Motion and appearance based background subtraction for freely moving cameras
作者：
Highlights：
• Motion and appearance based background subtraction for freely moving cameras.
• Automatic foreground and background model initialization.
• No labeling or any prior information.
• Appearance models are continuously updated to cope up continuously changing scene.
• Minimal computational and memory cost for resource constraint ego-vision systems.
摘要
•Motion and appearance based background subtraction for freely moving cameras.•Automatic foreground and background model initialization.•No labeling or any prior information.•Appearance models are continuously updated to cope up continuously changing scene.•Minimal computational and memory cost for resource constraint ego-vision systems.
论文关键词：Background subtraction,Foreground segmentation,Moving camera,Image segmentation
论文评审过程：Received 17 October 2018, Revised 6 March 2019, Accepted 10 March 2019, Available online 21 March 2019, Version of Record 27 March 2019.
论文官网地址：https://doi.org/10.1016/j.image.2019.03.003
