019):1-14. |
入库方式： OAI收割
来源：沈阳自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。