Post identification and location derivation in vineyards through point clouds using cylinder extraction and density clustering

An automatic pruning machine is desirable due to the limitations and drawbacks of current grapevine pruning methods. It mitigates the issue of skilled worker shortages and reduces overall labour cost. To achieve autonomous grapevine pruning accurately and effectively, it is crucial to identify and locate posts, cordons and canes, which are the main objects for automatic pruning operations. In this paper, a new method is proposed to automatically identify the post and derive its location using point clouds. This method adopted the advantages of cylinder extraction and density clustering, and combined the features of cylinder and density for identification purposes. The results of applying this method to different data sets in vineyards are presented and its effectiveness is illustrated.