Automated driving technology has gained a lot of momentum in the last few years. For the exploration field, navigation is the important key for autonomous operation. In difficult scenarios such as snowy environment, the road is covered with snow and road detection is impossible in this situation using only basic techniques. This paper introduces detection of snowy road in forest environment using RGB camera. The method combines noise filtering technique with morphological operation to classify the image component. By using the assumption that all road is covered by snow and the snow part is defined as road area. From the perspective image of road, the vanishing point of road is one of factor to scope the region of road. This vanishing point is found with fitting triangle technique. The performance of algorithm is evaluated by two error value: False Negative Rate and False Positive Rate. The error shows that the method has high efficiency for detect road with straight road but low performance for curved road. This road region will be applied with depth information from camera to detect for obstacle in the future work.
翻译:过去几年来,自动驾驶技术获得了很大的动力。对于勘探领域来说,航行是自主作业的重要关键。在雪地环境等困难情况下,道路被雪覆盖,道路探测在此情况下仅使用基本技术是不可能的。本文件介绍使用RGB相机探测森林环境中的雪路。这种方法结合了噪音过滤技术与形态操作,对图像部分进行分类。通过假设所有道路都被雪覆盖,而雪部分被定义为道路区域。从道路的视角看,道路的消失点是覆盖道路区域的一个因素。这个消失点是连接三角技术。算法的性能用两个错误值来评估:假负速和假正速率。错误表明,该方法具有高的效率,可以用直路探测道路,但弯曲路的性能低。这个路区将使用从相机获得的深度信息来探测未来工作中的障碍。