| 改进 SSD 的交通标志目标检测算法 |
| |
| 引用本文： | 肖丹东,陈劲杰.改进 SSD 的交通标志目标检测算法[J].教育技术导刊,2020,19(5):48-51. |
| |
| 作者姓名： | 肖丹东 陈劲杰 |
| |
| 作者单位： | 上海理工大学 机械工程学院，上海 200093 |
| |
| 摘 要： | 以 Faster R-CNN 为代表的 two-stage 目标检测算法检测速度慢，而 one-stage 目标检测算法中的 SSD算法虽然检测速度快，但对交通标志类小目标的检测效果不佳。因此在 SSD 算法 VGG16 骨干网络上引入感受野块（RFB）结构，既提升检测速度又可在小目标检测上达到良好的检测精度。与此同时，为提高网络分类精度，在损失函数中加入中心损失。将 SSD 算法与改进的 SSD 算法在 VOC 数据集上进行训练，对比其性能可知，改进后算法 mPA 值达到 80.7%，相比 SSD300（VGG16）算法提高了 3.5%。该算法在 LISA traffic sign 数据集上训练，在迁移学习的基础上得到的 mPA 值为 78.4%，检测单张图像平均耗时为 20.5ms，可满足实时性要求。
|
| 关 键 词： | 交通标志 小目标检测 RFB 结构 中心损失 |
| 收稿时间： | 2019-07-23 |
Traffic Sign Target Detection Algorithm Based on Improved SSD |
| |
| XIAO Dan-dong,CHEN Jin-jie.Traffic Sign Target Detection Algorithm Based on Improved SSD[J].Introduction of Educational Technology,2020,19(5):48-51. |
| |
| Authors: | XIAO Dan-dong CHEN Jin-jie |
| |
| Institution: | School of Mechanical Engineering，University of Shanghai for Science and Technology，Shanghai 200093，China |
| |
| Abstract: | The existing two-stage target detection algorithm represented by Faster R-CNN is slow in detection speed，while the SSD algorithm in one-stage target detection algorithm detects fast，but detects on small targets，such as traffic signs，not effectively. Therefore，the introduction of the RFB structure on the VGG16 backbone network in the SSD algorithm can achieve good detection accuracy on small target detection while taking into account the detection speed. At the same time，in order to improve the classification accuracy of the network，the center loss content is added to the loss function. SSD algorithm and the improved SSD algorithm are trained on the VOC data sets. The performance of the two algorithms are compared. The mAP value of the improved algorithm reaches 80.7%， which is 3.5% higher than that of SSD300（VGG16）algorithm. Then，based on the migration learning，the algorithm was trained on the LISA traffic sign data set，and the obtained mPA value is 78.4%，and the average time taken to detect a single image is 20.5 ms，which satisfy the requirements of real-time performance. |
| |
| Keywords: | traffic signs small target detection RFB structure center loss |
|
| 点击此处可从《教育技术导刊》浏览原始摘要信息 |
| 点击此处可从《教育技术导刊》下载免费的PDF全文 |
