• Floods in India are turning more severe, unpredictable and rather intractable. Number of urban floods is on the rise mainly due to poor drainage and encroachment of old water bodies of cities and towns.
   

• Unmanned Aerial Vehicles (UAVs) or drones are often used to reach remote areas or regions which are inaccessible to humans. Equipped with a large field of view, compact size, and remote control abilities, drones are deemed suitable for monitoring crowded or disaster-hit areas, and performing aerial surveillance. While research has focused on area monitoring, object detection and tracking, limited attention has been given to person identification, especially face recognition, using drones.
   

• To the best of our knowledge, limited attention has been given to the challenging yet important application of drone based face recognition. Automating the process of face recognition or tracking using drones can greatly benefit surveillance and remote monitoring scenarios

​

• Drone based face recognition brings with it a new set of challenges such as the effect of motion, pose, illumination, background, and height. The presence of these challenges, along with the relatively lower resolution of captured faces, varying distance between the drone and the subjects, the problem of drone based face recognition is thus rendered further challenging.

    
  
 

​

​

​

​

​

​

​

​

​

​

​

​

​

      USE OF FACE DETECTION  

     Use of face detection technique post floods:

⦁    Face detection datasets recognize tasks such as progression/regression, landmark localization, etc⦁    . https://susanqq.github.io/UTKFace/

⦁    After the flood crisis there will be devastating loss for human mankind. During the floods most of the people will be drowned, died, injured. Also sometimes it so happens that injured people will be rescued by the rescuers , but it becomes difficult to identify their faces due to facial injury, etc. 

​

• In order to detect the faces , high end face detection technique can be used .Wherein aerial view of their face will be taken and it will be stored in database. There training and testing of datasets takes place using machine learning or deep learning. Data will be trained based on the previous input images. 

⦁    Then the relatives/friends of particular person leaving in safe zone around flooded area can soon pick up him/her from the flooded place and can shift them to their place if the situation after the flood is too worst.

⦁    Drone face detection technique can also be used to find out the missing person drowned in flood. Drones can be used for more precision to find out the people struck under building debris, etc. 

⦁    In this way more loss of lives can be prevented.
Thermal Imaging :-
The unmanned air vehicle will consists of two cameras:
⦁    Face Detection.
⦁    Thermal Camera.

The face detection is used to detect the faces of people stuck whereas thermal camera detects the faces in dark vision. 
Inference :- In this We can save people  who are note even seen by the rescuers.

 

 

 

 

 

​