Universal Foreground Segmentation Based on Deep Feature Fusion Network for Multi-Scene Videos
Foreground/background (fg/bg) classification is an important first step for several video analysis tasks such as people counting, activity recognition and anomaly detection. As is the case for several other Computer Vision problems, the advent of deep Convolutional Neural Network (CNN) methods has l...
Main Authors: | Ye Tao, Zhihao Ling, Ioannis Patras |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8888275/ |
Similar Items
-
Foreground Segmentation in Depth Imagery Using Depth and Spatial Dynamic Models for Video Surveillance Applications
by: Carlos R. del-Blanco, et al.
Published: (2014-01-01) -
Weakly Supervised Foreground Segmentation Based on Superpixel Grouping
by: Wangsheng Yu, et al.
Published: (2018-01-01) -
Scene-Aware Deep Networks for Semantic Segmentation of Images
by: Zhike Yi, et al.
Published: (2019-01-01) -
Robust Background Subtraction with Foreground Validation for Urban Traffic Video
by: Cheung Sen-Ching S, et al.
Published: (2005-01-01) -
Comparative Evaluation of Background Subtraction Algorithms in Remote Scene Videos Captured by MWIR Sensors
by: Guangle Yao, et al.
Published: (2017-08-01)