4 papers
Automatic Ground Truths: Projected Image Annotations for Omnidirectional Vision
Victor Stamatescu, Peter Barsznica, Manjung Kim +6
We present a novel data set made up of omnidirectional video of multiple objects whose centroid positions are annotated automatically. Omnidirectional vision is an active field of…
Track Everything: Limiting Prior Knowledge in Online Multi-Object Recognition
Sebastien C. Wong, Victor Stamatescu, Adam Gatt +3
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 wi…
A data set for evaluating the performance of multi-class multi-object video tracking
Avishek Chakraborty, Victor Stamatescu, Sebastien C. Wong +2
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 syste…
Understanding data augmentation for classification: when to warp?
Sebastien C. Wong, Adam Gatt, Victor Stamatescu +1
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 t…