基于人体关键点的分心驾驶行为识别
|
摘要
驾驶员分心驾驶是造成交通事故的主要原因之一,利用车载设备识别驾驶员是否存在分心行为是当下亟须解决的问题。识别驾驶员是否存在分心行为的关键,在于正确理解驾驶员的姿态。对此,文中提出一种使用驾驶员的人体关键点位置信息来帮助卷积神经网络识别驾驶员是否分心驾驶的方法。通过加入人体关键点的位置信息,可以有效地使得卷积神经网络关注于驾驶员的姿态,减少背景信息的干扰。使用Alpha Pose系统获取驾驶员上半身9个关键点的坐标,利用高斯公式分别以每个关键点为中心生成热力图。热力图包含关键点位置的响应,离关键点越近的位置,响应值越大。在VGG16和ResNet50的基础上,探讨8种结构,分别将9张热力图和不同的特征图融合,作为下一个卷积的输入。实验结果表明,该方法在State Farm数据集上达到了94.934%的准确率,优于其他方法。
Detecting distraction of drivers is one of the main causes of traffic accidents. Using in-vehicle equipment to identify whether the driver has distracted behavior is an urgent problem to be solved. The key to identify whether the driver has distracted behavior is to correctly understand the driver's posture. For this,we propose a method to help the convolutional neural network identify whether the driver is distracted by driving by human keypoints. By adding the position information of human keypoints,the convolutional neural network can effectively focus on the driver's attitude and reduce the interference of background information. The Alpha Pose system is used to obtain the coordinates of 9 keypoints of the driver's upper body,and Gauss formula is used to generate the heat map with each keypoint as the center. The heat map contains the response of the keypoints. The closer to the keypoints,the higher the response value. On the basis of VGG16 and ResNet50,8 structures are discussed,and 9 heat maps and different characteristic graphs are respectively fused as the input of the next convolution. The experiment shows that the proposed method has an accuracy rate of 94.934% in the State Farm Dataset,which is better than other methods.
Detecting distraction of drivers is one of the main causes of traffic accidents. Using in-vehicle equipment to identify whether the driver has distracted behavior is an urgent problem to be solved. The key to identify whether the driver has distracted behavior is to correctly understand the driver's posture. For this,we propose a method to help the convolutional neural network identify whether the driver is distracted by driving by human keypoints. By adding the position information of human keypoints,the convolutional neural network can effectively focus on the driver's attitude and reduce the interference of background information. The Alpha Pose system is used to obtain the coordinates of 9 keypoints of the driver's upper body,and Gauss formula is used to generate the heat map with each keypoint as the center. The heat map contains the response of the keypoints. The closer to the keypoints,the higher the response value. On the basis of VGG16 and ResNet50,8 structures are discussed,and 9 heat maps and different characteristic graphs are respectively fused as the input of the next convolution. The experiment shows that the proposed method has an accuracy rate of 94.934% in the State Farm Dataset,which is better than other methods.
引文
[1] CRAYE C,RASHWAN A,KAMEL M S,et al.A multimo-dal driver fatigue and distraction assessment system[J].International Journalof Intelligent Transportation Systems Research,2016,14(3):173-194.
[2] SAHAYADHAS A,SUNDARAJ K,MURUGAPPAN M,et al.A physiological measures-based method for detecting inattention in drivers using machine learning approach[J].Biocybernetics & Biomedical Engineering,2015,35(3):198-205.
[3] 彭军强,吴平东,殷罡.疲劳驾驶的脑电特性探索[J].北京理工大学学报,2007,27(7):585-589.
[4] 李君羡,潘晓东.基于脑电分析的连续驾驶疲劳高发时间判断[J].交通科学与工程,2012,28(4):72-79.
[5] 薛雷.考虑驾驶员生物电信号的疲劳驾驶检测方法研究[D].长春:吉林大学,2015.
[6] 耿磊,袁菲,肖志涛,等.基于面部行为分析的驾驶员疲劳检测方法[J].计算机工程,2018,44(1):274-279.
[7] 才博.基于人脸识别驾驶员疲劳检测系统设计与开发[D].大连:大连理工大学,2016.
