| 李智伟,杨亚莉,钟卫军,杨聪,包壮壮.基于改进的SSD模型手机违规使用目标检测*[J].电子测量与仪器学报,2021,35(1):120-127 |
| 基于改进的SSD模型手机违规使用目标检测* |
| Target detection of illegal use of mobile phone based on improved SSD model |
| |
| DOI： |
| 中文关键词: 目标检测 深度学习 SSD 迁移学习 数据预处理 |
| 英文关键词:object detection deep learning SSD transfer learning data preprocessing |
| 基金项目:国家自然科学基金（61801518）、空军工程大学基础部研究生创新基金资助项目 |
|
|
| Author | Institution |
| Li Zhiwei | Department of Basic Sciences, Air Force Engineering University, Xi’an 710051, China |
| Yang Yali | Department of Basic Sciences, Air Force Engineering University, Xi’an 710051, China |
| Zhong Weijun | State Key Laboratory of Astronautic Dynamics, Xi’an 710043, China |
| Yang Cong | Department of Basic Sciences, Air Force Engineering University, Xi’an 710051, China |
| Bao Zhuangzhuang | Department of Basic Sciences, Air Force Engineering University, Xi’an 710051, China |
|
| 摘要点击次数: 1136 |
| 全文下载次数: 3 |
| 中文摘要: |
| 针对某些对手机使用有特殊规定的场所时常面临难以准确、高效地识别手机违规使用的问题,提出了一种基于改进的SSD模型来检测手机的违规使用。利用SSD模型获取初次目标位置及区域分类,并利用改进的DenseNet模型对初次目标框进行判定,从而获得精确的手机检测边界框。为改进数据预处理流程,采用了数据扩增与图像质量改善相结合的策略。在自建的手机检测数据集上的实验结果验证了这些改进策略的有效性,改进的SSD模型定位精度可达911%,识别精度高达98%,相比原有SSD模型提升了35%。改进的SSD模型同时具有识别精度高和定位精度高的特点,可为智能识别违规使用手机的行为提供理论依据和技术支持。 |
| 英文摘要: |
| In order to solve the problem that it is difficult to identify the illegal use of mobile phones accurately and efficiently in some places with special regulations on mobile phone use, this paper proposes an improved SSD model to detect the illegal use of mobile phones. The SSD model is used to obtain the location and area classification of the primary target, and the improved DenseNet model is used to determine the primary target frame, so as to obtain the accurate mobile phone detection boundary box. In order to improve the data preprocessing process, the strategy of combining data amplification with image quality improvement is adopted. The experimental results on the mobile phone set built by ourselves verifying the effectiveness of these improved strategies. The location accuracy of the improved SSD model can reach 911%, and the recognition accuracy can reach 98%, which is 35% higher than the original SSD model. The improved SSD model has the characteristics of high recognition accuracy and high positioning accuracy, which can provide theoretical basis and technical support for intelligent recognition of illegal use of mobile phones. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
