Image Based Landmark Detection in Vineyards

抄録

In this paper, we propose a robust algorithm to detect landmarks in a vineyard field. The algorithm only uses image data from inexpensive web-camera sensor to accurately detect pillars supporting the grape plants in the presence of noise. Robust detection of these landmarks is important for the autonomous task execution by a robot in vineyards. The detected pillars are also used for accurate localization and mapping. Moreover, based on accurate pillar detection, semantic data logging in vineyard becomes feasible. Traditionally, expensive GPS and Lidar sensors are used for landmark detection. The proposed method can robustly detect the supporting pillars or the vineyard using inexpensive cameras on robot.