摘要
矿井行人检测是实现机车无人驾驶的关键技术之一,传统视觉特征提取算法无法有效地应对矿井巷道环境复杂、照明恶劣等问题.为此提出了一种基于并行特征传递的矿井行人检测深度学习网络,以保证检测的高准确率与强实时性.首先阐述了网络的结构,包括并行工作的行人辨识模块和行人定位模块,以及两者之间的特征传递块;其中行人辨识模块粗略调整锚点框位置与大小且过滤负锚点,行人定位模块进一步提升回归精度并给出预测结果特征,传递块将行人辨识模块的不同层的特征转换成行人定位模块所需特征.其次采用数据集扩增、数据增强和难例挖掘等措施优化训练过程.最后给出基于安徽桃源与新集矿井采集视频的实验结果.实验数据表明,所提算法以37帧/s的实时处理速率,其平均精度仍可保持63.4%,与YOLOv1算法相比,平均精度提高9.2%,与M2Det算法相比,提高22帧/s.
Mine pedestrian detection is one of the key technologies for realizing un-manned locomotives.The traditional visual feature extraction algorithm cannot effectively address the complex mine roadway environment and poor lighting.This paper proposes a deep learning network for mine pedestrian detection based on parallel feature transfer to ensure high accuracy and strong real-time performance.First,we describe the structure of the network,including the parallel pedestrian identification module,pedestrian location module and the feature transfer block between them.The pedestrian identification module roughly adjusts the position and size of the anchor boxes and filters the negative anchor boxes.The pedestrian location module further improves the regression accuracy and gives the prediction results.Feature transfer block transmits the features to better connect the two modules.Second,we adopt data set amplification,data enhancement and hard negative mining to optimize the training process.Finally,we get the experimental data from the Taoyuan and Xinji mines in Anhui province.The experimental data show that the proposed algorithm can still maintain 63.4%AP at a rereal-time processing rate of 37 FPS.Compared with the YOLOv1,the AP increases by 9.2%.Compared with the M2Det,the calculation efficiency increases by 22 FPS.
作者
卫星
张海涛
陆阳
石雷
Wei Xing;Zhang Haitao;Lu Yang;Shi Lei(School of Computer and Information,Hefei University of Technology,Hefei 230601;Engineering Research Center of Safety Critical Industry Measure and Control Technology,Ministry of Education,Hefei 230601)
出处
《计算机辅助设计与图形学学报》
EI
CSCD
北大核心
2019年第12期2091-2100,共10页
Journal of Computer-Aided Design & Computer Graphics
基金
国家重点研发计划专项(2018YFC0604404)
安徽省重点研发计划项目(201904d07020008)
中央高校基本科研业务费专项(JZ2019YYPY0012)
关键词
矿井行人检测
深度学习网络
并行特征传递
无人驾驶
mine pedestrian detection
deep learning network
parallel feature transfer
unmanned drive
