Towards Benchmarking Scene Background Initialization
This work provides a benchmark for researchers and practitioners in video surveillance and computational photography, though it is incremental as it focuses on evaluation rather than new methods.
The paper addresses the lack of standardized evaluation for scene background initialization methods by assembling a dataset with ground truths and metrics, enabling fair comparison of existing techniques.
Given a set of images of a scene taken at different times, the availability of an initial background model that describes the scene without foreground objects is the prerequisite for a wide range of applications, ranging from video surveillance to computational photography. Even though several methods have been proposed for scene background initialization, the lack of a common groundtruthed dataset and of a common set of metrics makes it difficult to compare their performance. To move first steps towards an easy and fair comparison of these methods, we assembled a dataset of sequences frequently adopted for background initialization, selected or created ground truths for quantitative evaluation through a selected suite of metrics, and compared results obtained by some existing methods, making all the material publicly available.