Traffic sign detection algorithm based on feature expression enhancement
Traffic sign detection algorithm based on feature expression enhancement
复制标题
基于特征表达增强的交通标志检测算法
DOI：
10.1007/s11042-021-11413-x
复制
发表时间：
2021-08
影响因子：
3.6
通讯作者：
Rongcheng Cui
中科院分区：
文献类型：
--
作者：
Chao Sun;Mi Wen;Kai Zhang;Ping Meng;Rongcheng Cui
交通标志检测是计算机视觉领域的一个重要研究方向，对于自动驾驶和先进的辅助驾驶系统具有重要意义。由于自然场景中交通标志的复杂性，现有的交通标志检测算法存在误检率高、鲁棒性差等缺点。为了提高交通标志检测的准确性，提出了一种特征表达式增强SSD（ESSD）检测算法。ESSD以轻量级的方式提取语义信息，添加细节信息进行融合，通过多次卷积运算形成新的特征图，增强特征表达。与此同时，设计了一个新的目标默认框，以增加对交通标志的关注。SSD和ESSD在TT100K和CCTSDB数据集上重新训练。实验结果表明，改进后的ESSD算法的平均AP分别为81.26%和90.52%，平均AP提高了40%。使用PASCAL VOC数据集验证了ESSD模型的鲁棒性，该数据集显示出更好的小物体检测。
Traffic sign detection is an important research direction in computer vision, which is of great significance for autonomous driving and advanced assisted driving systems. Due to the complexity of traffic signs in natural scenes, existing traffic sign detection algorithms have disadvantages such as high false detection rates and poor robustness. To improve the accuracy of traffic sign detection, a feature expression enhanced SSD(ESSD) detection algorithm is proposed. ESSD extracts semantic information in a lightweight way, adds detailed information for fusion, and forms a new feature map through multiple convolution operations to enhance feature expression. Meanwhile, a new target default box was designed to increase the focus on traffic signs. The SSD and ESSD were retrained on TT100K and CCTSDB datasets. Experimental results show that the mAP of the improved ESSD is 81.26% and 90.52% and can improve AP up to 40%. The robustness of the ESSD model was verified using the PASCAL VOC data set, which showed better detection of small objects.
登录
查看更多内容
DOI：
10.1007/11736790_8
发表时间：
2005-04
期刊：
--
影响因子：
--
作者：
M. Everingham;Andrew Zisserman;Christopher K. I. Williams;L. Gool;Moray Allan;Charles M. Bishop;O. Chapelle-O
通讯作者：
M. Everingham;Andrew Zisserman;Christopher K. I. Williams;L. Gool;Moray Allan;Charles M. Bishop;O. Chapelle-O
DOI：
10.4018/978-1-5225-9096-5.ch007
发表时间：
2021-07
期刊：
Smart Computational Intelligence in Biomedical and Health Informatics
影响因子：
--
作者：
A. Sinha;S. Gupta;Anurag Tiwari;Amrita Chaturvedi
通讯作者：
A. Sinha;S. Gupta;Anurag Tiwari;Amrita Chaturvedi
影响因子：
20.6
作者：
Zou, Zhengxia;Chen, Keyan;Ye, Jieping
通讯作者：
Ye, Jieping
DOI：
10.1007/978-3-319-97436-1_3
发表时间：
2018-08
期刊：
Artificial Intelligence for Business
影响因子：
--
作者：
R. Akerkar
通讯作者：
R. Akerkar
DOI：
10.4018/978-1-5225-7862-8.ch007
发表时间：
2019
期刊：
Handbook of Research on Deep Learning Innovations and Trends
影响因子：
--
作者：
K. Lakhtaria;Darshankumar Modi
通讯作者：
K. Lakhtaria;Darshankumar Modi