Non-stationary VFD Evaluation Kit: Dataset and Metrics to Fuel Video-Based Fire Detection Development

Datasets play a major role in the advance of computer vision techniques nowadays. Open, complete and challenging ground truth data, combined with standardized metrics are essential to push the development and allow the proper evaluation of computer vision algorithms. Even though a significant amount of work on VFD (video-based fire detection) systems has been developed, compare different algorithms is a laborious task due to the lack of common evaluation schemes and evaluation datasets. We address both of these issues by presenting a dataset of fire videos along with frame by frame annotations to be used for non-stationary fire detection algorithms training and validation. By the time, this is the largest dataset released on this subject matter. Standard video file formats and open markup languages where used to allow compatibility and convenient integration with the most popular computer vision libraries. The dataset includes hand-held, robot attached and drone attached footages and aims to boost the development of fully autonomous firefighter robots. The presented ground truth and metrics adapt to the majority of the state-of-the-art techniques and provides a reliable and unbiased solution to compare them. The dataset, example source-code and documentation are publicly available under the Creative Commons 3.0 license on GitHub.

[1]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[2]  Maja Štula,et al.  Forest Fire Protection by Advanced Video Detection System - Croatian Experiences , 2006 .

[3]  Takashi Kashiwagi,et al.  An experimental investigation of the pulsation frequency of flames , 1992 .

[4]  Toby P. Breckon,et al.  A non-temporal texture driven approach to real-time fire detection , 2011, 2011 18th IEEE International Conference on Image Processing.

[5]  Turgay Celik,et al.  Fast and Efficient Method for Fire Detection Using Image Processing , 2010 .

[6]  Glenn Healey,et al.  A system for real-time fire detection , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Robert M. Haralick,et al.  Ridges and valleys on digital images , 1983, Comput. Vis. Graph. Image Process..

[8]  Daniel McDuff,et al.  Affectiva-MIT Facial Expression Dataset (AM-FED): Naturalistic and Spontaneous Facial Expressions Collected "In-the-Wild" , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[9]  A. Enis Çetin,et al.  Computer vision based method for real-time fire and flame detection , 2006, Pattern Recognit. Lett..

[10]  Ebroul Izquierdo,et al.  A Probabilistic Approach for Vision-Based Fire Detection in Videos , 2010, IEEE Transactions on Circuits and Systems for Video Technology.

[11]  A. Enis Çetin,et al.  Real-time wildfire detection using correlation descriptors , 2011, 2011 19th European Signal Processing Conference.

[12]  Nancy Chinchor,et al.  MUC-4 evaluation metrics , 1992, MUC.

[13]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[14]  A. Enis Çetin,et al.  Wildfire detection using LMS based active learning , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[15]  Cristiano Rafael Steffens,et al.  An Unconstrained Dataset for Non-Stationary Video Based Fire Detection , 2015, 2015 12th Latin American Robotics Symposium and 2015 3rd Brazilian Symposium on Robotics (LARS-SBR).

[16]  Ti Nguyen-Ti,et al.  Fire detection based on video processing method , 2013, 2013 International Conference on Advanced Technologies for Communications (ATC 2013).

[17]  Chao-Ho Chen,et al.  An early fire-detection method based on image processing , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[18]  ByoungChul Ko,et al.  Forest Smoke Detection Using CCD Camera and Spatial-temporal Variation of Smoke Visual Patterns , 2011, 2011 Eighth International Conference Computer Graphics, Imaging and Visualization.

[19]  Hakil Kim,et al.  Robust fire detection using logistic regression and randomness testing for real-time video surveillance , 2015, 2015 IEEE 10th Conference on Industrial Electronics and Applications (ICIEA).

[20]  Wolfram Burgard,et al.  A benchmark for the evaluation of RGB-D SLAM systems , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[21]  Hélène Laurent,et al.  Fire scene segmentations for forest fire characterization: A comparative study , 2011, 2011 18th IEEE International Conference on Image Processing.

[22]  Moulay A. Akhloufi,et al.  Benchmarking of wildland fire colour segmentation algorithms , 2015, IET Image Process..

[23]  Ricardus Anggi Pramunendar,et al.  Multi color feature, background subtraction and time frame selection for fire detection , 2013, 2013 International Conference on Robotics, Biomimetics, Intelligent Computational Systems.

[24]  Takeo Kanade,et al.  The Extended Cohn-Kanade Dataset (CK+): A complete dataset for action unit and emotion-specified expression , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops.

[25]  Zhe Ming Lu,et al.  Early Fire Detection Based on Flame Contours in Video , 2010 .

[26]  Andreas Geiger,et al.  Vision meets robotics: The KITTI dataset , 2013, Int. J. Robotics Res..

[27]  Jian Wang,et al.  Multi-feature fusion based fast video flame detection , 2010 .

[28]  Simon Y. Foo.  A rule-based machine vision system for fire detection in aircraft dry bays and engine compartments , 1996, Knowl. Based Syst..

[29]  G. Griffin,et al.  Caltech-256 Object Category Dataset , 2007 .

[30]  Turgay Çelik,et al.  Fire and smoke detection without sensors: Image processing based approach , 2007, 2007 15th European Signal Processing Conference.

[31]  Vincenzo Piuri,et al.  Wildfire Smoke Detection Using Computational Intelligence Techniques Enhanced With Synthetic Smoke Plume Generation , 2013, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[32]  A. Enis Çetin,et al.  Wavelet based real-time smoke detection in video , 2005, 2005 13th European Signal Processing Conference.

[33]  Martin Mueller,et al.  Optical Flow Estimation for Flame Detection in Videos , 2013, IEEE Transactions on Image Processing.

[34]  B. Matthews.  Comparison of the predicted and observed secondary structure of T4 phage lysozyme. , 1975, Biochimica et biophysica acta.

[35]  Pietro Perona,et al.  Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[36]  Hélène Laurent,et al.  Investigation of a novel image segmentation method dedicated to forest fire applications , 2013 .

[37]  A. Enis Çetin,et al.  Real-time dynamic texture recognition using random sampling and dimension reduction , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[38]  Hakil Kim,et al.  Fast fire flame detection in surveillance video using logistic regression and temporal smoothing , 2016 .

[39]  A. Enis Çetin,et al.  Contour based smoke detection in video using wavelets , 2006, 2006 14th European Signal Processing Conference.

[40]  Hasan Demirel,et al.  Fire detection in video sequences using a generic color model , 2009 .

[41]  Hélène Laurent,et al.  A New Supervised Evaluation Criterion for Region Based Segmentation Methods , 2007, ACIVS.

[42]  ByoungChul Ko,et al.  Wildfire smoke detection using spatiotemporal bag-of-features of smoke , 2013, 2013 IEEE Workshop on Applications of Computer Vision (WACV).