Vision-based waypoint following using templates and artificial neural networks
Vision-based waypoint following using templates and artificial neural networks
复制标题
DOI：
10.1016/j.neucom.2012.07.040
复制
发表时间：
2013-05
期刊：
影响因子：
6
通讯作者：
J. Souza;G. Pessin;P. Shinzato;F. Osório;D. Wolf
中科院分区：
文献类型：
--
作者：
J. Souza;G. Pessin;P. Shinzato;F. Osório;D. Wolf
提出了一种基于学习的自主导航车辆控制系统。我们的方法是基于图像处理，道路和导航区域识别，模板匹配分类导航控制，和基于GPS航点的轨迹选择。车辆遵循由GPS点定义的轨迹，使用单个单目摄像机避开障碍物，并保持车辆在道路车道上。从相机获得的图像的不同部分，被分类成导航和非导航区域的环境中使用神经网络。它们为车辆提供转向和速度控制。在不同的环境条件下进行了一些实验测试，以评估所提出的技术。
This paper presents a learning-based vehicle control system capable of navigating autonomously. Our approach is based on image processing, road and navigable area recognition, template matching classification for navigation control, and trajectory selection based on GPS waypoints. The vehicle follows a trajectory defined by GPS points avoiding obstacles using a single monocular camera and maintaining the vehicle in the road lane. Different parts of the image, obtained from the camera, are classified into navigable and non-navigable regions of the environment using neural networks. They provide steering and velocity control to the vehicle. Several experimental tests have been carried out under different environmental conditions to evaluate the proposed techniques.