||
本文为美国新奥尔良大学(作者:Sowmya Bandarupalli)的硕士论文,共84页。
本文介绍了一种利用无线传感器和摄像机进行车辆检测、跟踪的监控试验台研制。实验研究包括试验台的设计,并讨论了无线传感器和摄像机在实际应用中的一些问题。一组装有光传感器的装置用于检测、定位移动车辆的位置,利用背景减法对视频序列中的运动车辆进行检测。在每一帧中计算了车辆质心,采用非线性最小化方法对投影三维点到二维图像点的透视变换进行估计。将三个摄像头的车辆位置估计融合在一起,形成代表车辆运动的单一轨迹,给出了传感器和摄像机的实验结果。摄像机和无线传感器的车辆位置估计平均误差约为0.5英尺。
This thesis presents the development of asurveillance testbed using wireless sensors and video cameras for vehicledetection and tracking. The experimental study includes testbed design anddiscusses some of the implementation issues in using wireless sensors and videocameras for a practical application. A group of sensor devices equipped withlight sensors are used to detect and localize the position of moving vehicle.Background subtraction method is used to detect the moving vehicle from thevideo sequences. Vehicle centroid is calculated in each frame. A nonlinearminimization method is used to estimate the perspective transformation whichproject 3D points to 2D image points. Vehicle location estimates from threecameras are fused to form a single trajectory representing the vehicle motion.Experimental results using both sensors and cameras are presented. Averageerror between vehicle location estimates from the cameras and the wireless sensorsis around 0.5ft.
更多精彩文章请关注公众号:
Archiver|手机版|科学网 ( 京ICP备07017567号-12 )
GMT+8, 2024-9-25 13:40
Powered by ScienceNet.cn
Copyright © 2007- 中国科学报社