| 基于卷积神经网络的小目标交通标志检测算法 |
| |
| 引用本文： | 周苏,支雪磊,刘懂,宁皓,蒋连新,石繁槐.基于卷积神经网络的小目标交通标志检测算法[J].同济大学学报(自然科学版),2019,47(11):1626-1632. |
| |
| 作者姓名： | 周苏 支雪磊 刘懂 宁皓 蒋连新 石繁槐 |
| |
| 作者单位： | 同济大学 汽车学院， 上海 201804,同济大学 汽车学院， 上海 201804,同济大学 汽车学院， 上海 201804,苏州中德宏泰电子科技股份有限公司， 江苏 昆山 215332,苏州中德宏泰电子科技股份有限公司， 江苏 昆山 215332,同济大学 电子与信息工程学院， 上海 201804 |
| |
| 基金项目： | 奥地利Austrian Research Promotion Agency (FFG)基金”RoboCar”项目（No. 861000） |
| |
| 摘 要： | PVANet(performance vs accuracy network)卷积神经网络用于小目标检测的检测能力较弱.针对这一瓶颈问题,采用对PVANet网络的浅层特征提取层、深层特征提取层和HyperNet层(多层特征信息融合层)进行改进的措施,提出了一种适用于小目标物体检测的改进PVANet卷积神经网络模型,并在TT100K(Tsinghua-Tencent 100K)数据集上进行了交通标志检测算法验证实验.结果表明,所构建的卷积神经网络具有优秀的小目标物体检测能力,相应的交通标志检测算法可以实现较高的准确率.
|
| 关 键 词： | 卷积神经网络 交通标志检测 计算机视觉 小目标检测 |
| 收稿时间： | 2019/4/23 0:00:00 |
| 修稿时间： | 2019/9/30 0:00:00 |
A Convolutional Neural Network-Based Method for Small Traffic Sign Detection |
| |
| ZHOU Su,ZHI Xuelei,LIU Dong,NING Hao,JIANG Lianxin and SHI Fanhuai.A Convolutional Neural Network-Based Method for Small Traffic Sign Detection[J].Journal of Tongji University(Natural Science),2019,47(11):1626-1632. |
| |
| Authors: | ZHOU Su ZHI Xuelei LIU Dong NING Hao JIANG Lianxin and SHI Fanhuai |
| |
| Institution: | School of Automotive Studies, Tongji University, Shanghai 201804, China,School of Automotive Studies, Tongji University, Shanghai 201804, China,School of Automotive Studies, Tongji University, Shanghai 201804, China,Suzhou Zhongdehongtai Electronic Polytron Technology Co. Ltd., Kunshan 215332, China,Suzhou Zhongdehongtai Electronic Polytron Technology Co. Ltd., Kunshan 215332, China and College of Electronics and Information Engineering, Tongji University, Shanghai 201804, China |
| |
| Abstract: | In order to solve the small target detection convolutional neural network algorithm, the PVANet convolutional neural network structure was improved to conduct the experiments of traffic sign detection on the TT100K traffic sign data set. The shallow feature extraction, deep feature extraction, and HyperNet multilayer feature fusion modules were improved. The experimental results show that the improved PVANet convolutional neural network has an excellent detection ability for small target objects, and the corresponding traffic sign detection algorithm can achieve a higher mAP (mean average precision). |
| |
| Keywords: | convolutional neural network traffic sign detection computer vision small object detection |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《同济大学学报(自然科学版)》浏览原始摘要信息 |
| 点击此处可从《同济大学学报(自然科学版)》下载免费的PDF全文 |
|
