| 一种基于改进NMS的牛脸检测方法 |
| |
| 引用本文： | 苟先太,黄巍,刘琪芬.一种基于改进NMS的牛脸检测方法[J].计算机与现代化,2019,0(7):43-46,54. |
| |
| 作者姓名： | 苟先太 黄巍 刘琪芬 |
| |
| 作者单位： | 西南交通大学电气工程学院,四川成都,611756;西南交通大学电气工程学院,四川成都,611756;西南交通大学电气工程学院,四川成都,611756 |
| |
| 基金项目： | 四川省重大科技专项项目(18ZDZX0162); 四川省重点研发项目(2017GZ0159) |
| |
| 摘 要： | 针对牲畜牛身份认证的多牛脸检测场景,本文给出一种基于改进Faster R-CNN的牛脸检测方法。使用Inception v2替换ZF网络作为Faster R-CNN的基础网络,模型精度得到显著提升;针对多牛检测场景对NMS(Non-Maximum Suppression)进行相应优化,使模型的召回率得到显著提升。通过和其他目标检测模型对比实验,本文的改进模型在精确率和召回率上均优于其他模型。
|
| 关 键 词： | FASTER R-CNN INCEPTION V2 NMS 目标检测 |
| 收稿时间： | 2019-07-08 |
A Cattle Face Detection Method Based on Improved NMS |
| |
| GOU Xian-tai,HUANG Wei,LIU Qi-fen.A Cattle Face Detection Method Based on Improved NMS[J].Computer and Modernization,2019,0(7):43-46,54. |
| |
| Authors: | GOU Xian-tai HUANG Wei LIU Qi-fen |
| |
| Affiliation: | (School of Electrical Engineering, Southwest Jiaotong University, Chengdu 611756, China) |
| |
| Abstract: | A cattle face detection method based on improved Faster R-CNN is proposed for multi-face detection of livestock cattle identity authentication. Inception v2 is used to replace ZF network as the basic network of Faster R-CNN, which improves the model accuracy significantly. The NMS (Non-Maximum Suppression) is optimized for the multi-cattle detection scenario, so that the recall rate of the model is significantly improved. Comparing with other detection models, the improved model is superior to others in accuracy and recall. |
| |
| Keywords: | Faster R-CNN Inception v2 NMS object detection
|
| 本文献已被 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机与现代化》浏览原始摘要信息 |
|
点击此处可从《计算机与现代化》下载全文 |
|
