Abstract
Estimating the initial background of a scene is a key prerequisite for several applications in video analytics. In this paper, we present a simple approach that takes into account spatio-temporal motion intensities while estimating the true background. We tested the algorithm on real video sequences from the Scene Background Initialization (SBI) benchmark dataset, and the results show that the algorithm is competitive compared to the state of the art.
Original language | English |
---|---|
Title of host publication | 14th IEEE International Conference on Advanced Video and Signal Based Surveillance |
ISBN (Electronic) | 978-1-5386-2939-0 |
DOIs | |
Publication status | Published (in print/issue) - 23 Oct 2017 |
Event | 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) - Lecce, Italy Duration: 29 Aug 2017 → 1 Sept 2017 https://ieeexplore.ieee.org/xpl/conhome/8055736/proceeding |
Conference
Conference | 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) |
---|---|
City | Italy |
Period | 29/08/17 → 1/09/17 |
Internet address |
Keywords
- Video sequences
- Measurement
- Estimation
- Image color analysis
- Clustering algorithms
- Neural networks
- Adaptation models