Author pages are created from data sourced from our academic publisher partnerships and public sources.
Share This Author
A gradient descent rule for spiking neurons emitting multiple spikes
Navigation using an appearance based topological map
- O. Booij, B. Terwijn, Z. Zivkovic, B. Kröse
- Computer ScienceProceedings IEEE International Conference on…
- 10 April 2007
A system capable of using an appearance based topological map for navigation and made robust by using the epipolar geometry and a planar floor constraint in computing the necessary heading information to drive robustly in a large environment.
EL-GAN: Embedding Loss Driven Generative Adversarial Networks for Lane Detection
- Mohsen Ghafoorian, C. Nugteren, N. Baka, O. Booij, Michael Hofmann
- Computer ScienceECCV Workshops
- 14 June 2018
This work proposes EL-GAN: a GAN framework to mitigate the discussed problem using an embedding loss, and uses the TuSimple lane marking challenge to demonstrate that with this proposed framework it is viable to overcome the inherent anomalies of posing it as a semantic segmentation problem.
From images to rooms
Temporal Pattern Classification using Spiking Neural Networks
- O. Booij
- Computer Science
A novel supervised learning-rule is derived for Spiking Neural Networks (SNNs) using the gradient descent method, which can be applied on networks with a multi-layered architecture, taking full advantage of the capabilities of spiking neurons.
Re-thinking stages of cognitive development: An appraisal of connectionist models of the balance scale task
Efficient data association for view based SLAM using connected dominating sets
KPRNet: Improving projection-based LiDAR semantic segmentation
KPRNet improves the convolutional neural network architecture of 2D projection methods and utilizes KPConv to replace the commonly used post-processing techniques with a learnable point-wise component which allows the model to obtain more accurate 3D labels.
I Bet You Are Wrong: Gambling Adversarial Networks for Structured Semantic Segmentation
- Laurens Samson, N. V. Noord, O. Booij, Michael Hofmann, E. Gavves, Mohsen Ghafoorian
- Computer ScienceIEEE/CVF International Conference on Computer…
- 7 August 2019
This paper rethink adversarial training for semantic segmentation and proposes to reformulate the fake/real discrimination framework with a correct/incorrect training objective, replacing the discriminator with a "gambler" network that learns to spot and distribute its budget in areas where the predictions are clearly wrong.
No frame left behind: Full Video Action Recognition
- X. Liu, S. Pintea, F. K. Nejadasl, O. Booij, J. V. Gemert
- Computer ScienceIEEE/CVF Conference on Computer Vision and…
- 29 March 2021
This work proposes full video action recognition and considers all video frames, and relies on temporally localized clustering in combination with fast Hamming distances in feature space to make this computational tractable.