Eye in the Sky: Drone Surveillance System

This drone surveillance system has been mainly developed to identify violent activities by individuals in large public areas. The system does so by first spotting each human in the image frame. Next, the body posture of each human is estimated which is then used to make a determination if two people are involved in violent activity.


Figure 1 :The Illustration shows the skeleton corresponding to the humans in an image. The angles (shown in green for few limbs) between the various limbs in this structure are used by the SVM to recognize the humans engaged in violent activities.

 

Figure 2 : The figure (left) illustrates the 14 body key-points annotated on the human body. The description of the human body points is as Facial Region (Purple): P1-Head, P2- Neck; Arms Region (Red): P3- Right shoulder, P4- Right Elbow, P5- Right Wrist, P6- Left Shoulder, P7- Left Elbow, P8- Left Wrist; Legs Region (Green): P9-Right Hip, P10- Right Knee, P11-Right Ankle, P12- Left Hip, P13- Left Knee, P14- Left Ankle. The figure (right) shows the Parrot AR Drone used to capture the images in the dataset and close-ups of few annotated keypoints.


 Dr. S N Omkar
Chief Research Scientist
Department of Aerospace Engineering

Amarjot Singh
PhD Student, University of cambridge

website URL: www.amarjotsingh.com , https://sites.google.com/site/compintellab/

Dr. S. N. Omkar (Aerospace Engineering, IISc) was interviewed by BBC about his work on recognizing violence in crowds using drone-computing