Trunk detection in tree crops using RGB-D images for structure-based ICM-SLAM

JAVIER GIMENEZ; SANSONI SEBASTIAN; SANTIAGO TOSETTI; FLAVIO CAPRARO; RICARDO CARELLI

COMPUTERS AND ELETRONICS IN AGRICULTURE

ELSEVIER SCI LTD

Lugar: Amsterdam; Año: 2022 vol. 199

0168-1699

Agricultural environments with tree plantations usually present a regular structure that can be used by SLAMsystems to improve self-location, and therefore, facilitate the autonomous navigation. In this context, tree trunksare natural landmarks that can be used to incorporate the environment structure into the problem modeling. Thisarticle presents a trunk detector solely based on RGB-D data obtained from a frontal-view stereo camera, and aSLAM system that incorporates the regular tree distribution of these crops. The trunk detector can be adapted tosimilar agricultural environments because its parameters have specific geometric meanings, which differentiatesit from black box-type procedures. The structure-based SLAM system has theoretical and practical advantagesover the well-known SLAM procedures in the mentioned context. This proposal can be executed on-line and isexperimentally tested with databases obtained from a challenging agricultural environment. Results show a goodperformance and robustness when the database is spatially or temporally subsampled, even under adverselighting conditions.