CDnet 2014: An Expanded Change Detection Benchmark Dataset

By Yi Wang, Pierre-Marc Jodoin, Fatih Murat Porikli, Janusz Konrad, Yannick Benezeth, Prakash Ishwar. 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2014

864 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/80c3b84fddd0ddece79500af5e1afbd2b40e7ef8

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. Pierre-Luc St-Charles
3. Augusto Salazar
4. Gerhard Rigoll
5. Thomas Baltzer Moeslund
6. Guillaume-Alexandre Bilodeau
7. Namrata Vaswani
8. Zheng Zhu

In Biomedical Engineering

1. Thierry Bouwmans
2. Sajid Javed
3. Praneeth Narayanamurthy
4. Pierre-Luc St-Charles
5. Gerhard Rigoll
6. Guillaume-Alexandre Bilodeau
7. Namrata Vaswani
8. Soon Ki Jung

In Computer Vision and Pattern Recognition

1. Thierry Bouwmans
2. Belmar García García
3. Sajid Javed
4. Soon Ki Jung
5. Thomas Baltzer Moeslund
6. Chris H. Bahnsen
7. Mohammadreza Babaee
8. Duc Tung Dinh

Citations in the corpus

• Rain Removal in Traffic Surveillance: Does it Matter? (2018, methodology): “net dataset [6] and is not successful on a classical feature tracking pipeline.”
• Robust Subspace Learning: Robust PCA, Robust Subspace Tracking, and Robust Subspace Recovery (2017, methodology): “After this, we provide a quantitative performance evaluation of these and many other RPCA methods for foreground-background separation (background subtraction) using Change Detection (CDnet) 2012 dataset [61].”
• SuBSENSE: A Universal Change Detection Method With Local Adaptive Sensitivity (2015, methodology): “For their specific descriptions, refer to [3] and [4].”
• A Deep Convolutional Neural Network for Background Subtraction (2017, methodology): “For the newly added categories in CDnet 2014 [27] (see Table 2), only half of the ground truth segmentations were provided to avoid parameter tuning of background subtraction”
• An Efficient Optical Flow Based Motion Detection Method for Non-stationary Scenes (2018, background): “According to the results of Playground and Highway sequences, our method is sensitive to shadow, which leads to some false positive results and has negative influence on the quantitative results.”
• Deep Neural Network Concepts for Background Subtraction: A Systematic Review and Comparative Evaluation (2018, methodology): “ook/fb.resnet.torch 18 Thierry Bouwmans, Sajid Javed, Maryam Sultana, Soon Ki Jung [216] evaluated their method on a subset of 6sequences of CDnet 2012 [62] instead of all the categories of CDnet 2014[203] making the comparisonmore difficult with the other DNN methods. Alikan [2] designed a Multi-Vie”
• Camera-trap images segmentation using multi-layer robust principal component analysis (2017, methodology): “The algorithms suBSENSE, Fuzzy-Adaptive-SOM, GMM, and AGMM have been tested in the 2014 Computer Vision and PatternRecognition (CVPR)ChangeDetectionWorkshops [38], obtaining average F-measure 0.”
• Background Subtraction in Real Applications: Challenges, Current Models and Future Directions (2019, background): “extended with additional camera-captured videos ( 70,000 new frames) spanning 5 new categories, and became the CDnet 2014 dataset [377].”