Background Subtraction Based on Color and Depth Using Active Sensors
Metadatos
Mostrar el registro completo del ítemEditorial
MDPI
Materia
Background subtraction Foreground Segmentation Depth Kinect Active sensors Computer vision Video surveillance Sensor fusion
Fecha
2013Referencia bibliográfica
Fernández-Sánchez, E.J.; Díaz, J.; Ros, E. Background Subtraction Based on Color and Depth Using Active Sensors. Sensors, 13(7): 8895-8915 (2013). [doi: 10.3390/s130708895]
Patrocinador
This work was supported by the projects of excellence from Junta de Andalucia MULTIVISION (TIC-3873), ITREBA (TIC-5060) and VITVIR (P11-TIC-8120), the national project, ARC-VISION (TEC2010-15396), and the EU Project, TOMSY (FP7-270436).Resumen
Depth information has been used in computer vision for a wide variety of tasks. Since active range sensors are currently available at low cost, high-quality depth maps can be used as relevant input for many applications. Background subtraction and video segmentation algorithms can be improved by fusing depth and color inputs, which are complementary and allow one to solve many classic color segmentation issues. In this paper, we describe one fusion method to combine color and depth based on an advanced color-based algorithm. This technique has been evaluated by means of a complete dataset recorded with Microsoft Kinect, which enables comparison with the original method. The proposed method outperforms the others in almost every test, showing more robustness to illumination changes, shadows, reflections and camouflage.