[8] LE T H N,ZHENG Y,ZHU C,et al.Multiple scale faster-RCNN approach to driver’s cell-phone usage and hands on steering wheel detection[C]//IEEE conference on computer vision and pattern recognition workshops.Las Vegas,NV,USA:IEEE,2016:46-53.
[9] REN Shaoqing,HE Kaiming,GIRSHICK R,et al.Faster R-CNN:towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,39(6):1137-1149.
[10] 张辉,钱大琳,邵春福,等.驾驶人分心状态判别支持向量机模型优化算法[J].交通运输系统工程与信息,2018,18(1):127-132.
[11] 王冠,李振龙.基于反向双目识别的驾驶员分心检测[J].科学技术与工程,2018,18(17):82-88.
[12] SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[C]//International conference on learning representations.[s.l.]:[s.n.],2015:44-54.
[13] HE Kaiming,ZHANG Xiangyu,REN Shaoqing,et al.Deep residual learning for image recognition[C]//Computer vision and pattern recognition workshops.[s.l.]:IEEE,2016:770-778.
[14] JADERBERG M,SIMONYAN K,ZISSERMAN A.Spatial transformer networks[C]//Advances in neural information processing systems.[s.l.]:[s.n.],2015:2017-2025.
[15] YANG Wei,LI Shuang,OUYANG Wanli,et al.Learning feature pyramids for human pose estimation[C]//IEEE international conference on computer vision.[s.l.]:IEEE,2017:1290-1299.
[16] NEWELL A,YANG Kaiyu,DENG Jia.Stacked hourglass networks for human pose estimation[C]//European conference on computer vision.[s.l.]:Springer,2016:483-499.
[2] SAHAYADHAS A,SUNDARAJ K,MURUGAPPAN M,et al.A physiological measures-based method for detecting inattention in drivers using machine learning approach[J].Biocybernetics & Biomedical Engineering,2015,35(3):198-205.
[3] 彭军强,吴平东,殷罡.疲劳驾驶的脑电特性探索[J].北京理工大学学报,2007,27(7):585-589.
[4] 李君羡,潘晓东.基于脑电分析的连续驾驶疲劳高发时间判断[J].交通科学与工程,2012,28(4):72-79.
[5] 薛雷.考虑驾驶员生物电信号的疲劳驾驶检测方法研究[D].长春:吉林大学,2015.
[6] 耿磊,袁菲,肖志涛,等.基于面部行为分析的驾驶员疲劳检测方法[J].计算机工程,2018,44(1):274-279.
[7] 才博.基于人脸识别驾驶员疲劳检测系统设计与开发[D].大连:大连理工大学,2016.
[8] LE T H N,ZHENG Y,ZHU C,et al.Multiple scale faster-RCNN approach to driver’s cell-phone usage and hands on steering wheel detection[C]//IEEE conference on computer vision and pattern recognition workshops.Las Vegas,NV,USA:IEEE,2016:46-53.
[9] REN Shaoqing,HE Kaiming,GIRSHICK R,et al.Faster R-CNN:towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,39(6):1137-1149.
[10] 张辉,钱大琳,邵春福,等.驾驶人分心状态判别支持向量机模型优化算法[J].交通运输系统工程与信息,2018,18(1):127-132.
[11] 王冠,李振龙.基于反向双目识别的驾驶员分心检测[J].科学技术与工程,2018,18(17):82-88.
[12] SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[C]//International conference on learning representations.[s.l.]:[s.n.],2015:44-54.
[13] HE Kaiming,ZHANG Xiangyu,REN Shaoqing,et al.Deep residual learning for image recognition[C]//Computer vision and pattern recognition workshops.[s.l.]:IEEE,2016:770-778.
[14] JADERBERG M,SIMONYAN K,ZISSERMAN A.Spatial transformer networks[C]//Advances in neural information processing systems.[s.l.]:[s.n.],2015:2017-2025.
[15] YANG Wei,LI Shuang,OUYANG Wanli,et al.Learning feature pyramids for human pose estimation[C]//IEEE international conference on computer vision.[s.l.]:IEEE,2017:1290-1299.
[16] NEWELL A,YANG Kaiyu,DENG Jia.Stacked hourglass networks for human pose estimation[C]//European conference on computer vision.[s.l.]:Springer,2016:483-499.