一种用于驾驶场景下手机检测的端到端的神经网络  

An end-to-end neural network for mobile phone detection in driving scenarios

作　　者：戴腾 张珂 尹东[1,2] Dai Teng;Zhang Ke;Yin Dong(School of Information Science Technology,University of Science and Technology of China,Hefei,Anhui 230027,China;Key Laboratory of Electromagnetic Space Information of Chinese Academy of Sciences,Hefei,Anhui 230027,China)

机构地区：[1]中国科学技术大学信息科学技术学院,安徽合肥230027 [2]中国科学院电磁空间信息重点实验室,安徽合肥230027

出　　处：《光电工程》2021年第4期68-77,共10页Opto-Electronic Engineering

基　　金：安徽省2018年度重点研究与开发计划项目(1804a09020049)。

摘　　要：小目标物体实时检测一直是图像处理领域中的难点。本文基于深度学习的目标检测算法,提出了一种端到端的神经网络,用于复杂驾驶场景下的手机小目标检测。首先,通过改进YOLOv4算法,设计了一个端到端的小目标检测网络(OMPDNet)来提取图片特征;其次,基于K-means算法设计了一个聚类中心更加贴切数据样本分布的聚类算法K-means-Precise,用以生成适应于小目标数据的先验框(anchor),从而提升网络模型的效率;最后,采用监督与弱监督方式构建了自己的数据集,并在数据集中加入负样本用于训练。在复杂的驾驶场景实验中,本文提出的OMPDNet算法不仅可以有效地完成驾驶员行车时使用手机的检测任务,而且对小目标检测在准确率和实时性上较当今流行算法都有一定的优势。Real-time detection of small objects is always a difficult problem in image processing.Based on the target detection algorithm of deep learning,this paper proposed an end-to-end neural network for mobile phone small target detection in complex driving scenarios.Firstly,an end-to-end small target detection network(OMPDNet)was designed to extract image features by improving the YOLOv4 algorithm.Secondly,based on the K-means algorithm,a K-means-Precise clustering algorithm of more appropriate data samples distribution in the clustering center was designed,which was used to generate prior frames suitable for small target data,so as to improve the efficiency of the network model.Finally,we constructed our own data set with supervision and weak supervision,and added negative samples to the data set for training.In the complex driving scene experiments,the OMPDNet algorithm proposed in this paper can not only effectively complete the detection task of using mobile phone while driving,but also has certain advantages over the current popular algorithms in accuracy and real-time for small target detection.

关 键 词：目标检测 神经网络 聚类算法 监督与弱监督 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] TP391.41[自动化与计算机技术—控制科学与工程]