基于微型FCN和传感器数据融合的迷宫小车姿态调整
|
摘要
为了实现无人小车在无标志迷宫内的姿态调整,在融合了超声波传感器和摄像头数据的基础上,提出了一种微型全卷积网络(FCN),用于实时分割地面,检测迷宫车道线,进行精确调整。该网络相较于常见的FCN,参数量下降了97%,显存占用下降了86. 44%,检测帧率达到了11. 2 fps,可用于嵌入式系统搭载。经实测检验,算法具有良好的调整效果,可用于小车迷宫内实时姿态调整。
In order to achieve the attitude adjustment of the unmanned car in no-mark maze,on the basis of fusion of ultrasonic sensor and camera data,a miniature fully convolutional networks( FCN) is proposed to divide the ground in real-time,detect the maze lane line and for precise adjustment. Compared with the common FCN,the parameter volume of the network drops by 97 %,the memory usage drops by 86. 44 %,and the detection frame rate reaches 11. 2 fps. So it can be used for embedded systems carrying. After the actual test,the algorithm has good adjustment effect,and can be used for unmanned car attitude adjustment in real-time in maze.
In order to achieve the attitude adjustment of the unmanned car in no-mark maze,on the basis of fusion of ultrasonic sensor and camera data,a miniature fully convolutional networks( FCN) is proposed to divide the ground in real-time,detect the maze lane line and for precise adjustment. Compared with the common FCN,the parameter volume of the network drops by 97 %,the memory usage drops by 86. 44 %,and the detection frame rate reaches 11. 2 fps. So it can be used for embedded systems carrying. After the actual test,the algorithm has good adjustment effect,and can be used for unmanned car attitude adjustment in real-time in maze.
引文
[1]Liu W,Anguelov D,Erhan D,et al.SSD:Single shot multi Box detector[C]∥European Conference on Computer Vision,2016.
[2]Long J,Shelhamer E,Darrell T.Fully convolutional networks for semantic segmentation[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2015:3431-3440.
[3]洪名佳,汪慧兰,黄娜君,等.一种基于FCN的车道线检测算法[J].无线电通信技术,2018,44(6):587-592.
[4]朱锋彬,应娜.基于改进卷积神经网络的快速车辆检测[J].传感器与微系统,2018,37(12):153-155,160.
[5]陈功醇,贾志绚.基于视觉传感器的车道检测算法[J].传感器与微系统,2014,33(11):125-128.
[6]胡骁,李岁劳,吴剑.基于特征颜色的车道线检测算法[J].计算机仿真,2011,28(10):344-348.
[7]卞建勇,徐建闽.一种基于改进Hough变换的车道线检测算法[J].微电子学与计算机,2013,30(5):157-161.
[8]李亚娣,黄海波,李相鹏,等.基于Canny算子和Hough变换的夜间车道线检测[J].科学技术与工程,2016,16(31):234-237,242.
[9]王超,王欢,赵春霞,等.基于梯度增强和逆透视验证的车道线检测[J].哈尔滨工程大学学报,2014(9):1156-1163.
[2]Long J,Shelhamer E,Darrell T.Fully convolutional networks for semantic segmentation[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2015:3431-3440.
[3]洪名佳,汪慧兰,黄娜君,等.一种基于FCN的车道线检测算法[J].无线电通信技术,2018,44(6):587-592.
[4]朱锋彬,应娜.基于改进卷积神经网络的快速车辆检测[J].传感器与微系统,2018,37(12):153-155,160.
[5]陈功醇,贾志绚.基于视觉传感器的车道检测算法[J].传感器与微系统,2014,33(11):125-128.
[6]胡骁,李岁劳,吴剑.基于特征颜色的车道线检测算法[J].计算机仿真,2011,28(10):344-348.
[7]卞建勇,徐建闽.一种基于改进Hough变换的车道线检测算法[J].微电子学与计算机,2013,30(5):157-161.
[8]李亚娣,黄海波,李相鹏,等.基于Canny算子和Hough变换的夜间车道线检测[J].科学技术与工程,2016,16(31):234-237,242.
[9]王超,王欢,赵春霞,等.基于梯度增强和逆透视验证的车道线检测[J].哈尔滨工程大学学报,2014(9):1156-1163.