Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 4
Encontrada(s) 1 página(s)

RUA. Repositorio Institucional de la Universidad de Alicante
Publication Otros (Other)

Segmentation and 3D reconstruction of rose plants from stereoscopic images

  • Cuevas-Velasquez, Hanz
  • Gallego, Antonio-Javier
  • Fisher, Robert B.
  • Gallego, Antonio-Javier|||/items/8f865afc-8f63-4e0d-9408-bebc7ba836d0
The method proposed in this paper is part of the vision module of a garden robot capable of navigating towards rose bushes and clip them according to a set of pruning rules. The method is responsible for performing the segmentation of the branches and recovering their morphology in 3D. The obtained reconstruction allows the manipulator of the robot to select the candidate branches to be pruned. This method first obtains a stereo pair of images and calculates the disparity image using block matching and the segmentation of the branches using a Fully Convolutional Neuronal Network modified to return a map with the probability at the pixel level of the presence of a branch. A post-processing step combines the segmentation and the disparity in order to improve the results. Then, the skeleton of the plant and the branching structure are calculated, and finally, the 3D reconstruction is obtained. The proposed approach is evaluated with five different datasets, three of them compiled by the authors and two from the state of the art, including indoor and outdoor scenes with uncontrolled environments. The different steps of the proposed pipeline are evaluated and compared with other state-of-the-art methods, showing that the accuracy of the segmentation improves other methods for this task, even with variable lighting, and also that the skeletonization and the reconstruction processes obtain robust results.
Repositori Obert UdL
Publication Artículo científico (JournalArticle)

Evaluation of a boxwood topiary trimming robot

  • Marrewijk, Bart M.van
  • Vroegindeweij, Bastiaan A.
  • Gené Mola, Jordi
  • Mencarelli, Angelo
  • Hemming, Jochen
  • Mayer, Nikolaus
  • Wenger, Maximilian
  • Kootstra, Gert
This paper describes a new robot specifically developed for topiary trimming and evaluatesits performance through a novel evaluation method. Experiments were carried out in a realgarden letting the robot trim spherical-, cylindrical- and cuboid-shaped boxwood topiaries.The robot's performance was evaluated using a quantitative evaluation method, whichmade accurate 3D point clouds of the bush before and after trimming using photogram-metry. For each point in these point clouds, the Euclidean distance to the ground-truthshape was calculated and classified as correctly trimmed (CT) when the distance waswithin 2 cm of the ground-truth shape. Using this information the percentage of CT pointsbefore and after trimming were compared. Results show a reasonable robot accuracy whentrimming spherical topiaries, reporting a 24 percentage point increase of CT points, goingfrom 27% (before) to 51% (after) trimming of the bush surface. Cylinders and cuboids had alower performance, which reported an increase of CT between 0.2 and 6 percentage point.The performance of the robot was also qualitatively assessed by human observers byscoring topiaries. The highest score of a single bush is a 3.1 out of 5. These results, com-bined with the quantitative evaluation show that the robot can trim autonomously, but itdoes not reach the required accuracy for practical application. Despite this, the evaluationmethod was able to reveal main bottlenecks of the robot in real-world experiments.Together with the robot description, this paper can be used as a guideline for the devel-opment and evaluation of gardening robots., The work was performed within the TrimBot2020 project that has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No. 688007. The authors wish to thank Dejan Kaljaca for his strong contributions on the arm control, motion planning and the field evaluation experiments. The Spanish Ministry of Education and the Spanish Ministry of Science, Innovation and Universities are thanked for J. Gené’s pre-doctoral fellowships FPU15/03355 and EST18/00487, respectively.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

Cam-CONVS: Camera-aware multi-scale convolutions for single-view depth

  • Facil, J.M.
  • Ummenhofer, B.
  • Zhou, H.
  • Montesano, L.
  • Brox, T.
  • Civera, J.
Single-view depth estimation suffers from the problem that a network trained on images from one camera does not generalize to images taken with a different camera model. Thus, changing the camera model requires collecting an entirely new training dataset. In this work, we propose a new type of convolution that can take the camera parameters into account, thus allowing neural networks to learn calibration-aware patterns. Experiments confirm that this improves the generalization capabilities of depth prediction networks considerably, and clearly outperforms the state of the art when the train and test images are acquired with different cameras.
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Evaluation of a boxwood topiary trimming robot

  • Marrewijk, Bart M.van
  • Vroegindeweij, Bastiaan A.
  • Gené Mola, Jordi
  • Mencarelli, Angelo
  • Hemming, Jochen
  • Mayer, Nikolaus
  • Wenger, Maximilian
  • Kootstra, Gert
This paper describes a new robot specifically developed for topiary trimming and evaluatesits performance through a novel evaluation method. Experiments were carried out in a realgarden letting the robot trim spherical-, cylindrical- and cuboid-shaped boxwood topiaries.The robot's performance was evaluated using a quantitative evaluation method, whichmade accurate 3D point clouds of the bush before and after trimming using photogram-metry. For each point in these point clouds, the Euclidean distance to the ground-truthshape was calculated and classified as correctly trimmed (CT) when the distance waswithin 2 cm of the ground-truth shape. Using this information the percentage of CT pointsbefore and after trimming were compared. Results show a reasonable robot accuracy whentrimming spherical topiaries, reporting a 24 percentage point increase of CT points, goingfrom 27% (before) to 51% (after) trimming of the bush surface. Cylinders and cuboids had alower performance, which reported an increase of CT between 0.2 and 6 percentage point.The performance of the robot was also qualitatively assessed by human observers byscoring topiaries. The highest score of a single bush is a 3.1 out of 5. These results, com-bined with the quantitative evaluation show that the robot can trim autonomously, but itdoes not reach the required accuracy for practical application. Despite this, the evaluationmethod was able to reveal main bottlenecks of the robot in real-world experiments.Together with the robot description, this paper can be used as a guideline for the devel-opment and evaluation of gardening robots., The work was performed within the TrimBot2020 project that has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No. 688007. The authors wish to thank Dejan Kaljaca for his strong contributions on the arm control, motion planning and the field evaluation experiments. The Spanish Ministry of Education and the Spanish Ministry of Science, Innovation and Universities are thanked for J. Gené’s pre-doctoral fellowships FPU15/03355 and EST18/00487, respectively.