Real Time Flood Detection, Alarm and Monitoring System Using Image Processing and Multiple Linear Regression

Authors: Lean Karlo S. Tolentino, Rochelynne E. Baron, Celestine Antoinette C. Blacer, Jose Miguel D. Aliswag, Dave Carlo E. De Guzman, John Bryan A. Fronda, Regina C. Valeriano, Jay Fel C. Quijano, Maria Victoria C. Padilla, Gilfred Allen M. Madrigal, Ira C. Valenzuela, Edmon O. Fernandez

Abstract

In the Philippines, flooding, which is typically produced by excessive rainfall and strong seas, is one of the most prevalent natural occurrences. This natural calamity cannot be avoided but the good thing is, we can practice ourselves to be prepared for it. After conducting an analysis regarding the needs of people residing in Barangay Frances, Calumpit, Bulacan, it was then decided to develop a project that can help lessen the difficulty they are experiencing when they evacuate. The system uses image processing as its flood detection method. It also uses several sensors for different purposes to make it more reliable to the users. These sensors used are the rain gauge, float switch, and flow rate meter sensor. It measures two of the important parameters in flood detection namely precipitation rate (mm/hr), flood level (ft), and the flow rate (L/hr). The data accumulated by the sensors are sent immediately to the Android application so it can be used by people living in the area to monitor the flood levels in real time. To measure the reliability of the system, the flood level taken from the automated system and conventional method were compared. A small mean squared error (MSE) of these 2 data which is 0.125 was achieved.