#### Filter Results:

- Full text PDF available (114)

#### Publication Year

1989

2017

- This year (2)
- Last 5 years (23)
- Last 10 years (85)

#### Publication Type

#### Co-author

#### Journals and Conferences

#### Brain Region

#### Cell Type

#### Key Phrases

#### Method

#### Organism

Learn More

- Temujin Gautama, Marc M. Van Hulle
- IEEE Trans. Neural Networks
- 2002

We introduce a new technique for estimating the optical flow field, starting from image sequences. As suggested by Fleet and Jepson (1990), we track contours of constant phase over time, since these are more robust to variations in lighting conditions and deviations from pure translation than contours of constant amplitude. Our phase-based approach proceeds… (More)

Support Vector Machines have demonstrated excellent results in pattern recognition tasks and 3D object recognition. In this contribution, we confirm some of the results in 3D object recognition and compare it to other object recognition systems. We use different pixel-level representations to perform the experiments, while we extend the setting to the more… (More)

A novel ‘Delay Vector Variance’ (DVV) method for detecting the presence of determinism and nonlinearity in a time series is introduced. The method is based upon the examination of local predictability of a signal. Additionally, it spans the complete range of local linear models due to the standardisation to the distribution of pairwise distances between… (More)

- Marc M. Van Hulle
- Neural Computation
- 1997

- Karl Pauwels, Marc M. Van Hulle
- 2008 IEEE Computer Society Conference on Computer…
- 2008

Phase-based optical flow algorithms are characterized by high precision and robustness, but also by high computational requirements. Using the CUDA platform, we have implemented a phase-based algorithm that maps exceptionally well on the GPUpsilas architecture. This optical flow algorithm revolves around a reliability measure that evaluates the consistency… (More)

Most statistical signal nonlinearity analyses adopt the Monte-Carlo approach proposed by Theiler and co-workers, namely the ‘surrogate data’ method. A surrogate time series, or ‘surrogate’ for short, is generated as a realisation of the null hypothesis of linearity. A measure (‘test statistic’) is computed for the original time series and it is compared to… (More)

- Adrien Combaz, Nikolay Chumerin, Nikolay V. Manyakov, Arne Robben, Johan A. K. Suykens, Marc M. Van Hulle
- Neurocomputing
- 2012

A P300 Speller is a brain–computer interface (BCI) that enables subjects to spell text on a computer screen by detecting P300 Event-Related Potentials in their electroencephalograms (EEG). This BCI application is of particular interest to disabled patients who have lost all means of verbal and motor communication. Error-related Potentials (ErrPs) in the EEG… (More)

- Karl Pauwels, Marc M. Van Hulle
- Computer Vision and Image Understanding
- 2006

A novel method is introduced for optimal estimation of rigid camera motion from instantaneous velocity measurements. The error surface associated with this problem is highly complex and existing algorithms suffer heavily from local minima. Repeated minimization with different random initializations and selection of the minimum-cost solution are a common… (More)

- Marc M. Van Hulle
- Neural Computation
- 2005

We introduce a new unsupervised learning algorithm for kernel-based topographic map formation of heteroscedastic gaussian mixtures that allows for a unified account of distortion error (vector quantization), log-likelihood, and Kullback-Leibler divergence.

- Temujin Gautama, Danilo P. Mandic, Marc M. Van Hulle
- ICASSP
- 2003

A novel method for determining the set of parameters for a phase space representation of a time series is proposed. Based upon the differential entropy, both the optimal embedding dimension , and time lag , are simultaneously determined. The choice of these parameters is closely related to the length of the optimal tap input delay line of an adaptive filter… (More)