Victor Stamatescu

Learn More
In this paper we investigate the benefit of augmenting data with synthetically created samples when training a machine learning classifier. Two approaches for creating additional training samples are data warping, which generates additional samples through transformations applied in the data-space, and synthetic over-sampling, which creates additional(More)
A critical issue for adaptive visual tracking is that of model drift, which occurs when the state space of the object of interest is polluted by observations that should have been attributed to background clutter. One approach to mitigating model drift in adaptive feature-learning visual tracking systems is to introduce prior information about the object of(More)
In 2004, we searched for very high energy (VHE) gamma-ray emission from the Galactic Plane using the CANGAROO-III stereoscopic observation system. Two different longitude regions (= −19 • .5 and = +13 • .0) on the Galactic Plane were observed during July and August 2004. We analyzed events that triggered three telescopes aiming to measure the diffuse(More)
We present the detection of nearby BL Lacertae object PKS 2155-304 with the CANGAROO-III imaging atmospheric Cherenkov telescope system. This observation was triggered by the H.E.S.S. report in July 2006 that the outburst at TeV gamma-ray energy range occured on this object. Observations have been performed between 2006 July 28 and August 2. A signal from(More)
We report on the detection of very-high energy (VHE, E > 100 GeV) γ-ray emission from NGC 1275, the central radio galaxy of the Perseus cluster of galaxies. The source has been detected by the MAGIC telescopes with a statistical significance of 6.6 σ above 100 GeV in 46 hr of stereo observations carried out between August 2010 and February 2011. The(More)
Context. Magnetars are an extreme, highly magnetized class of isolated neutron stars whose large X-ray luminosity is believed to be driven by their high magnetic field. Aims. Study for the first time the possible very high energy γ-ray emission above 100 GeV from magnetars, observing the sources 4U 0142+61 and 1E 2259+586. Methods. We observed the two(More)
This paper addresses the problem of online tracking and classification of multiple objects in an image sequence. Our proposed solution is to first track all objects in the scene without relying on object-specific prior knowledge, which in other systems can take the form of hand-crafted features or user-based track initialization. We then classify the(More)
Supermassive black holes with masses of millions to billions of solar masses are commonly found in the centers of galaxies. Astronomers seek to image jet formation using radio interferometry but still suffer from insufficient angular resolution. An alternative method to resolve small structures is to measure the time variability of their emission. Here we(More)
One of the challenges in evaluating multi-object video detection, tracking and classification systems is having publically available data sets with which to compare different systems. However, the measures of performance for tracking and classification are different. Data sets that are suitable for evaluating tracking systems may not be appropriate for(More)
  • 1