A Deep Convolutional Neural Network for Background Subtraction

By Mohammadreza Babaee, Duc Tung Dinh, Gerhard Rigoll. 2017

88 citations recorded by the source corpus.

In this work, we present a novel background subtraction system that uses a deep Convolutional Neural Network (CNN) to perform the segmentation. With this approach, feature engineering and parameter tuning become unnecessary since the network parameters can be learned from data by training a single CNN that can handle various video scenes. Additionally, we propose a new approach to estimate background model from video. For the training of the CNN, we employed randomly 5 percent video frames and their ground truth segmentations taken from the Change Detection challenge 2014(CDnet 2014). We also utilized spatial-median filtering as the post-processing of the network outputs. Our method is evaluated with different data-sets, and the network outperforms the existing algorithms with respect to the average ranking over different evaluation metrics. Furthermore, due to the network architecture, our CNN is capable of real time processing.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Thierry Bouwmans
2. Sara Beery
3. Grant Van Horn
4. Bastian Leibe
5. Pietro Perona
6. Niki Trigoni
7. Soon Ki Jung
8. Paul Voigtlaender

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Bastian Leibe
3. Yi Yang
4. Xiaogang Wang
5. Philip H. S. Torr
6. Trevor Darrell
7. Andrew Zisserman
8. Jitendra Malik

In Media Technology

1. Soon Ki Jung
2. Sajid Javed
3. Bastian Leibe
4. Pietro Perona
5. Niki Trigoni
6. Thierry Bouwmans
7. Sara Beery
8. Paul Voigtlaender

Citations in the corpus

• Recognition in Terra Incognita (2018, background): “background in video is a well studied problem [36], [37].”
• Deep Neural Network Concepts for Background Subtraction: A Systematic Review and Comparative Evaluation (2018, methodology): “Deep CNN [4] No (37 × 37) Scene-specific GT No Yes No (Post-proc.”
• Visual SLAM and Structure from Motion in Dynamic Environments (2018, methodology): “Instead of initializing the foreground object, background initialization sets a background model similarly found in background subtraction techniques [7, 126].”
• The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches (2018, unknown): “MIT proposed “Eyeriss” as a hardware for deep convolutional neural networks (DCNN) [278].”
• Online Adaptation of Convolutional Neural Networks for Video Object Segmentation (2017, background): “Recently, deep learning based approaches, which often utilize large classification datasets for pretraining, have shown extremely good performance for VOS [7, 20, 24, 35] and the related tasks of single-object tracking [5, 18, 31] and background modeling [2, 6, 44].”