Search Results for author: Eldert J. van Henten

Found 7 papers, 2 papers with code

Gradient-based Local Next-best-view Planning for Improved Perception of Targeted Plant Nodes

1 code implementation28 Nov 2023 Akshay K. Burusa, Eldert J. van Henten, Gert Kootstra

We propose a gradient-based NBV planner using differential ray sampling, which directly estimates the local gradient direction for viewpoint planning to overcome occlusion and improve perception.

3D Reconstruction

Efficient Search and Detection of Relevant Plant Parts using Semantics-Aware Active Vision

no code implementations16 Jun 2023 Akshay K. Burusa, Joost Scholten, David Rapado Rincon, Xin Wang, Eldert J. van Henten, Gert Kootstra

To automate harvesting and de-leafing of tomato plants using robots, it is important to search and detect the relevant plant parts, namely tomatoes, peduncles, and petioles.

Development and evaluation of automated localisation and reconstruction of all fruits on tomato plants in a greenhouse based on multi-view perception and 3D multi-object tracking

no code implementations4 Nov 2022 David Rapado Rincon, Eldert J. van Henten, Gert Kootstra

The accuracy of the representation was evaluated in a real-world environment, where successful representation and localisation of tomatoes in tomato plants were achieved, despite high levels of occlusion, with the total count of tomatoes estimated with a maximum error of 5. 08% and the tomatoes tracked with an accuracy up to 71. 47%.

3D Multi-Object Tracking

Attention-driven Active Vision for Efficient Reconstruction of Plants and Targeted Plant Parts

no code implementations21 Jun 2022 Akshay K. Burusa, Eldert J. van Henten, Gert Kootstra

We conclude that an attention mechanism for active-vision is necessary to significantly improve the quality of perception in complex agro-food environments.

3D Reconstruction

Active learning with MaskAL reduces annotation effort for training Mask R-CNN

3 code implementations13 Dec 2021 Pieter M. Blok, Gert Kootstra, Hakim Elchaoui Elghor, Boubacar Diallo, Frits K. van Evert, Eldert J. van Henten

In our study, MaskAL was compared to a random sampling method on a broccoli dataset with five visually similar classes.

Active Learning

Improved Part Segmentation Performance by Optimising Realism of Synthetic Images using Cycle Generative Adversarial Networks

no code implementations16 Mar 2018 Ruud Barth, Jochen Hemming, Eldert J. van Henten

We hypothesised that the translated images can be used for (i) improved learning of empirical images, and (ii) that learning without any fine-tuning with empirical images is improved by bootstrapping with translated images over bootstrapping with synthetic images.

Generative Adversarial Network Translation

Cannot find the paper you are looking for? You can Submit a new open access paper.