Flood areas detection based on UAV surveillance system

In this paper we propose a methodology for detection, localization, segmentation and size evaluation of flood areas from aerial images which are taken with drones. The approach is based on sliding box method and texture features analyses. The process of feature selection takes into account a performance degree obtained from false positive and false negative cases. We combined different properties of the images like color, texture and fractal types. A class of flood and one of non-flood were established based on clustering properties of some features and a criterion of similarity is used to segment the flood zones. Finally, the evaluation of the flood size is proposed. The method was tested on 10 images of flood zones and a rate of accuracy of 98.87% was obtained.

[1]  Michalis Zervakis,et al.  Feature analysis on river flow video data for floating tracers detection , 2014, 2014 IEEE International Conference on Imaging Systems and Techniques (IST) Proceedings.

[2]  M. B. Filho,et al.  ACCURACY OF LACUNARITY ALGORITHMS IN TEXTURE CLASSIFICATION OF HIGH SPATIAL RESOLUTION IMAGES FROM URBAN AREAS , 2008 .

[3]  Wail Gueaieb,et al.  A UAV based system for real time flash flood monitoring in desert environments using Lagrangian microsensors , 2013, 2013 International Conference on Unmanned Aircraft Systems (ICUAS).

[4]  Rajeev Sharma,et al.  Noncontact level sensing technique using computer vision , 2002, IEEE Trans. Instrum. Meas..

[5]  Wilhelm Burger,et al.  Digital Image Processing - An Algorithmic Introduction using Java , 2008, Texts in Computer Science.

[6]  Kevin Barraclough,et al.  I and i , 2001, BMJ : British Medical Journal.

[7]  J.C. Yang,et al.  Vision based Fire/Flood Alarm Surveillance System via Robust Detection Strategy , 2008, 2008 IEEE Instrumentation and Measurement Technology Conference.

[8]  Nirupam Sarkar,et al.  An Efficient Differential Box-Counting Approach to Compute Fractal Dimension of Image , 1994, IEEE Trans. Syst. Man Cybern. Syst..

[9]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[10]  Shi-Wei Lo,et al.  Cyber Surveillance for Flood Disasters , 2015, Sensors.

[11]  C. Metz.  Basic principles of ROC analysis. , 1978, Seminars in nuclear medicine.

[12]  Muhammad Faisal Khan,et al.  Segmentation and Classification Using Logistic Regression in Remote Sensing Imagery , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[13]  Keun-Chang Kwak,et al.  A Trends Analysis of Image Processing in Unmanned Aerial Vehicle , 2014 .

[14]  Loretta Ichim,et al.  Computer — Aided localization of the optic disc based on textural features , 2015, 2015 9th International Symposium on Advanced Topics in Electrical Engineering (ATEE).

[15]  Loretta Ichim,et al.  Sliding Box Method for Automated Detection of the Optic Disc and Macula in Retinal Images , 2015, IWBBIO.

[16]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[17]  Parwati Sofan,et al.  Detecting areas affected by flood using multi-temporal ALOS PALSAR remotely sensed data in Karawang, West Java, Indonesia , 2015, Natural Hazards.

[18]  Hans-Gerd Maas,et al.  AN AUTONOMOUS IMAGE BASED APPROACH FOR DETECTING GLACIAL LAKE OUTBURST FLOODS , 2014 .

[19]  William J. Emery,et al.  An automated flood detection framework for very high spatial resolution imagery , 2014, 2014 IEEE Geoscience and Remote Sensing Symposium.

[20]  Jean-François Crétaux,et al.  Water level estimation by remote sensing for the 2008 flooding of the Kosi River , 2014 .

[21]  Youngjoon Han,et al.  Embedded implementation of image-based water-level measurement system , 2011 .